Tootfinder

$\ell_{1}^{2}-\eta\ell_{2}^{2}$ sparsity regularization for nonlinear ill-posed problems
Long Li, Liang Ding
https://arxiv.org/abs/2508.16163 https://arxiv…

$\ell_{1}^{2}-η\ell_{2}^{2}$ sparsity regularization for nonlinear ill-posed problems
In this study, we investigate the $\left\|\cdot\right\|_{\ell_{1}}^{2}-η\left\|\cdot\right\|_{\ell_{2}}^{2}$ sparsity regularization with $0< η\leq 1$, in the context of nonlinear ill-posed inverse problems. We focus on the examination of the well-posedness associated with this regularization approach. Notably, the case where $η=1$ presents weaker theoretical outcomes than $0< η<1$, primarily due to the absence of coercivity and the Radon-Riesz property associated with t…

Papanicolaou Stain Unmixing for RGB Image Using Weighted Nucleus Sparsity and Total Variation Regularization
Nanxin Gong, Saori Takeyama, Masahiro Yamaguchi, Takumi Urata, Fumikazu Kimura, Keiko Ishii
https://arxiv.org/abs/2506.20450

Papanicolaou Stain Unmixing for RGB Image Using Weighted Nucleus Sparsity and Total Variation Regularization
The Papanicolaou stain, consisting of eosin Y, hematoxylin, light Green SF yellowish, orange G, and Bismarck brown Y, provides extensive color information essential for cervical cancer screening in cytopathology. However, the visual observation of these colors is subjective and difficult to characterize. In digital image analysis, the RGB intensities are affected by staining and imaging variations, hindering direct quantification of color in Papanicolaou-stained samples. Stain unmixing is a pro…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/3]:
- Adaptive Multi-Order Graph Regularized NMF with Dual Sparsity for Hyperspectral Unmixing
Hui Chen, Liangyu Liu, Xianchao Xiu, Wanquan Liu

Generation of Synthetic Clinical Text: A Systematic Review
Basel Alshaikhdeeb, Ahmed Abdelmonem Hemedan, Soumyabrata Ghosh, Irina Balaur, Venkata Satagopam
https://arxiv.org/abs/2507.18451

Generation of Synthetic Clinical Text: A Systematic Review
Generating clinical synthetic text represents an effective solution for common clinical NLP issues like sparsity and privacy. This paper aims to conduct a systematic review on generating synthetic medical free-text by formulating quantitative analysis to three research questions concerning (i) the purpose of generation, (ii) the techniques, and (iii) the evaluation methods. We searched PubMed, ScienceDirect, Web of Science, Scopus, IEEE, Google Scholar, and arXiv databases for publications asso…

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
David Chanin, Adri\`a Garriga-Alonso
https://arxiv.org/abs/2508.16560 https://

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to single concepts. A core SAE training hyperparameter is L0: how many features should fire per token on average. Existing work compares SAE algorithms using sparsity--reconstruction tradeoff plots, implying L0 is a free parameter with no single correct value. In this work we study the effect of L0 on BatchTopK SAEs, and show that if L0 is not set precisely, the SAE fails to learn the underlying featu…

from my link log —
NaN-propagation: a novel method for sparsity detection in black-box computational functions.
https://arxiv.org/abs/2507.23186
saved 2025-08-14

NaN-Propagation: A Novel Method for Sparsity Detection in Black-Box Computational Functions
When numerically evaluating a function's gradient, sparsity detection can enable substantial computational speedups through Jacobian coloring and compression. However, sparsity detection techniques for black-box functions are limited, and existing finite-difference-based methods suffer from false negatives due to coincidental zero gradients. These false negatives can silently corrupt gradient calculations, leading to difficult-to-diagnose errors. We introduce NaN-propagation, which exploits the…

Scalable Subset Selection in Linear Mixed Models
Ryan Thompson, Matt P. Wand, Joanna J. J. Wang
https://arxiv.org/abs/2506.20425 https://

Scalable Subset Selection in Linear Mixed Models
Linear mixed models (LMMs), which incorporate fixed and random effects, are key tools for analyzing heterogeneous data, such as in personalized medicine or adaptive marketing. Nowadays, this type of data is increasingly wide, sometimes containing thousands of candidate predictors, necessitating sparsity for prediction and interpretation. However, existing sparse learning methods for LMMs do not scale well beyond tens or hundreds of predictors, leaving a large gap compared with sparse methods fo…

WebGuard :Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERT
Ye Tian, Zhang Yumin, Yifan Jia, Jianguo Sun, Yanbin Wang
https://arxiv.org/abs/2506.19356

WebGuard++:Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERT
URL+HTML feature fusion shows promise for robust malicious URL detection, since attacker artifacts persist in DOM structures. However, prior work suffers from four critical shortcomings: (1) incomplete URL modeling, failing to jointly capture lexical patterns and semantic context; (2) HTML graph sparsity, where threat-indicative nodes (e.g., obfuscated scripts) are isolated amid benign content, causing signal dilution during graph aggregation; (3) unidirectional analysis, ignoring URL-HTML feat…

Modeling User Preferences as Distributions for Optimal Transport-based Cross-domain Recommendation under Non-overlapping Settings
Ziyin Xiao, Toyotaro Suzumura
https://arxiv.org/abs/2508.16210

Modeling User Preferences as Distributions for Optimal Transport-based Cross-domain Recommendation under Non-overlapping Settings
Cross-Domain Recommender (CDR) systems aim to transfer knowledge from dense to sparse domains, alleviating data sparsity and cold-start issues in single-domain recommendation. While many methods assume overlapping users or items to connect domains, this is often unrealistic in real-world settings. Thus, non-overlapping CDR systems, which require no shared users or items, are needed. However, non-overlapping CDR is challenging due to: (1) the absence of overlap preventing direct bridges betwee…

Revisiting CHAMPAGNE: Sparse Bayesian Learning as Reweighted Sparse Coding
Dylan Sechet, Matthieu Kowalski, Samy Mokhtari, Bruno Torr\'esani
https://arxiv.org/abs/2506.20534

Revisiting CHAMPAGNE: Sparse Bayesian Learning as Reweighted Sparse Coding
This paper revisits the CHAMPAGNE algorithm within the Sparse Bayesian Learning (SBL) framework and establishes its connection to reweighted sparse coding. We demonstrate that the SBL objective can be reformulated as a reweighted $\ell_{21}$-minimization problem, providing a more straightforward interpretation of the sparsity mechanism and enabling the design of an efficient iterative algorithm. Additionally, we analyze the behavior of this reformulation in the low signal-to-noise ratio (SNR) r…

A Sparsity-Aware Autonomous Path Planning Accelerator with HW/SW Co-Design and Multi-Level Dataflow Optimization
Yifan Zhang, Xiaoyu Niu, Hongzheng Tian, Yanjun Zhang, Bo Yu, Shaoshan Liu, Sitao Huang
https://arxiv.org/abs/2507.16177

A Sparsity-Aware Autonomous Path Planning Accelerator with HW/SW Co-Design and Multi-Level Dataflow Optimization
Path planning is critical for autonomous driving, generating smooth, collision-free, feasible paths based on perception and localization inputs. However, its computationally intensive nature poses significant challenges for resource-constrained autonomous driving hardware. This paper presents an end-to-end FPGA-based acceleration framework targeting the quadratic programming (QP), core of optimization-based path planning. We employ a hardware-friendly alternating direction method of multipliers…

Hybrid Near-Far Field 6D Movable Antenna Design Exploiting Directional Sparsity and Deep Learning
Xiaodan Shao, Limei Hu, Yulong Sun, Xing Li, Yixiao Zhang, Jingze Ding, Xiaoming Shi, Feng Chen, Derrick Wing Kwan Ng, Robert Schober
https://arxiv.org/abs/2506.15808

Hybrid Near-Far Field 6D Movable Antenna Design Exploiting Directional Sparsity and Deep Learning
Six-dimensional movable antenna (6DMA) has been identified as a new disruptive technology for future wireless systems to support a large number of users with only a few antennas. However, the intricate relationships between the signal carrier wavelength and the transceiver region size lead to inaccuracies in traditional far-field 6DMA channel model, causing discrepancies between the model predictions and the hybrid-field channel characteristics in practical 6DMA systems, where users might be in…

Accelerating Correlated Wave Function Calculations with Hierarchical Matrix Compression of the Two-Electron Integrals
Hongji Gao, Xiangmin Jiao, Benjamin G. Levine
https://arxiv.org/abs/2506.16576

Accelerating Correlated Wave Function Calculations with Hierarchical Matrix Compression of the Two-Electron Integrals
Leveraging matrix sparsity has proven a fruitful strategy for accelerating quantum chemical calculations. Here we present the hierarchical SOS-MP2 algorithm, which uses hierarchical matrix ($\mathcal{H}^{2}$) compression of the electron repulsion integral (ERI) tensor to reduce both time and space complexity. This approach is based on the atomic orbital Laplace transform MP2 calculations, leveraging the data sparsity of the ERI tensor and the element-wise sparsity of the energy-weighted density…

GRASP: Grouped Regression with Adaptive Shrinkage Priors
Shu Yu Tew, Daniel F. Schmidt, Mario Boley
https://arxiv.org/abs/2506.18092 https://

GRASP: Grouped Regression with Adaptive Shrinkage Priors
We introduce GRASP, a simple Bayesian framework for regression with grouped predictors, built on the normal beta prime (NBP) prior. The NBP prior is an adaptive generalization of the horseshoe prior with tunable hyperparameters that control tail behavior, enabling a flexible range of sparsity, from strong shrinkage to ridge-like regularization. Unlike prior work that introduced the group inverse-gamma gamma (GIGG) prior by decomposing the NBP prior into structured hierarchies, we show that dire…

BitWave: Exploiting Column-Based Bit-Level Sparsity for Deep Learning Acceleration
Man Shi, Vikram Jain, Antony Joseph, Maurice Meijer, Marian Verhelst
https://arxiv.org/abs/2507.12444

BitWave: Exploiting Column-Based Bit-Level Sparsity for Deep Learning Acceleration
Bit-serial computation facilitates bit-wise sequential data processing, offering numerous benefits, such as a reduced area footprint and dynamically-adaptive computational precision. It has emerged as a prominent approach, particularly in leveraging bit-level sparsity in Deep Neural Networks (DNNs). However, existing bit-serial accelerators exploit bit-level sparsity to reduce computations by skipping zero bits, but they suffer from inefficient memory accesses due to the irregular indices of th…

Enhancing Compiler Optimization Efficiency through Grammatical Decompositions of Control-Flow Graphs
Xuran Cai
https://arxiv.org/abs/2507.16660 https://

Enhancing Compiler Optimization Efficiency through Grammatical Decompositions of Control-Flow Graphs
This thesis addresses the complexities of compiler optimizations, such as register allocation and Lifetime-optimal Speculative Partial Redundancy Elimination (LOSPRE), which are often handled using tree decomposition algorithms. However, these methods frequently overlook important sparsity aspects of Control Flow Graphs (CFGs) and result in high computational costs. We introduce the SPL (Series-Parallel-Loop) decomposition, a novel framework that offers optimal solutions to these challenges. A …

On Balancing Sparsity with Reliable Connectivity in Distributed Network Design with Random K-out Graphs
Mansi Sood, Eray Can Elumar, Osman Yagan
https://arxiv.org/abs/2508.11863

On Balancing Sparsity with Reliable Connectivity in Distributed Network Design with Random K-out Graphs
In several applications in distributed systems, an important design criterion is ensuring that the network is sparse, i.e., does not contain too many edges, while achieving reliable connectivity. Sparsity ensures communication overhead remains low, while reliable connectivity is tied to reliable communication and inference on decentralized data reservoirs and computational resources. A class of network models called random K-out graphs appear widely as a heuristic to balance connectivity and sp…

Recovery Thresholding Hyperinterpolations in Signal Processing
Congpei An, Jiashu Ran
https://arxiv.org/abs/2507.17916 https://arxiv.org/pdf/2507.17916

Recovery Thresholding Hyperinterpolations in Signal Processing
This paper introduces recovery thresholding hyperinterpolations, a novel class of methods for sparse signal reconstruction in the presence of noise. We develop a framework that integrates thresholding operators--including hard thresholding, springback, and Newton thresholding--directly into the hyperinterpolation structure to maintain sparsity during signal recovery. Our approach leverages Newton's method to minimize one-dimensional nonconvex functions, which we then extend to solve multivariab…

Sparsity of the Main Effect Matrix Factor Model
Zetai Cen, Kaixin Liu, Clifford Lam
https://arxiv.org/abs/2508.12510 https://arxiv.org/pdf/2508.12510

Sparsity of the Main Effect Matrix Factor Model
We introduce sparsity detection and estimation in main effect matrix factor models for matrix-valued time series. A carefully chosen set of identification conditions for the common component and the potentially nonstationary main effects is proposed to strengthen the interpretations of sparse main effects, while estimators of all model components are presented. Sparse estimation of the latent main effects is proposed using a doubly adaptive fused lasso estimation to allow for sparse sub-block d…

Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models
Andrii Balashov
https://arxiv.org/abs/2507.17107 https://

Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models
Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we challenge this assumption with a surprising finding: RL fine-tuning consistently modifies only a small subnetwork (typically 5-30% of weights), leaving most parameters unchanged. We call this phenomenon RL-induced parameter update sparsity. It arises naturall…

Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
Qirui Li, Guangcong Zheng, Qi Zhao, Jie Li, Bin Dong, Yiwu Yao, Xi Li
https://arxiv.org/abs/2508.12969

Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse patterns, fail to fully exploit the inherent spatio-temporal redundancies in video data. Through systematic analysis of video diffusion transformers (DiT), we uncover a key insight: Attention matrices exhibit structured, yet heterogeneous sparsity patterns, whe…

SVD method for sparse recovery
Long Li, Liang Ding
https://arxiv.org/abs/2506.11379 https://arxiv.org/pdf/2506.11379

SVD method for sparse recovery
Sparsity regularization has garnered significant interest across multiple disciplines, including statistics, imaging, and signal processing. Standard techniques for addressing sparsity regularization include iterative soft thresholding algorithms and their accelerated variants. However, these algorithms rely on Landweber iteration, which can be computationally intensive. Therefore, there is a pressing need to develop a more efficient algorithm for sparsity regularization. The Singular Value Dec…

Fast Flexible LSQR with a Hybrid Variant for Efficient Large-Scale Regularization
Eva Miku\v{s}ov\'a, Iveta Hn\v{e}tynkov\'a
https://arxiv.org/abs/2506.19666

Fast Flexible LSQR with a Hybrid Variant for Efficient Large-Scale Regularization
A wide range of applications necessitates solving large-scale ill-posed problems contaminated by noise. Krylov subspace regularization methods are particularly advantageous in this context, as they rely solely on matrix-vector multiplication. Among the most widely used techniques are LSQR and CGLS, both of which can be extended with flexible preconditioning to enforce solution properties such as nonnegativity or sparsity. Flexible LSQR (FLSQR) can also be further combined with direct methods to…

Enhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement
Yuhan Wang, Qing Xie, Zhifeng Bao, Mengzi Tang, Lin Li, Yongjian Liu
https://arxiv.org/abs/2507.17112

Enhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement
Cross-domain recommendation (CDR) aims to alleviate the data sparsity by transferring knowledge across domains. Disentangled representation learning provides an effective solution to model complex user preferences by separating intra-domain features (domain-shared and domain-specific features), thereby enhancing robustness and interpretability. However, disentanglement-based CDR methods employing generative modeling or GNNs with contrastive objectives face two key challenges: (i) pre-separation…

The $3$-sparsity of $X^n-1$ over finite fields, II
Kaimin Cheng
https://arxiv.org/abs/2507.10779 https://arxiv.org/pdf/2507.10779

The $3$-sparsity of $X^n-1$ over finite fields, II
Let $q$ be a prime power and $\mathbb{F}_q$ the finite field with $q$ elements. For a positive integer $n$, the polynomial $X^n - 1 \in \mathbb{F}_q[X]$ is termed $3$-sparse over $\mathbb{F}_q$ if all its irreducible factors in $\mathbb{F}_q[X]$ are either binomials or trinomials. In 2021, Oliveira and Reis characterized all positive integers $n$ for which $X^n - 1$ is 3-sparse over $\mathbb{F}_q$ when $q = 2$ and $q = 4$. Recently, the author provided a complete characterization for odd $q$. T…

Dyadic data with ordered outcome variables
Chris Muris, Cavit Pakel, Qichen Zhang
https://arxiv.org/abs/2507.16689 https://arxiv.org/…

Dyadic data with ordered outcome variables
We consider ordered logit models for directed network data that allow for flexible sender and receiver fixed effects that can vary arbitrarily across outcome categories. This structure poses a significant incidental parameter problem, particularly challenging under network sparsity or when some outcome categories are rare. We develop the first estimation method for this setting by extending tetrad-differencing conditional maximum likelihood (CML) techniques from binary choice network models. Th…

SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation
Qi Li, Kun Li, Haozhi Han, Liang Yuan, Junshi Chen, Yunquan Zhang, Yifeng Chen, Hong An, Ting Cao, Mao Yang
https://arxiv.org/abs/2506.22969

SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation
Sparse Tensor Cores offer exceptional performance gains for AI workloads by exploiting structured 2:4 sparsity. However, their potential remains untapped for core scientific workloads such as stencil computations, which exhibit irregular sparsity patterns.This paper presents SparStencil, the first system to retarget sparse TCUs for scientific stencil computations through structured sparsity transformation. SparStencil introduces three key techniques: (1) Adaptive Layout Morphing, which restruct…

From Local Interactions to Global Operators: Scalable Gaussian Process Operator for Physical Systems
Sawan Kumar, Tapas Tripura, Rajdip Nayek, Souvik Chakraborty
https://arxiv.org/abs/2506.15906

From Local Interactions to Global Operators: Scalable Gaussian Process Operator for Physical Systems
Operator learning offers a powerful paradigm for solving parametric partial differential equations (PDEs), but scaling probabilistic neural operators such as the recently proposed Gaussian Processes Operators (GPOs) to high-dimensional, data-intensive regimes remains a significant challenge. In this work, we introduce a novel, scalable GPO, which capitalizes on sparsity, locality, and structural information through judicious kernel design. Addressing the fundamental limitation of cubic computat…

Exact versus Approximate Representations of Boolean Functions in the De Morgan Basis
Arkadev Chattopadhyay, Yogesh Dahiya, Shachar Lovett
https://arxiv.org/abs/2507.13963

Exact versus Approximate Representations of Boolean Functions in the De Morgan Basis
A seminal result of Nisan and Szegedy (STOC, 1992) shows that for any total Boolean function, the degree of the real polynomial that computes the function, and the minimal degree of a real polynomial that point-wise approximates the function, are at most polynomially separated. Extending this result from degree to other complexity measures like sparsity of the polynomial representation, or total weight of the coefficients, remains poorly understood. In this work, we consider this problem in t…

Extracting transient Koopman modes from short-term weather simulations with sparsity-promoting dynamic mode decomposition
Zhicheng Zhang, Yoshihiko Susuki, Atsushi Okazaki
https://arxiv.org/abs/2506.14083

Extracting transient Koopman modes from short-term weather simulations with sparsity-promoting dynamic mode decomposition
Convective features-here represented as warm bubble-like patterns-reveal essential, high-level information about how short-term weather dynamics evolve within a high-dimensional state space. We introduce a data-driven framework that uncovers transient dynamics captured by Koopman modes responsible for these structures and traces their emergence, growth, and decay. Our approach incorporates the sparsity-promoting dynamic mode decomposition into the framework of Koopman mode decomposition, yieldi…

Quantum Error Correction Exploiting Degeneracy to Approach the Hashing Bound
Kenta Kasai
https://arxiv.org/abs/2506.15636 https://arx…

Quantum Error Correction Exploiting Degeneracy to Approach the Hashing Bound
Quantum error correction is essential for realizing scalable quantum computation. Among various approaches, low-density parity-check codes over higher-order Galois fields have shown promising performance due to their structured sparsity and compatibility with iterative decoding algorithms whose computational complexity scales linearly with the number of physical qubits. In this work, we demonstrate that explicitly exploiting the degeneracy of quantum errors can significantly enhance the decodin…

Dynamic mode decomposition for detecting transient activity via sparsity and smoothness regularization
Yutaro Tanaka, Hiroya Nakao
https://arxiv.org/abs/2508.10266 https://

Dynamic mode decomposition for detecting transient activity via sparsity and smoothness regularization
Dynamic Mode Decomposition (DMD) is a data-driven modal decomposition technique that extracts coherent spatio-temporal structures from high-dimensional time-series data. By decomposing the dynamics into a set of modes, each associated with a single frequency and a growth rate, DMD enables a natural modal decomposition and dimensionality reduction of complex dynamical systems. However, when DMD is applied to transient dynamics, even if a large number of modes are used, it remains difficult to in…

PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching
Haotong Du, Yaqing Wang, Fei Xiong, Lei Shao, Ming Liu, Hao Gu, Quanming Yao, Zhen Wang
https://arxiv.org/abs/2506.18382

PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching
With the expansion of business scales and scopes on online platforms, multi-scenario matching has become a mainstream solution to reduce maintenance costs and alleviate data sparsity. The key to effective multi-scenario recommendation lies in capturing both user preferences shared across all scenarios and scenario-aware preferences specific to each scenario. However, existing methods often overlook user-specific modeling, limiting the generation of personalized user representations. To address …

Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity
Niloofar Asefi, Leonard Lupin-Jimenez, Tianning Wu, Ruoying He, Ashesh Chattopadhyay
https://arxiv.org/abs/2507.06479

Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity
Reconstructing ocean dynamics from observational data is fundamentally limited by the sparse, irregular, and Lagrangian nature of spatial sampling, particularly in subsurface and remote regions. This sparsity poses significant challenges for forecasting key phenomena such as eddy shedding and rogue waves. Traditional data assimilation methods and deep learning models often struggle to recover mesoscale turbulence under such constraints. We leverage a deep learning framework that combines neural…

IzhiRISC-V -- a RISC-V-based Processor with Custom ISA Extension for Spiking Neuron Networks Processing with Izhikevich Neurons
Wiktor J. Szczerek, Artur Podobas
https://arxiv.org/abs/2508.12846

IzhiRISC-V -- a RISC-V-based Processor with Custom ISA Extension for Spiking Neuron Networks Processing with Izhikevich Neurons
Spiking Neural Network processing promises to provide high energy efficiency due to the sparsity of the spiking events. However, when realized on general-purpose hardware -- such as a RISC-V processor -- this promise can be undermined and overshadowed by the inefficient code, stemming from repeated usage of basic instructions for updating all the neurons in the network. One of the possible solutions to this issue is the introduction of a custom ISA extension with neuromorphic instructions for s…

Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
Sangwoo Jeon, Juchul Shin, Gyeong-Tae Kim, YeonJe Cho, Seongwoo Kim
https://arxiv.org/abs/2508.10747

Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
Generalized planning using deep reinforcement learning (RL) combined with graph neural networks (GNNs) has shown promising results in various symbolic planning domains described by PDDL. However, existing approaches typically represent planning states as fully connected graphs, leading to a combinatorial explosion in edge information and substantial sparsity as problem scales grow, especially evident in large grid-based environments. This dense representation results in diluted node-level infor…

This https://arxiv.org/abs/2505.12453 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
Federated recommender system (FedRec) has emerged as a solution to protect user data through collaborative training techniques. A typical FedRec involves transmitting the full model and entire weight updates between edge devices and the server, causing significant burdens to devices with limited bandwidth and computational power. While the sparsity of embedding updates provides opportunity for payload optimization, existing sparsity-aware federated protocols generally sacrifice privacy for effi…

This https://arxiv.org/abs/2505.14884 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
Accelerating large language model (LLM) inference is critical for real-world deployments requiring high throughput and low latency. Contextual sparsity, where each token dynamically activates only a small subset of the model parameters, shows promise but does not scale to large batch sizes due to union of active neurons quickly approaching dense computation. We introduce Polar Sparsity, highlighting a key shift in sparsity importance from MLP to Attention layers as we scale batch size and seque…

Approximate Sparsity Class and Minimax Estimation
Lucas Z. Zhang
https://arxiv.org/abs/2508.09278 https://arxiv.org/pdf/2508.09278

Approximate Sparsity Class and Minimax Estimation
Motivated by the orthogonal series density estimation in $L^2([0,1],μ)$, in this project we consider a new class of functions that we call the approximate sparsity class. This new class is characterized by the rate of decay of the individual Fourier coefficients for a given orthonormal basis. We establish the $L^2([0,1],μ)$ metric entropy of such class, with which we show the minimax rate of convergence. For the density subset in this class, we propose an adaptive density estimator based on a…

Optimal Exact Designs of Multiresponse Experiments under Linear and Sparsity Constraints
Lenka Filov\'a, P\'al Somogyi, Radoslav Harman
https://arxiv.org/abs/2507.04713

Optimal Exact Designs of Multiresponse Experiments under Linear and Sparsity Constraints
We propose a computational approach to constructing exact designs on finite design spaces that are optimal for multiresponse regression experiments under a combination of the standard linear and specific 'sparsity' constraints. The linear constraints address, for example, limits on multiple resource consumption and the problem of optimal design augmentation, while the sparsity constraints control the set of distinct trial conditions utilized by the design. The key idea is to construct an artifi…

Distribution-Guided Auto-Encoder for User Multimodal Interest Cross Fusion
Moyu Zhang, Yongxiang Tang, Yujun Jin, Jinxin Hu, Yu Zhang
https://arxiv.org/abs/2508.14485 https://…

Distribution-Guided Auto-Encoder for User Multimodal Interest Cross Fusion
Traditional recommendation methods rely on correlating the embedding vectors of item IDs to capture implicit collaborative filtering signals to model the user's interest in the target item. Consequently, traditional ID-based methods often encounter data sparsity problems stemming from the sparse nature of ID features. To alleviate the problem of item ID sparsity, recommendation models incorporate multimodal item information to enhance recommendation accuracy. However, existing multimodal recomm…

Learning Sparsity for Effective and Efficient Music Performance Question Answering
Xingjian Diao, Tianzhen Yang, Chunhui Zhang, Weiyi Wu, Ming Cheng, Jiang Gui
https://arxiv.org/abs/2506.01319

Learning Sparsity for Effective and Efficient Music Performance Question Answering
Music performances, characterized by dense and continuous audio as well as seamless audio-visual integration, present unique challenges for multimodal scene understanding and reasoning. Recent Music Performance Audio-Visual Question Answering (Music AVQA) datasets have been proposed to reflect these challenges, highlighting the continued need for more effective integration of audio-visual representations in complex question answering. However, existing Music AVQA methods often rely on dense and…

Topolow: Force-Directed Euclidean Embedding of Dissimilarity Data with Robustness Against Non-Metricity and Sparsity
Omid Arhami, Pejman Rohani
https://arxiv.org/abs/2508.01733 …

Topolow: Force-Directed Euclidean Embedding of Dissimilarity Data with Robustness Against Non-Metricity and Sparsity
The problem of embedding a set of objects into a low-dimensional Euclidean space based on a matrix of pairwise dissimilarities is fundamental in data analysis, machine learning, and statistics. However, the assumptions of many standard analytical methods are violated when the input dissimilarities fail to satisfy metric or Euclidean axioms. We present the mathematical and statistical foundations of Topolow, a physics-inspired, gradient-free optimization framework for such embedding problems. To…

HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap
Wenxiang Lin, Xinglin Pan, Lin Zhang, Shaohuai Shi, Xuan Wang, Xiaowen Chu
https://arxiv.org/abs/2508.09591

HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap
The sparsely activated mixture-of-experts (MoE) transformer has become a common architecture for large language models (LLMs) due to its sparsity, which requires fewer computational demands while easily scaling the model size. In MoE models, each MoE layer requires to dynamically choose tokens to activate particular experts for computation while the activated experts may not be located in the same device or GPU as the token. However, this leads to substantial communication and load imbalances a…

VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration
Shereef Helal, Alberto Garcia-Ortiz, Lennart Bamberg
https://arxiv.org/abs/2506.01166

VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration
Leveraging high degrees of unstructured sparsity is a promising approach to enhance the efficiency of deep neural network DNN accelerators - particularly important for emerging Edge-AI applications. We introduce VUSA, a systolic-array architecture that virtually grows based on the present sparsity to perform larger matrix multiplications with the same number of physical multiply-accumulate MAC units. The proposed architecture achieves saving by 37% and 68% in area and power efficiency, respecti…

Replaced article(s) found for cs.PF. https://arxiv.org/list/cs.PF/new
[1/1]:
- SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
Mohammad Mozaffari, Amir Yazdanbakhsh, Maryam Mehri Dehnavi

The $3$-sparsity of $X^n-1$ over finite fields
Kaimin Cheng
https://arxiv.org/abs/2507.06655 https://arxiv.org/pdf/2507.06655

The $3$-sparsity of $X^n-1$ over finite fields
Let $q$ be a prime power and $\mathbb{F}_q$ the finite field with $q$ elements. For a positive integer $n$, the binomial $f_n(X):= X^n-1\in\mathbb{F}_q[X]$ is called $3$-sparse over $\mathbb{F}_q$ if each irreducible factor of $f_n(X)$ over $\mathbb{F}_q$ is either a binomial or a trinomial. In 2021, Oliveira and Reis characterized all positive integers $n$ for which $f_n(X)$ is $3$-sparse over $\mathbb{F}_q$ when $q = 2$ and $q = 4$, and posed the open problem of whether, for any given $q$, th…

Sparsity and Total Variation Constrained Multilayer Linear Unmixing for Hyperspectral Imagery
Gang Yang
https://arxiv.org/abs/2508.03403 https://arxiv.org/…

Sparsity and Total Variation Constrained Multilayer Linear Unmixing for Hyperspectral Imagery
Hyperspectral unmixing aims at estimating material signatures (known as endmembers) and the corresponding proportions (referred to abundances), which is a critical preprocessing step in various hyperspectral imagery applications. This study develops a novel approach called sparsity and total variation (TV) constrained multilayer linear unmixing (STVMLU) for hyperspectral imagery. Specifically, based on a multilayer matrix factorization model, to improve the accuracy of unmixing, a TV constraint…

Iterative Augmentation with Summarization Refinement (IASR) Evaluation for Unstructured Survey data Modeling and Analysis
Payal Bhattad, Sai Manoj Pudukotai Dinakarrao, Anju Gupta
https://arxiv.org/abs/2507.12126

Iterative Augmentation with Summarization Refinement (IASR) Evaluation for Unstructured Survey data Modeling and Analysis
Text data augmentation is a widely used strategy for mitigating data sparsity in natural language processing (NLP), particularly in low-resource settings where limited samples hinder effective semantic modeling. While augmentation can improve input diversity and downstream interpretability, existing techniques often lack mechanisms to ensure semantic preservation during large-scale or iterative generation, leading to redundancy and instability. This work introduces a principled evaluation frame…

Crosslisted article(s) found for cs.IT. https://arxiv.org/list/cs.IT/new
[1/1]:
- On Balancing Sparsity with Reliable Connectivity in Distributed Network Design with Random K-out ...
Mansi Sood, Eray Can Elumar, Osman Yagan

Efficient Canonical Correlation Analysis with Sparsity
Zixuan Wu, Elena Tuzhilina, Claire Donnat
https://arxiv.org/abs/2507.11160 https://

Efficient Canonical Correlation Analysis with Sparsity
In high-dimensional settings, Canonical Correlation Analysis (CCA) often fails, and existing sparse methods force an untenable choice between computational speed and statistical rigor. This work introduces a fast and provably consistent sparse CCA algorithm (ECCAR) that resolves this trade-off. We formulate CCA as a high-dimensional reduced-rank regression problem, which allows us to derive consistent estimators with high-probability error bounds without relying on computationally expensive tec…

Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
William de Vazelhes, Xiao-Tong Yuan, Bin Gu
https://arxiv.org/abs/2506.08558

Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
In sparse optimization, enforcing hard constraints using the $\ell_0$ pseudo-norm offers advantages like controlled sparsity compared to convex relaxations. However, many real-world applications demand not only sparsity constraints but also some extra constraints. While prior algorithms have been developed to address this complex scenario with mixed combinatorial and convex constraints, they typically require the closed form projection onto the mixed constraints which might not exist, and/or on…

Intrinsic and Extrinsic Organized Attention: Softmax Invariance and Network Sparsity
Oluwadamilola Fasina, Ruben V. C. Pohle, Pei-Chun Su, Ronald R. Coifman
https://arxiv.org/abs/2506.15541

Intrinsic and Extrinsic Organized Attention: Softmax Invariance and Network Sparsity
We examine the intrinsic (within the attention head) and extrinsic (amongst the attention heads) structure of the self-attention mechanism in transformers. Theoretical evidence for invariance of the self-attention mechanism to softmax activation is obtained by appealing to paradifferential calculus, (and is supported by computational examples), which relies on the intrinsic organization of the attention heads. Furthermore, we use an existing methodology for hierarchical organization of tensors …

SparseEMG: Computational Design of Sparse EMG Layouts for Sensing Gestures
Anand Kumar, Antony Albert Raj Irudayaraj, Ishita Chandra, Adwait Sharma, Aditya Shekhar Nittala
https://arxiv.org/abs/2508.05098

SparseEMG: Computational Design of Sparse EMG Layouts for Sensing Gestures
Gesture recognition with electromyography (EMG) is a complex problem influenced by gesture sets, electrode count and placement, and machine learning parameters (e.g., features, classifiers). Most existing toolkits focus on streamlining model development but overlook the impact of electrode selection on classification accuracy. In this work, we present the first data-driven analysis of how electrode selection and classifier choice affect both accuracy and sparsity. Through a systematic evaluatio…

A New Perspective of the Meese-Rogoff Puzzle: Application of Sparse Dynamic Shrinkage
Zheng Fan, Worapree Maneesoonthorn, Yong Song
https://arxiv.org/abs/2507.14408

A New Perspective of the Meese-Rogoff Puzzle: Application of Sparse Dynamic Shrinkage
We propose the Markov Switching Dynamic Shrinkage process (MSDSP), nesting the Dynamic Shrinkage Process (DSP) of Kowal et al. (2019). We revisit the Meese-Rogoff puzzle (Meese and Rogoff, 1983a,b, 1988) by applying the MSDSP to the economic models deemed inferior to the random walk model for exchange rate predictions. The flexibility of the MSDSP model captures the possibility of zero coefficients (sparsity), constant coefficient (dynamic shrinkage), as well as sudden and gradual parameter mov…

Sparsity-Promoting Dynamic Mode Decomposition Applied to Sea Surface Temperature Fields
Zhicheng Zhang, Yoshihiko Susuki, Atsushi Okazaki
https://arxiv.org/abs/2507.05711

Sparsity-Promoting Dynamic Mode Decomposition Applied to Sea Surface Temperature Fields
In this paper, we leverage Koopman mode decomposition to analyze the nonlinear and high-dimensional climate systems acting on the observed data space. The dynamics of atmospheric systems are assumed to be equation-free, with the linear evolution of observables derived from measured historical long-term time-series data snapshots, such as monthly sea surface temperature records, to construct a purely data-driven climate dynamics. In particular, sparsity-promoting dynamic mode decomposition is ex…

MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Weitao Jia, Jinghui Lu, Haiyang Yu, Siqi Wang, Guozhi Tang, An-Lan Wang, Weijie Yin, Dingkang Yang, Yuxiang Nie, Bin Shan, Hao Feng, Irene Li, Kun Yang, Han Wang, Jingqun Tang, Teng Fu, Changhong Jin, Chao Feng, Xiaohui Lv, Can Huang
https://arxiv.org/abs/2508.09670…

MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where zero rewards from consistently incorrect candidate answers provide no learning signal, particularly in challenging tasks. To address this, we propose Multi-Expert Mutual Learning GRPO (MEML-GRPO), an innovative framework that utilizes diverse expert prompts as …

Efficient Reward Identification In Max Entropy Reinforcement Learning with Sparsity and Rank Priors
Mohamad Louai Shehab, Alperen Tercan, Necmiye Ozay
https://arxiv.org/abs/2508.07400

Efficient Reward Identification In Max Entropy Reinforcement Learning with Sparsity and Rank Priors
In this paper, we consider the problem of recovering time-varying reward functions from either optimal policies or demonstrations coming from a max entropy reinforcement learning problem. This problem is highly ill-posed without additional assumptions on the underlying rewards. However, in many applications, the rewards are indeed parsimonious, and some prior information is available. We consider two such priors on the rewards: 1) rewards are mostly constant and they change infrequently, 2) rew…

Uncertainty Quantification for Linear Inverse Problems with Besov Prior: A Randomize-Then-Optimize Method
Andreas Horst, Babak Maboudi Afkham, Yiqiu Dong, Jakob Lemvig
https://arxiv.org/abs/2506.16888

Uncertainty Quantification for Linear Inverse Problems with Besov Prior: A Randomize-Then-Optimize Method
In this work, we investigate the use of Besov priors in the context of Bayesian inverse problems. The solution to Bayesian inverse problems is the posterior distribution which naturally enables us to interpret the uncertainties. Besov priors are discretization invariant and can promote sparsity in terms of wavelet coefficients. We propose the randomize-then-optimize method to draw samples from the posterior distribution with Besov priors under a general parameter setting and estimate the modes …

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
Yunhua Fang, Rui Xie, Asad Ul Haq, Linsen Ma, Kaoutar El Maghraoui, Naigang Wang, Meng Wang, Liu Liu, Tong Zhang
https://arxiv.org/abs/2508.13231

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past tokens varies over time, requiring the full KV cache to remain accessible and sustaining pressure on both bandwidth and capacity. With advances in interconnects such as NVLink and LPDDR5X, modern AI hardware now integrates high-bandwidth memory (HBM) with high-s…

Privacy Preserving Inference of Personalized Content for Out of Matrix Users
Michael Sun, Tai Vu, Andrew Wang
https://arxiv.org/abs/2508.14905 https://arxi…

Privacy Preserving Inference of Personalized Content for Out of Matrix Users
Recommender systems for niche and dynamic communities face persistent challenges from data sparsity, cold start users and items, and privacy constraints. Traditional collaborative filtering and content-based approaches underperform in these settings, either requiring invasive user data or failing when preference histories are absent. We present DeepNaniNet, a deep neural recommendation framework that addresses these challenges through an inductive graph-based architecture combining user-item in…

Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction
Ya\c{s}ar Utku Al\c{c}alar, Mehmet Ak\c{c}akaya
https://arxiv.org/abs/2505.24136

Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction
Physics-driven deep learning (PD-DL) models have proven to be a powerful approach for improved reconstruction of rapid MRI scans. In order to train these models in scenarios where fully-sampled reference data is unavailable, self-supervised learning has gained prominence. However, its application at high acceleration rates frequently introduces artifacts, compromising image fidelity. To mitigate this shortcoming, we propose a novel way to train PD-DL networks via carefully-designed perturbation…

Joint Angle and Velocity-Estimation for Target Localization in Bistatic mmWave MIMO Radar in the Presence of Clutter
Priyanka Maity, Suraj Srivastava, Aditya K. Jagannatham, Lajos Hanzo
https://arxiv.org/abs/2506.11497

Joint Angle and Velocity-Estimation for Target Localization in Bistatic mmWave MIMO Radar in the Presence of Clutter
Sparse Bayesian learning (SBL)-aided target localization is conceived for a bistatic mmWave MIMO radar system in the presence of unknown clutter, followed by the development of an angle-Doppler (AD)-domain representation of the target-plus-clutter echo model for accurate target parameter estimation. The proposed algorithm exploits the three-dimensional (3D) sparsity arising in the AD domain of the scattering scene and employs the powerful SBL framework for the estimation of target parameters, s…

From Graphical Lasso to Atomic Norms: High-Dimensional Pattern Recovery
Piotr Graczyk, Bartosz Ko{\l}odziejek, Hideto Nakashima, Maciej Wilczy\'nski
https://arxiv.org/abs/2506.13353

From Graphical Lasso to Atomic Norms: High-Dimensional Pattern Recovery
Estimating high-dimensional precision matrices is a fundamental problem in modern statistics, with the graphical lasso and its $\ell_1$-penalty being a standard approach for recovering sparsity patterns. However, many statistical models, e.g. colored graphical models, exhibit richer structures like symmetry or equality constraints, which the $\ell_1$-norm cannot adequately capture. This paper addresses the gap by extending the high-dimensional analysis of pattern recovery to a general class of …

Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation
Hengyu Zhang, Chunxu Shen, Xiangguo Sun, Jie Tan, Yanchao Tan, Yu Rong, Hong Cheng, Lingling Yi
https://arxiv.org/abs/2507.15395

Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation
In real-world recommendation scenarios, users typically engage with platforms through multiple types of behavioral interactions. Multi-behavior recommendation algorithms aim to leverage various auxiliary user behaviors to enhance prediction for target behaviors of primary interest (e.g., buy), thereby overcoming performance limitations caused by data sparsity in target behavior records. Current state-of-the-art approaches typically employ hierarchical design following either cascading (e.g., vi…

This https://arxiv.org/abs/2506.04667 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

FlashDMoE: Fast Distributed MoE in a Single Kernel
The computational sparsity of Mixture-of-Experts (MoE) models enables sub-linear growth in compute cost as model size increases, offering a scalable path to training massive neural networks. However, existing implementations suffer from \emph{low GPU utilization}, \emph{significant latency overhead}, and a fundamental \emph{inability to leverage task locality}, primarily due to CPU-managed scheduling, host-initiated communication, and frequent kernel launches. To overcome these limitations, we …

Xeric varieties
Natalia Garcia-Fritz, Hector Pasten
https://arxiv.org/abs/2508.05560 https://arxiv.org/pdf/2508.05560…

Xeric varieties
Let $X$ be a smooth projective variety over a number field $k$. The Green--Griffiths--Lang conjecture relates the question of finiteness of rational points in $X$ to the triviality of rational maps from abelian varieties to $X$ and to complex hyperbolicity. Here we investigate the phenomenon of sparsity of rational points in $X$ -- roughly speaking, when there are very few rational points if counted ordered by height. We are interested in the case when sparsity holds over every finite extension…

Quantum simulation of a noisy classical nonlinear dynamics
Sergey Bravyi, Robert Manson-Sawko, Mykhaylo Zayats, Sergiy Zhuk
https://arxiv.org/abs/2507.06198

Quantum simulation of a noisy classical nonlinear dynamics
We consider the problem of simulating dynamics of classical nonlinear dissipative systems with $N\gg 1$ degrees of freedom. To make the problem tractable for quantum computers, we add a weak Gaussian noise to the equation of motion and the initial state. Our main result is an end-to-end quantum algorithm for simulating the noisy dynamics of nonlinear systems satisfying certain sparsity and divergence-free conditions. For any constant nonzero noise rate, the quantum runtime scales polynomially w…

HOMI: Ultra-Fast EdgeAI platform for Event Cameras
Shankaranarayanan H, Satyapreet Singh Yadav, Adithya Krishna, Ajay Vikram P, Mahesh Mehendale, Chetan Singh Thakur
https://arxiv.org/abs/2508.12637

HOMI: Ultra-Fast EdgeAI platform for Event Cameras
Event cameras offer significant advantages for edge robotics applications due to their asynchronous operation and sparse, event-driven output, making them well-suited for tasks requiring fast and efficient closed-loop control, such as gesture-based human-robot interaction. Despite this potential, existing event processing solutions remain limited, often lacking complete end-to-end implementations, exhibiting high latency, and insufficiently exploiting event data sparsity. In this paper, we pres…

BioScore: A Foundational Scoring Function For Diverse Biomolecular Complexes
Yuchen Zhu, Jihong Chen, Yitong Li, Xiaomin Fang, Xianbin Ye, Jingzhou He, Xujun Zhang, Jingxuan Ge, Chao Shen, Xiaonan Zhang, Tingjun Hou, Chang-Yu Hsieh
https://arxiv.org/abs/2507.10877

BioScore: A Foundational Scoring Function For Diverse Biomolecular Complexes
Structural assessment of biomolecular complexes is vital for translating molecular models into functional insights, shaping our understanding of biology and aiding drug discovery. However, current structure-based scoring functions often lack generalizability across diverse biomolecular systems. We present BioScore, a foundational scoring function that addresses key challenges -- data sparsity, cross-system representation, and task compatibility -- through a dual-scale geometric graph learning f…

Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
Zetian Sun, Dongfang Li, Zhuoen Chen, Yuhuai Qin, Baotian Hu
https://arxiv.org/abs/2508.10548 https://…

Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
Reward sparsity in long-horizon reinforcement learning (RL) tasks remains a significant challenge, while existing outcome-based reward shaping struggles to define meaningful immediate rewards without introducing bias or requiring explicit task decomposition. Alternatively, verification-based reward shaping uses stepwise critics, but misalignment between immediate rewards and long-term objectives can lead to reward hacking and suboptimal policies. In this work, we address this problem in the con…

On Mitigating Data Sparsity in Conversational Recommender Systems
Sixiao Zhang, Mingrui Liu, Cheng Long, Wei Yuan, Hongxu Chen, Xiangyu Zhao, Hongzhi Yin
https://arxiv.org/abs/2507.00479

On Mitigating Data Sparsity in Conversational Recommender Systems
Conversational recommender systems (CRSs) capture user preference through textual information in dialogues. However, they suffer from data sparsity on two fronts: the dialogue space is vast and linguistically diverse, while the item space exhibits long-tail and sparse distributions. Existing methods struggle with (1) generalizing to varied dialogue expressions due to underutilization of rich textual cues, and (2) learning informative item representations under severe sparsity. To address these …

A direct approach to tree-guided feature aggregation for high-dimensional regression
Jinwen Fu, Aaron J. Molstad, Hui Zou
https://arxiv.org/abs/2507.19650 https://

A direct approach to tree-guided feature aggregation for high-dimensional regression
In high-dimensional linear models, sparsity is often exploited to reduce variability and achieve parsimony. Equi-sparsity, where one assumes that predictors can be aggregated into groups sharing the same effects, is an alternative parsimonious structure that can be more suitable in certain applications. Previous work has clearly demonstrated the benefits of exploiting equi-sparsity in the presence of ``rare features'' (Yan and Bien 2021). In this work, we propose a new tree-guided regularizatio…

Enhancing Signal Proportion Estimation Through Leveraging Arbitrary Covariance Structures
Jingtian Bai, Xinge Jessie Jeng
https://arxiv.org/abs/2507.11922 …

Enhancing Signal Proportion Estimation Through Leveraging Arbitrary Covariance Structures
Accurately estimating the proportion of true signals among a large number of variables is crucial for enhancing the precision and reliability of scientific research. Traditional signal proportion estimators often assume independence among variables and specific signal sparsity conditions, limiting their applicability in real-world scenarios where such assumptions may not hold. This paper introduces a novel signal proportion estimator that leverages arbitrary covariance dependence information am…

A new sparsity promoting residual transform operator for Lasso regression
Yao Xiao, Anne Gelb, Aditya Viswanathan
https://arxiv.org/abs/2506.22689 https://…

A new sparsity promoting residual transform operator for Lasso regression
Lasso regression is a widely employed approach within the $\ell_1$ regularization framework used to promote sparsity and recover piecewise smooth signals $f:[a,b) \rightarrow \mathbb{R}$ when the given observations are obtained from noisy, blurred, and/or incomplete data environments. In choosing the regularizing sparsity-promoting operator, it is assumed that the particular type of variability of the underlying signal, for example, piecewise constant or piecewise linear behavior across the ent…

Replaced article(s) found for math.NT. https://arxiv.org/list/math.NT/new
[1/1]:
- Arithmetic sparsity in mixed Hodge settings
Kenneth Chung Tak Chiu
https://…

THAT: Token-wise High-frequency Augmentation Transformer for Hyperspectral Pansharpening
Hongkun Jin, Hongcheng Jiang, Zejun Zhang, Yuan Zhang, Jia Fu, Tingfeng Li, Kai Luo
https://arxiv.org/abs/2508.08183

THAT: Token-wise High-frequency Augmentation Transformer for Hyperspectral Pansharpening
Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multi-scale feature modeling. Hyperspectral images exhibit intrinsic spectral priors (e.g., abundance sparsity) and spatial priors (e.g., non-local similarity), which are critical for accurate reconstruction. From a spectral-spatial perspective, Vision Transformers (ViTs) fa…

Recovering Individual-Level Activity Sequences from Location-Based Service Data Using a Novel Transformer-Based Model
Weiyu Luo, Chenfeng Xiong
https://arxiv.org/abs/2508.02734 …

Recovering Individual-Level Activity Sequences from Location-Based Service Data Using a Novel Transformer-Based Model
Location-Based Service (LBS) data provides critical insights into human mobility, yet its sparsity often yields incomplete trip and activity sequences, making accurate inferences about trips and activities difficult. We raise a research problem: Can we use activity sequences derived from high-quality LBS data to recover incomplete activity sequences at the individual level? This study proposes a new solution, the Variable Selection Network-fused Insertion Transformer (VSNIT), integrating the In…

MOSS: Multi-Objective Optimization for Stable Rule Sets
Brian Liu, Rahul Mazumder
https://arxiv.org/abs/2506.08030 https://arxiv.org/…

MOSS: Multi-Objective Optimization for Stable Rule Sets
We present MOSS, a multi-objective optimization framework for constructing stable sets of decision rules. MOSS incorporates three important criteria for interpretability: sparsity, accuracy, and stability, into a single multi-objective optimization framework. Importantly, MOSS allows a practitioner to rapidly evaluate the trade-off between accuracy and stability in sparse rule sets in order to select an appropriate model. We develop a specialized cutting plane algorithm in our framework to rapi…

Sparse Signal Recovery From Quadratic Systems with Full-Rank Matrices
Jinming Wen, Yi Hu, Meng Huang
https://arxiv.org/abs/2507.07557 https://

Sparse Signal Recovery From Quadratic Systems with Full-Rank Matrices
In signal processing and data recovery, reconstructing a signal from quadratic measurements poses a significant challenge, particularly in high-dimensional settings where measurements $m$ is far less than the signal dimension $n$ (i.e., $m \ll n$). This paper addresses this problem by exploiting signal sparsity. Using tools from algebraic geometry, we derive theoretical recovery guarantees for sparse quadratic systems, showing that $m\ge 2s$ (real case) and $m\ge 4s-2$ (complex case) generic me…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/6]:
- Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inferenc...
Jialin Zhao, Yingtao Zhang, Carlo Vittorio Cannistraci

Double Duty: FPGA Architecture to Enable Concurrent LUT and Adder Chain Usage
Junius Pun, Xilai Dai, Grace Zgheib, Mahesh A. Iyer, Andrew Boutros, Vaughn Betz, Mohamed S. Abdelfattah
https://arxiv.org/abs/2507.11709

Double Duty: FPGA Architecture to Enable Concurrent LUT and Adder Chain Usage
Flexibility and customization are key strengths of Field-Programmable Gate Arrays (FPGAs) when compared to other computing devices. For instance, FPGAs can efficiently implement arbitrary-precision arithmetic operations, and can perform aggressive synthesis optimizations to eliminate ineffectual operations. Motivated by sparsity and mixed-precision in deep neural networks (DNNs), we investigate how to optimize the current logic block architecture to increase its arithmetic density. We find that…

R2 priors for Grouped Variance Decomposition in High-dimensional Regression
Javier Enrique Aguilar, David Kohns, Aki Vehtari, Paul-Christian B\"urkner
https://arxiv.org/abs/2507.11833

R2 priors for Grouped Variance Decomposition in High-dimensional Regression
We introduce the Group-R2 decomposition prior, a hierarchical shrinkage prior that extends R2-based priors to structured regression settings with known groups of predictors. By decomposing the prior distribution of the coefficient of determination R2 in two stages, first across groups, then within groups, the prior enables interpretable control over model complexity and sparsity. We derive theoretical properties of the prior, including marginal distributions of coefficients, tail behavior, and …

Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation
Shouxing Ma, Yawen Zeng, Shiqing Wu, Guandong Xu
https://arxiv.org/abs/2508.13745 https://

Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation
Multi-modal recommender system focuses on utilizing rich modal information ( i.e., images and textual descriptions) of items to improve recommendation performance. The current methods have achieved remarkable success with the powerful structure modeling capability of graph neural networks. However, these methods are often hindered by sparse data in real-world scenarios. Although contrastive learning and homography ( i.e., homogeneous graphs) are employed to address the data sparsity challenge, …

Aligning Effective Tokens with Video Anomaly in Large Language Models
Yingxian Chen, Jiahui Liu, Ruifan Di, Yanwei Li, Chirui Chang, Shizhen Zhao, Wilton W. T. Fok, Xiaojuan Qi, Yik-Chung Wu
https://arxiv.org/abs/2508.06350

Aligning Effective Tokens with Video Anomaly in Large Language Models
Understanding abnormal events in videos is a vital and challenging task that has garnered significant attention in a wide range of applications. Although current video understanding Multi-modal Large Language Models (MLLMs) are capable of analyzing general videos, they often struggle to handle anomalies due to the spatial and temporal sparsity of abnormal events, where the redundant information always leads to suboptimal outcomes. To address these challenges, exploiting the representation and g…

Post-reduction inference for confidence sets of models
Heather Battey, Daniel Garcia Rasines, Yanbo Tang
https://arxiv.org/abs/2507.10373 https://

Post-reduction inference for confidence sets of models
Sparsity in a regression context makes the model itself an object of interest, pointing to a confidence set of models as the appropriate presentation of evidence. A difficulty in areas such as genomics, where the number of candidate variables is vast, arises from the need for preliminary reduction prior to the assessment of models. The present paper considers a resolution using inferential separations fundamental to the Fisherian approach to conditional inference, namely, the sufficiency/co-suf…

Rethinking Contrastive Learning in Session-based Recommendation
Xiaokun Zhang, Bo Xu, Fenglong Ma, Zhizheng Wang, Liang Yang, Hongfei Lin
https://arxiv.org/abs/2506.05044

Rethinking Contrastive Learning in Session-based Recommendation
Session-based recommendation aims to predict intents of anonymous users based on limited behaviors. With the ability in alleviating data sparsity, contrastive learning is prevailing in the task. However, we spot that existing contrastive learning based methods still suffer from three obstacles: (1) they overlook item-level sparsity and primarily focus on session-level sparsity; (2) they typically augment sessions using item IDs like crop, mask and reorder, failing to ensure the semantic consist…

This https://arxiv.org/abs/2505.21036 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion}, a novel training-free sparse attention method that exploits inherent sparsity nature in visual data to accelerate attention computation while preserving video quality. Specifically, we identify three unique sparse patterns in video generation attention calcu…

Representation Quantization for Collaborative Filtering Augmentation
Yunze Luo, Yinjie Jiang, Gaode Chen, Jingchi Wang, Shicheng Wang, Ruina Sun, Jiang Yuezihan, Jun Zhang, Jian Liang, Han Li, Kun Gai, Kaigui Bian
https://arxiv.org/abs/2508.11194

Representation Quantization for Collaborative Filtering Augmentation
As the core algorithm in recommendation systems, collaborative filtering (CF) algorithms inevitably face the problem of data sparsity. Since CF captures similar users and items for recommendations, it is effective to augment the lacking user-user and item-item homogeneous linkages. However, existing methods are typically limited to connecting through overlapping interacted neighbors or through similar attributes and contents. These approaches are constrained by coarse-grained, sparse attributes…

Covariance scanning for adaptively optimal change point detection in high-dimensional linear models
Haeran Cho, Housen Li
https://arxiv.org/abs/2507.02552 …

Covariance scanning for adaptively optimal change point detection in high-dimensional linear models
This paper investigates the detection and estimation of a single change in high-dimensional linear models. We derive minimax lower bounds for the detection boundary and the estimation rate, which uncover a phase transition governed the sparsity of the covariance-weighted differential parameter. This form of "inherent sparsity" captures a delicate interplay between the covariance structure of the regressors and the change in regression coefficients on the detectability of a change point. Complem…

This https://arxiv.org/abs/2408.15578 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAR_…

FireFly-S: Exploiting Dual-Side Sparsity for Spiking Neural Networks Acceleration with Reconfigurable Spatial Architecture
Spiking Neural Networks (SNNs), with their brain-inspired structure using discrete spikes instead of continuous activations, are gaining attention for their potential of efficient processing on neuromorphic chips. While current SNN hardware accelerators often prioritize temporal spike sparsity, exploiting sparse synaptic weights offers significant untapped potential for even greater efficiency. To address this, we propose FireFly-S, a Sparse extension of the FireFly series. This co-optimized so…

Flexible Operator Fusion for Fast Sparse Transformer with Diverse Masking on GPU
Wenhao Dai, Haodong Deng, Mengfei Rong, Xinyu Yang, Hongyu Liu, Fangxin Liu, Hailong Yang, Weifeng Liu, Qingxiao Sun
https://arxiv.org/abs/2506.06095

Flexible Operator Fusion for Fast Sparse Transformer with Diverse Masking on GPU
Large language models are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask layers introduce sparsity into Transformer to reduce calculations. However, previous works rarely focus on the performance optimization of sparse Transformer. Moreover, rule-based mechanisms ignore the fusion opportunities of mixed-type operators and fail to adapt to va…

Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation
Teng Shi, Weijie Yu, Xiao Zhang, Ming He, Jianping Fan, Jun Xu
https://arxiv.org/abs/2508.04145

Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation
In modern online platforms, search and recommendation (S&R) often coexist, offering opportunities for performance improvement through search-enhanced approaches. Existing studies show that incorporating search signals boosts recommendation performance. However, the effectiveness of these methods relies heavily on rich search interactions. They primarily benefit a small subset of users with abundant search behavior, while offering limited improvements for the majority of users who exhibit only s…

A new hierarchical distribution on arbitrary sparse precision matrices
Gianluca Mastrantonio, Pierfrancesco Alaimo Di Loro, Marco Mingione
https://arxiv.org/abs/2506.09607

A new hierarchical distribution on arbitrary sparse precision matrices
We introduce a general strategy for defining distributions over the space of sparse symmetric positive definite matrices. Our method utilizes the Cholesky factorization of the precision matrix, imposing sparsity through constraints on its elements while preserving their independence and avoiding the numerical evaluation of normalization constants. In particular, we develop the S-Bartlett as a modified Bartlett decomposition, recovering the standard Wishart as a particular case. By incorporating…

BaroPoser: Real-time Human Motion Tracking from IMUs and Barometers in Everyday Devices
Libo Zhang, Xinyu Yi, Feng Xu
https://arxiv.org/abs/2508.03313 https://

BaroPoser: Real-time Human Motion Tracking from IMUs and Barometers in Everyday Devices
In recent years, tracking human motion using IMUs from everyday devices such as smartphones and smartwatches has gained increasing popularity. However, due to the sparsity of sensor measurements and the lack of datasets capturing human motion over uneven terrain, existing methods often struggle with pose estimation accuracy and are typically limited to recovering movements on flat terrain only. To this end, we present BaroPoser, the first method that combines IMU and barometric data recorded by…

Solving Approximation Tasks with Greedy Deep Kernel Methods
Marian Klink, Tobias Ehring, Robin Herkert, Robin Lautenschlager, Dominik G\"oddeke, Bernard Haasdonk
https://arxiv.org/abs/2508.08759

Solving Approximation Tasks with Greedy Deep Kernel Methods
Kernel methods are versatile tools for function approximation and surrogate modeling. In particular, greedy techniques offer computational efficiency and reliability through inherent sparsity and provable convergence. Inspired by the success of deep neural networks and structured deep kernel networks, we consider deep, multilayer kernels for greedy approximation. This multilayer structure, consisting of linear kernel layers and optimizable kernel activation function layers in an alternating fas…

This https://arxiv.org/abs/2506.02965 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs
Mixture-of-Experts (MoE) has been gaining popularity due to its successful adaptation to large language models (LLMs). In this work, we introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE), which leverages the sparsity of the MoE architecture for memory-efficient decentralized collaborative LLM training, enabling multiple parties with limited GPU-memory and data resources to collectively train more capable LLMs than they could achieve individually. At the same time, this appro…

NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for Recommendation
Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Hewei Wang, Wei Wang, Xiping Hu, Edith Ngai
https://arxiv.org/abs/2507.07522

NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for Recommendation
Graph Neural Networks (GNNs) are widely used in collaborative filtering to capture high-order user-item relationships. To address the data sparsity problem in recommendation systems, Graph Contrastive Learning (GCL) has emerged as a promising paradigm that maximizes mutual information between contrastive views. However, existing GCL methods rely on augmentation techniques that introduce semantically irrelevant noise and incur significant computational and storage costs, limiting effectiveness a…

Multi-Faceted Large Embedding Tables for Pinterest Ads Ranking
Runze Su, Jiayin Jin, Jiacheng Li, Sihan Wang, Guangtong Bai, Zelun Wang, Li Tang, Yixiong Meng, Huasen Wu, Zhimeng Pan, Kungang Li, Han Sun, Zhifang Liu, Haoyang Li, Siping Ji, Ling Leng, Prathibha Deshikachar
https://arxiv.org/abs/2508.05700

Multi-Faceted Large Embedding Tables for Pinterest Ads Ranking
Large embedding tables are indispensable in modern recommendation systems, thanks to their ability to effectively capture and memorize intricate details of interactions among diverse entities. As we explore integrating large embedding tables into Pinterest's ads ranking models, we encountered not only common challenges such as sparsity and scalability, but also several obstacles unique to our context. Notably, our initial attempts to train large embedding tables from scratch resulted in neutral…

Research on E-Commerce Long-Tail Product Recommendation Mechanism Based on Large-Scale Language Models
Qingyi Lu, Haotian Lyu, Jiayun Zheng, Yang Wang, Li Zhang, Chengrui Zhou
https://arxiv.org/abs/2506.06336

Research on E-Commerce Long-Tail Product Recommendation Mechanism Based on Large-Scale Language Models
As e-commerce platforms expand their product catalogs, accurately recommending long-tail items becomes increasingly important for enhancing both user experience and platform revenue. A key challenge is the long-tail problem, where extreme data sparsity and cold-start issues limit the performance of traditional recommendation methods. To address this, we propose a novel long-tail product recommendation mechanism that integrates product text descriptions and user behavior sequences using a large-…