Tootfinder

Robot Learning with Sparsity and Scarcity
Jingxi Xu
https://arxiv.org/abs/2509.16834 https://arxiv.org/pdf/2509.16834…

Robot Learning with Sparsity and Scarcity
Unlike in language or vision, one of the fundamental challenges in robot learning is the lack of access to vast data resources. We can further break down the problem into (1) data sparsity from the angle of data representation and (2) data scarcity from the angle of data quantity. In this thesis, I will discuss selected works on two domains: (1) tactile sensing and (2) rehabilitation robots, which are exemplars of data sparsity and scarcity, respectively. Tactile sensing is an essential modalit…

Joint Pilot Allocation and Sequence Design for MIMO-OFDM Systems With Channel Sparsity
Kabuto Arai, Koji Ishibashi, Hiroki Iimori, Yuto Hama, Paulo Valente Klaine, Szabolcs Malomsoky
https://arxiv.org/abs/2509.17916

Joint Pilot Allocation and Sequence Design for MIMO-OFDM Systems With Channel Sparsity
This paper proposes a joint optimization of pilot subcarrier allocation and non-orthogonal sequence for multiple-input-multiple-output (MIMO)-orthogonal frequency-division multiplexing (OFDM) systems under compressed sensing (CS)-based channel estimation exploiting delay and angle sparsity. Since the performance of CS-based approaches depends on a coherence metric of the sensing matrix in the measurement process, we formulate a joint optimization problem to minimize this coherence. Due to the d…

Overcoming Output Dimension Collapse: How Sparsity Enables Zero-shot Brain-to-Image Reconstruction at Small Data Scales
Kenya Otsuka, Yoshihiro Nagano, Yukiyasu Kamitani
https://arxiv.org/abs/2509.15832

Overcoming Output Dimension Collapse: How Sparsity Enables Zero-shot Brain-to-Image Reconstruction at Small Data Scales
Advances in brain-to-image reconstruction are enabling us to externalize the subjective visual experiences encoded in the brain as images. Achieving such reconstruction with limited training data requires generalization beyond the training set, a task known as zero-shot prediction. Despite its importance, we still lack theoretical guidelines for achieving efficient and accurate reconstruction. In this paper, we provide a theoretical analysis of two widely used models for translating brain activ…

SnipSnap: A Joint Compression Format and Dataflow Co-Optimization Framework for Efficient Sparse LLM Accelerator Design
Junyi Wu, Chao Fang, Zhongfeng Wang
https://arxiv.org/abs/2509.17072

SnipSnap: A Joint Compression Format and Dataflow Co-Optimization Framework for Efficient Sparse LLM Accelerator Design
The growing scale of large language models (LLMs) has intensified demands on computation and memory, making efficient inference a key challenge. While sparsity can reduce these costs, existing design space exploration (DSE) frameworks often overlook compression formats, a key factor for leveraging sparsity on accelerators. This paper proposes SnipSnap, a joint compression format and dataflow co-optimization framework for efficient sparse LLM accelerator design. SnipSnap introduces: (1) a hierar…

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…

Approximation properties of operator coorbit spaces and sparsity classes
Monika D\"orfler, Lukas K\"ohldorfer, Franz Luef, Henry McNulty
https://arxiv.org/abs/2509.16440

Approximation properties of operator coorbit spaces and sparsity classes
Extensions of coorbit spaces for functions to operators have been introduced by two different groups in \cite{doelumcskr24} and \cite{köbaLOC25}, where one is based on the coorbit theory of Feichtinger-Gröchening while the other is based on the theory of localized frames. We show that for certain Gabor g-frames the co-orbit spaces in \cite{köbaLOC25} conincide with the ones in \cite{doelumcskr24} and we refer to this class of operators as operator coorbit spaces. Based on the description of …

DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
Sikai Bai, Haoxi Li, Jie Zhang, Zicong Hong, Song Guo
https://arxiv.org/abs/2509.16105 https:…

DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
Despite the significant breakthrough of Mixture-of-Experts (MoE), the increasing scale of these MoE models presents huge memory and storage challenges. Existing MoE pruning methods, which involve reducing parameter size with a uniform sparsity across all layers, often lead to suboptimal outcomes and performance degradation due to varying expert redundancy in different MoE layers. To address this, we propose a non-uniform pruning strategy, dubbed \textbf{Di}fferentiable \textbf{E}xpert \textbf{P…

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…

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…

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…

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…

SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
Chih-Chuan Cheng, Yi-Ju Tseng
https://arxiv.org/abs/2510.12659

SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
We propose SG-XDEAT (Sparsity-Guided Cross Dimensional and Cross-Encoding Attention with Target Aware Conditioning), a novel framework designed for supervised learning on tabular data. At its core, SG-XDEAT employs a dual-stream encoder that decomposes each input feature into two parallel representations: a raw value stream and a target-conditioned (label-aware) stream. These dual representations are then propagated through a hierarchical stack of attention-based modules. SG-XDEAT integrates th…

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…

Optimal Subspace Embeddings: Resolving Nelson-Nguyen Conjecture Up to Sub-Polylogarithmic Factors
Shabarish Chenakkod, Micha{\l} Derezi\'nski, Xiaoyu Dong
https://arxiv.org/abs/2508.14234

Optimal Subspace Embeddings: Resolving Nelson-Nguyen Conjecture Up to Sub-Polylogarithmic Factors
We give a proof of the conjecture of Nelson and Nguyen [FOCS 2013] on the optimal dimension and sparsity of oblivious subspace embeddings, up to sub-polylogarithmic factors: For any $n\geq d$ and $ε\geq d^{-O(1)}$, there is a random $\tilde O(d/ε^2)\times n$ matrix $Π$ with $\tilde O(\log(d)/ε)$ non-zeros per column such that for any $A\in\mathbb{R}^{n\times d}$, with high probability, $(1-ε)\|Ax\|\leq\|ΠAx\|\leq(1+ε)\|Ax\|$ for all $x\in\mathbb{R}^d$, where…

Robust Sparse Subspace Tracking from Corrupted Data Observations
Ta Giang Thuy Loan, Hoang-Lan Nguyen, Nguyen Thi Ngoc Lan, Do Hai Son, Tran Thi Thuy Quynh, Nguyen Linh Trung, Karim Abed-Meraim, Thanh Trung Le
https://arxiv.org/abs/2509.16585

Robust Sparse Subspace Tracking from Corrupted Data Observations
Subspace tracking is a fundamental problem in signal processing, where the goal is to estimate and track the underlying subspace that spans a sequence of data streams over time. In high-dimensional settings, data samples are often corrupted by non-Gaussian noises and may exhibit sparsity. This paper explores the alpha divergence for sparse subspace estimation and tracking, offering robustness to data corruption. The proposed method outperforms the state-of-the-art robust subspace tracking metho…

Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
Wei Guo, Maura Pintor, Ambra Demontis, Battista Biggio
https://arxiv.org/abs/2509.08747 https://

Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
In the deployment phase, semi-structured sparsity accelerates the execution of deep neural networks on modern GPUs via sparse matrix multiplication. In this paper, targeting the semi-structured sparsity, we introduce a Silent Until Sparse (SUS) backdoor attack, where the released full model remains silent (benign), but becomes a backdoored model after sparsification. The attack operates in two phases: (i) in the backdoor training phase, the backdoor functionality is injected into specific weigh…

Improved Hamiltonian learning and sparsity testing through Bell sampling
Savar D. Sinha, Yu Tong
https://arxiv.org/abs/2509.07937 https://arxiv.org/pdf/250…

Improved Hamiltonian learning and sparsity testing through Bell sampling
We consider the problem of learning an $M$-sparse Hamiltonian and the related problem of Hamiltonian sparsity testing. Through a detailed analysis of Bell sampling, we reduce the total evolution time required by the state-of-the-art algorithm for $M$-sparse Hamiltonian learning to $\widetilde{\mathcal{O}}(M/ε)$, where $ε$ denotes the $\ell^{\infty}$ error, achieving an improvement by a factor of $M$ (ignoring the logarithmic factor) while only requiring access to forward time-evolution. We th…

Utilizing dynamic sparsity on pretrained DETR
Reza Sedghi, Anand Subramoney, David Kappel
https://arxiv.org/abs/2510.09380 https://arxiv.org/pdf/2510.09380…

Utilizing dynamic sparsity on pretrained DETR
Efficient inference with transformer-based models remains a challenge, especially in vision tasks like object detection. We analyze the inherent sparsity in the MLP layers of DETR and introduce two methods to exploit it without retraining. First, we propose Static Indicator-Based Sparsification (SIBS), a heuristic method that predicts neuron inactivity based on fixed activation patterns. While simple, SIBS offers limited gains due to the input-dependent nature of sparsity. To address this, we i…

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
Prasenjit K Mudi, Anshi Sachan, Dahlia Devapriya, Sheetal Kalyani
https://arxiv.org/abs/2510.12666

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
Whisper models have achieved remarkable progress in speech recognition; yet their large size remains a bottleneck for deployment on resource-constrained edge devices. This paper proposes a framework to design fine-tuned variants of Whisper which address the above problem. Structured sparsity is enforced via the Sparse Group LASSO penalty as a loss regularizer, to reduce the number of FLOating Point operations (FLOPs). Further, a weight statistics aware pruning algorithm is proposed. We also des…

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…

MOSAIC: Minimax-Optimal Sparsity-Adaptive Inference for Change Points in Dynamic Networks
Yingying Fan, Jingyuan Liu, Jinchi Lv, Ao Sun
https://arxiv.org/abs/2509.06303 https://…

MOSAIC: Minimax-Optimal Sparsity-Adaptive Inference for Change Points in Dynamic Networks
We propose a new inference framework, named MOSAIC, for change-point detection in dynamic networks with the simultaneous low-rank and sparse-change structure. We establish the minimax rate of detection boundary, which relies on the sparsity of changes. We then develop an eigen-decomposition-based test with screened signals that approaches the minimax rate in theory, with only a minor logarithmic loss. For practical implementation of MOSAIC, we adjust the theoretical test by a novel residual-bas…

Efficient Brain Network Estimation with Sparse ICA in Non-Human Primate Neuroimaging
Qiang Li, Liang Ma, Masoud Seraji, Shujian Yu, Yun Wang, Jingyu Liu, Vince D. Calhoun
https://arxiv.org/abs/2509.16803

Efficient Brain Network Estimation with Sparse ICA in Non-Human Primate Neuroimaging
Independent component analysis (ICA) is widely used to separate mixed signals and recover statistically independent components. However, in non-human primate neuroimaging studies, most ICA-recovered spatial maps are often dense. To extract the most relevant brain activation patterns, post-hoc thresholding is typically applied-though this approach is often imprecise and arbitrary. To address this limitation, we employed the Sparse ICA method, which enforces both sparsity and statistical independ…

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

Scalable Quantum Monte Carlo Method for Polariton Chemistry via Mixed Block Sparsity and Tensor Hypercontraction Method
Yu Zhang
https://arxiv.org/abs/2510.11634 https://…

Scalable Quantum Monte Carlo Method for Polariton Chemistry via Mixed Block Sparsity and Tensor Hypercontraction Method
We present a reduced-scaling auxiliary-field quantum Monte Carlo (AFQMC) framework designed for large molecular systems and ensembles, with or without coupling to optical cavities. Our approach leverages the natural block sparsity of Cholesky decomposition (CD) of electron repulsion integrals in molecular ensembles and employs tensor hypercontraction (THC) to efficiently compress low-rank Cholesky blocks. By representing the Cholesky vectors in a mixed format, keeping high-rank blocks in block-…

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…

Feature Understanding and Sparsity Enhancement via 2-Layered kernel machines (2L-FUSE)
Fabiana Camattari, Sabrina Guastavino, Francesco Marchetti, Emma Perracchione
https://arxiv.org/abs/2509.07806

Feature Understanding and Sparsity Enhancement via 2-Layered kernel machines (2L-FUSE)
We propose a novel sparsity enhancement strategy for regression tasks, based on learning a data-adaptive kernel metric, i.e., a shape matrix, through 2-Layered kernel machines. The resulting shape matrix, which defines a Mahalanobis-type deformation of the input space, is then factorized via an eigen-decomposition, allowing us to identify the most informative directions in the space of features. This data-driven approach provides a flexible, interpretable and accurate feature reduction scheme. …

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge
Zhirui Huang, Rui Ma, Shijie Cao, Ran Shu, Ian Wang, Ting Cao, Chixiao Chen, Yongqiang Xiong
https://arxiv.org/abs/2509.13765

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge
Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without significantly compromising model accuracy. Conventional LLM inference platforms (e.g GPUs) cannot capitalize on its benefits, as they (i) lack native support for ternary arithmetic and memory specialization and (ii) remain severely under-utilized in low-batch, real-time scenarios. In this work, we …

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…

Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
Tam Thuc Do, Philip A. Chou, Gene Cheung
https://arxiv.org/abs/2509.08685 https://

Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
Given encoded 3D point cloud geometry available at the decoder, we study the problem of lossy attribute compression in a multi-resolution B-spline projection framework. A target continuous 3D attribute function is first projected onto a sequence of nested subspaces $\mathcal{F}^{(p)}_{l_0} \subseteq \cdots \subseteq \mathcal{F}^{(p)}_{L}$, where $\mathcal{F}^{(p)}_{l}$ is a family of functions spanned by a B-spline basis function of order $p$ at a chosen scale and its integer shifts. The projec…

Sparsity, Stress-Independence and Globally Linked Pairs in Graph Rigidity Theory
D\'aniel Garamv\"olgyi, Bill Jackson, Tibor Jord\'an
https://arxiv.org/abs/2509.03150

Sparsity, Stress-Independence and Globally Linked Pairs in Graph Rigidity Theory
A graph is $\mathcal{R}_d$-independent (resp. $\mathcal{R}_d$-connected) if its $d$-dimensional generic rigidity matroid is free (resp. connected). A result of Maxwell from 1867 implies that every $\mathcal{R}_d$-independent graph satisfies the sparsity condition $|E(H)|\leq d|V(H)|-\binom{d+1}{2}$ for all subgraphs $H$ with at least $d+1$ vertices. Several other families of graphs $G$ arising naturally in rigidity theory, such as minimally globally $d$-rigid graphs, are kno…

Repulsive mixtures via the sparsity-inducing partition prior
Alexander Mozdzen, Timothy Wertz, Maria De Iorio, Andrea Cremaschi, Gregor Kastner, Johan Eriksson
https://arxiv.org/abs/2509.25860

Repulsive mixtures via the sparsity-inducing partition prior
We introduce a novel prior distribution for modelling the weights in mixture models based on a generalisation of the Dirichlet distribution, the Selberg Dirichlet distribution. This distribution contains a repulsive term, which naturally penalises values that lie close to each other on the simplex, thus encouraging few dominating clusters. The repulsive behaviour induces additional sparsity on the number of components. We refer to this construction as sparsity-inducing partition (SIP) prior. By…

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…

exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation
Yue Xu, Litao Wei, Pengyu An, Qingyu Zhang, Yong-Lu Li
https://arxiv.org/abs/2509.14688

exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation
Tactile-aware robot learning faces critical challenges in data collection and representation due to data scarcity and sparsity, and the absence of force feedback in existing systems. To address these limitations, we introduce a tactile robot learning system with both hardware and algorithm innovations. We present exUMI, an extensible data collection device that enhances the vanilla UMI with robust proprioception (via AR MoCap and rotary encoder), modular visuo-tactile sensing, and automated cal…

Semi-sparsity Generalization for Variational Mesh Denoising
Junqing Huang, Haihui Wang, Michael Ruzhansky
https://arxiv.org/abs/2510.13372 https://arxiv.or…

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…

You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models
Pawe{\l} M\k{a}ka, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
https://arxiv.org/abs/2509.14031

You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models
Achieving human-level translations requires leveraging context to ensure coherence and handle complex phenomena like pronoun disambiguation. Sparsity of contextually rich examples in the standard training data has been hypothesized as the reason for the difficulty of context utilization. In this work, we systematically validate this claim in both single- and multilingual settings by constructing training datasets with a controlled proportions of contextually relevant examples. We demonstrate a …

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

Functional Donoho-Elad-Gribonval-Nielsen-Fuchs Sparsity Theorem
K. Mahesh Krishna
https://arxiv.org/abs/2510.09609 https://arxiv.org/pdf/2510.09609

Functional Donoho-Elad-Gribonval-Nielsen-Fuchs Sparsity Theorem
Celebrated breakthrough sparsity theorem obtained independently by Donoho and Elad \textit{[Proc. Natl. Acad. Sci. USA, 2003]} and Gribonval and Nielsen \textit{[IEEE Trans. Inform. Theory, 2003]} and Fuchs \textit{[IEEE Trans. Inform. Theory, 2004]} says that unique sparse solution to NP-Hard $\ell_0$-minimization problem can be obtained using unique solution to P-Type $\ell_1$-minimization problem. In this paper, we extend their result to abstract Banach spaces using 1-approximate Schauder fr…

Event-Driven Control via Sparsity-Promoting Regularization: A Rollout Approach with Performance Guarantees
Shumpei Nishida, Kunihisa Okano
https://arxiv.org/abs/2509.24799 https…

Event-Driven Control via Sparsity-Promoting Regularization: A Rollout Approach with Performance Guarantees
This paper presents a controller design method aiming to balance control performance and actuation frequency. In this framework, actuation timings are determined in an event-driven manner, resulting in intermittent control actions. Control performance is measured by an infinite-horizon average cost, and input sparsity is promoted through actuation-rate regularization. Since the formulated optimal control problem has a combinatorial nature, we employ a rollout algorithm to find a suboptimal solu…

Hetero-EUCLID: Interpretable model discovery for heterogeneous hyperelastic materials using stress-unsupervised learning
Kanhaiya Lal Chaurasiya, Saurav Dutta, Siddhant Kumar, Akshay Joshi
https://arxiv.org/abs/2509.11784

Hetero-EUCLID: Interpretable model discovery for heterogeneous hyperelastic materials using stress-unsupervised learning
We propose a computational framework, Hetero-EUCLID, for segmentation and parameter identification to characterize the full hyperelastic behavior of all constituents of a heterogeneous material. In this work, we leverage the Bayesian-EUCLID (Efficient Unsupervised Constitutive Law Identification and Discovery) framework to efficiently solve the heterogenized formulation through parsimonious model selection using sparsity-promoting priors and Monte Carlo Markov Chain sampling. We utilize experim…

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
Liangkun Chen, Zijian Wen, Tian Wu, Xiaoxi Zhang, Chuan Wu
https://arxiv.org/abs/2510.10302

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
The Mixture-of-Experts (MoE) architecture has been widely adopted in large language models (LLMs) to reduce computation cost through model sparsity. Employing speculative decoding (SD) can further accelerate MoE inference by drafting multiple tokens per step and verifying them in parallel. However, combining MoE with SD inflates GPU memory and aggravates CPU-GPU bandwidth contention during multi-token verification. Existing MoE offloading systems are SD-agnostic and do not address this bottlene…

Crosslisted article(s) found for math.OC. https://arxiv.org/list/math.OC/new
[1/1]:
- Functional Donoho-Elad-Gribonval-Nielsen-Fuchs Sparsity Theorem
K. Mahesh Krishna

Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories
Muhammad Ayub Sabir, Junbiao Pang, Jiaqi Wu, Fatima Ashraf
https://arxiv.org/abs/2510.12686

Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories
Abnormal stop detection (ASD) in intercity coach transportation is critical for ensuring passenger safety, operational reliability, and regulatory compliance. However, two key challenges hinder ASD effectiveness: sparse GPS trajectories, which obscure short or unauthorized stops, and limited labeled data, which restricts supervised learning. Existing methods often assume dense sampling or regular movement patterns, limiting their applicability. To address data sparsity, we propose a Sparsity-Aw…

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…

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, …

SDGraph: Multi-Level Sketch Representation Learning by Sparse-Dense Graph Architecture
Xi Cheng, Pingfa Feng, Zhichao Liao, Mingyu Fan, Long Zeng
https://arxiv.org/abs/2510.12192

SDGraph: Multi-Level Sketch Representation Learning by Sparse-Dense Graph Architecture
Freehand sketches exhibit unique sparsity and abstraction, necessitating learning pipelines distinct from those designed for images. For sketch learning methods, the central objective is to fully exploit the effective information embedded in sketches. However, there is limited research on what constitutes effective sketch information, which in turn constrains the performance of existing approaches. To tackle this issue, we first proposed the Multi-Level Sketch Representation Scheme to systemati…

GBEES-GPU: An efficient parallel GPU algorithm for high-dimensional nonlinear uncertainty propagation
Benjamin L. Hanson, Carlos Rubio, Adri\'an Garc\'ia-Guti\'errez, Thomas Bewley
https://arxiv.org/abs/2508.13986

GBEES-GPU: An efficient parallel GPU algorithm for high-dimensional nonlinear uncertainty propagation
Eulerian nonlinear uncertainty propagation methods often suffer from finite domain limitations and computational inefficiencies. A recent approach to this class of algorithm, Grid-based Bayesian Estimation Exploiting Sparsity, addresses the first challenge by dynamically allocating a discretized grid in regions of phase space where probability is non-negligible. However, the design of the original algorithm causes the second challenge to persist in high-dimensional systems. This paper presents …

$\mathsf{P} \neq \mathsf{NP}$: A Non-Relativizing Proof via Quantale Weakness and Geometric Complexity
Ben Goertzel
https://arxiv.org/abs/2510.08814 https://

$\mathsf{P} \neq \mathsf{NP}$: A Non-Relativizing Proof via Quantale Weakness and Geometric Complexity
We give a compositional, information-theoretic framework that turns short programs into locality on many independent blocks, and combine it with symmetry and sparsity of masked random Unique-SAT to obtain distributional lower bounds that contradict the self-reduction upper bound under $\mathsf{P}=\mathsf{NP}$. We work in the weakness quantale $w_Q=K_{\mathrm{poly}}(\cdot\mid\cdot)$. For an efficiently samplable ensemble $D_m$ made by masking random $3$-CNFs with fresh $S_m\ltimes(\mathbb{Z}_2)^…

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…

Domain Knowledge Infused Generative Models for Drug Discovery Synthetic Data
Bing Hu, Jong-Hoon Park, Helen Chen, Young-Rae Cho, Anita Layton
https://arxiv.org/abs/2510.09837 ht…

Domain Knowledge Infused Generative Models for Drug Discovery Synthetic Data
The role of Artificial Intelligence (AI) is growing in every stage of drug development. Nevertheless, a major challenge in drug discovery AI remains: Drug pharmacokinetic (PK) and Drug-Target Interaction (DTI) datasets collected in different studies often exhibit limited overlap, creating data overlap sparsity. Thus, data curation becomes difficult, negatively impacting downstream research investigations in high-throughput screening, polypharmacy, and drug combination. We propose xImagand-DKI, …

Learning Discrete Bayesian Networks with Hierarchical Dirichlet Shrinkage
Alexander Dombowsky, David B. Dunson
https://arxiv.org/abs/2509.13267 https://arx…

Learning Discrete Bayesian Networks with Hierarchical Dirichlet Shrinkage
Discrete Bayesian networks (DBNs) provide a broadly useful framework for modeling dependence structures in multivariate categorical data. There is a vast literature on methods for inferring conditional probabilities and graphical structure in DBNs, but data sparsity and parametric assumptions are major practical issues. In this article, we detail a comprehensive Bayesian framework for learning DBNs. First, we propose a hierarchical prior for the conditional probabilities that enables complicate…

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…

The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
Youssef Chaabouni, David Gamarnik
https://arxiv.org/abs/2509.01809 http…

The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
We consider the problem of recovering the support of a sparse signal using noisy projections. While extensive work has been done on the dense measurement matrix setting, the sparse setting remains less explored. In this work, we establish sufficient conditions on the sample size for successful sparse recovery using sparse measurement matrices. Bringing together our result with previously known necessary conditions, we discover that, in the regime where $ds/p \rightarrow +\infty$, sparse recover…

Minimax and adaptive estimation of general linear functionals under sparsity
Jie Xie, Dongming Huang
https://arxiv.org/abs/2509.25595 https://arxiv.org/pdf…

Minimax and adaptive estimation of general linear functionals under sparsity
We study the problem of estimating a linear functional $η^\intercal θ$ of a high-dimensional sparse mean vector $θ$ with an arbitrary loading vector $η$ under symmetric noise with exponentially decaying tails, with Gaussian noise as an important example. We first establish the nonasymptotic minimax rate in the oracle setting with known sparsity level $s$. This rate explicitly depends on the structure of $η$, sparsity level $s$, and tail parameter of noise. We then develop an adaptive estim…

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://…

MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness
Huizheng Wang, Zichuan Wang, Zhiheng Yue, Yousheng Long, Taiquan Wei, Jianxun Yang, Yang Wang, Chao Li, Shaojun Wei, Yang Hu, Shouyi Yin
https://arxiv.org/abs/2509.10372

MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness
Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. This highlights the need for a versatile compute-memory efficient accelerator. Unfortunately, existing Transformer accelerators struggle to address both aspects simultaneously, as they focus on value-level processing, missing fine-grained opportunities to optimize computation and memory collaboratively. This paper introd…

Theoretical Validation of the Latent Optimally Partitioned-$\ell_2/\ell_1$ Penalty with Application to Angular Power Spectrum Estimation
Hiroki Kuroda, Renato Luis Garrido Cavalcante, Masahiro Yukawa
https://arxiv.org/abs/2509.13745

Theoretical Validation of the Latent Optimally Partitioned-$\ell_2/\ell_1$ Penalty with Application to Angular Power Spectrum Estimation
This paper demonstrates that, in both theory and practice, the latent optimally partitioned (LOP)-$\ell_2/\ell_1$ penalty is effective for exploiting block-sparsity without the knowledge of the concrete block structure. More precisely, we first present a novel theoretical result showing that the optimized block partition in the LOP-$\ell_2/\ell_1$ penalty satisfy a condition required for accurate recovery of block-sparse signals. Motivated by this result, we present a new application of the LOP…

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…

FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning
Sijing Xie, Dingzhu Wen, Changsheng You, Qimei Chen, Mehdi Bennis, Kaibin Huang
https://arxiv.org/abs/2510.12078

FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning
Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while reducing training costs, this paper proposes Federated LoRA with Dropout (FedLoDrop), a new framework that applies dropout to the rows and columns of the trainable matrix in Federated LoRA. A generalization error bound and convergence analysis under sparsity regularization are obta…

TGPO: Tree-Guided Preference Optimization for Robust Web Agent Reinforcement Learning
Ziyuan Chen, Zhenghui Zhao, Zhangye Han, Miancan Liu, Xianhang Ye, Yiqing Li, Hongbo Min, Jinkui Ren, Xiantao Zhang, Guitao Cao
https://arxiv.org/abs/2509.14172

TGPO: Tree-Guided Preference Optimization for Robust Web Agent Reinforcement Learning
With the rapid advancement of large language models and vision-language models, employing large models as Web Agents has become essential for automated web interaction. However, training Web Agents with reinforcement learning faces critical challenges including credit assignment misallocation, prohibitively high annotation costs, and reward sparsity. To address these issues, we propose Tree-Guided Preference Optimization (TGPO), an offline reinforcement learning framework that proposes a tree-s…

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…

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…

Fast RLS Identification Leveraging the Linearized System Sparsity: Predictive Cost Adaptive Control for Quadrotors
Tam W. Nguyen
https://arxiv.org/abs/2508.17577 https://…

Fast RLS Identification Leveraging the Linearized System Sparsity: Predictive Cost Adaptive Control for Quadrotors
This paper presents a centralized predictive cost adaptive control (PCAC) strategy for the position and attitude control of quadrotors. PCAC is an optimal, prediction-based control method that uses recursive least squares (RLS) to identify model parameters online, enabling adaptability in dynamic environments. Addressing challenges with black-box approaches in systems with complex couplings and fast dynamics, this study leverages the unique sparsity of quadrotor models linearized around hover p…

$\ell_{1}^{2}-\eta\ell_{2}^{2}$ 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…

NEURAL: An Elastic Neuromorphic Architecture with Hybrid Data-Event Execution and On-the-fly Attention Dataflow
Yuehai Chen, Farhad Merchant
https://arxiv.org/abs/2509.15036 htt…

NEURAL: An Elastic Neuromorphic Architecture with Hybrid Data-Event Execution and On-the-fly Attention Dataflow
Spiking neural networks (SNNs) have emerged as a promising alternative to artificial neural networks (ANNs), offering improved energy efficiency by leveraging sparse and event-driven computation. However, existing hardware implementations of SNNs still suffer from the inherent spike sparsity and multi-timestep execution, which significantly increase latency and reduce energy efficiency. This study presents NEURAL, a novel neuromorphic architecture based on a hybrid data-event execution paradigm…

Environment Reconstruction in Multi-Bounce Channels with Array Partial Blockage
Yuan Liu, Linlong Wu, Xuesong Cai, M. R. Bhavani Shankar
https://arxiv.org/abs/2509.13559 https:/…

Environment Reconstruction in Multi-Bounce Channels with Array Partial Blockage
Extremely-large antenna arrays (ELAA) are important in applications requiring high angular resolution. However, a prominent issue is the spatial non-stationary (SNS) channels due to partial blockage to the ELAA. In this paper, we address the scatterer localization and subsequent environment reconstruction considering partially blocked SNS channels. Specifically, the SNS effects are parametrically modeled through spatial-varying amplitudes with sparsity. Based on the established signal model, th…

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
Joachim Diederich
https://arxiv.org/abs/2510.09338 https://arxiv.org/pdf/2510.09338

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
We present a novel framework for training large language models with continuously adjustable internal representations that span the full spectrum from localist (interpretable, rule-based) to distributed (generalizable, efficient) encodings. The key innovation is a locality dial, a tunable parameter that dynamically controls the degree of localization during both training and inference without requiring model retraining. This is achieved through group sparsity penalties on attention mechanisms, …

SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
Zhiliu Yang, Jinyu Dai, Jianyuan Zhang, Zhu Yang
https://arxiv.org/abs/2510.12749

SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
The scene perception, understanding, and simulation are fundamental techniques for embodied-AI agents, while existing solutions are still prone to segmentation deficiency, dynamic objects' interference, sensor data sparsity, and view-limitation problems. This paper proposes a novel framework, named SPORTS, for holistic scene understanding via tightly integrating Video Panoptic Segmentation (VPS), Visual Odometry (VO), and Scene Rendering (SR) tasks into an iterative and unified perspective. Fir…

Efficient Group Lasso Regularized Rank Regression with Data-Driven Parameter Determination
Meixia Lin, Meijiao Shi, Yunhai Xiao, Qian Zhang
https://arxiv.org/abs/2510.11546 http…

Efficient Group Lasso Regularized Rank Regression with Data-Driven Parameter Determination
High-dimensional regression often suffers from heavy-tailed noise and outliers, which can severely undermine the reliability of least-squares based methods. To improve robustness, we adopt a non-smooth Wilcoxon score based rank objective and incorporate structured group sparsity regularization, a natural generalization of the lasso, yielding a group lasso regularized rank regression method. By extending the tuning-free parameter selection scheme originally developed for the lasso, we introduce …

A Tutorial on Conducting Mediation Analysis with Exposure Mixtures
Yiran Wang, Yi-Ting Lin, Sean McGrath, John D. Meeker, Sung Kyun Park, Joshua L. Warren, Bhramar Mukherjee
https://arxiv.org/abs/2509.10916

A Tutorial on Conducting Mediation Analysis with Exposure Mixtures
Causal mediation analysis is a powerful tool in environmental health research, allowing researchers to uncover the pathways through which exposures influence health outcomes. While traditional mediation methods have been widely applied to individual exposures, real-world scenarios often involve complex mixtures. Such mixtures introduce unique methodological challenges, including multicollinearity, sparsity of active exposures, and potential nonlinear and interactive effects. This paper provides…

Arithmetic Sparsity and Cohomological Obstructions in Weighted Projective Spaces
Tony Shaska Sr
https://arxiv.org/abs/2509.02319 https://arxiv.org/pdf/2509…

Arithmetic Sparsity and Cohomological Obstructions in Weighted Projective Spaces
This paper investigates the distribution of rational and algebraic points of bounded weighted height in weighted projective spaces over number fields. For a weighted projective space with weights q over a number field k of degree m, we derive an asymptotic formula for the count of such points, featuring a leading term D times X raised to m e Q, plus an error term, where e is the extension degree and Q is the sum of the weights. The constant D combines geometric aspects of the weights with an ar…

Accuracy-Robustness Trade Off via Spiking Neural Network Gradient Sparsity Trail
Nhan T. Luu
https://arxiv.org/abs/2509.23762 https://arxiv.org/pdf/2509.23…

Accuracy-Robustness Trade Off via Spiking Neural Network Gradient Sparsity Trail
Spiking Neural Networks (SNNs) have attracted growing interest in both computational neuroscience and artificial intelligence, primarily due to their inherent energy efficiency and compact memory footprint. However, achieving adversarial robustness in SNNs, particularly for vision-related tasks, remains a nascent and underexplored challenge. Recent studies have proposed leveraging sparse gradients as a form of regularization to enhance robustness against adversarial perturbations. In this work,…

Gaussian Mixture Model with unknown diagonal covariances via continuous sparse regularization
Romane Giard (ECL, ICJ, PSPM), Yohann de Castro (ICJ, ECL, PSPM, IUF), Cl\'ement Marteau (PSPM, ICJ, UCBL)
https://arxiv.org/abs/2509.12889

Gaussian Mixture Model with unknown diagonal covariances via continuous sparse regularization
This paper addresses the statistical estimation of Gaussian Mixture Models (GMMs) with unknown diagonal covariances from independent and identically distributed samples. We employ the Beurling-LASSO (BLASSO), a convex optimization framework that promotes sparsity in the space of measures, to simultaneously estimate the number of components and their parameters. Our main contribution extends the BLASSO methodology to multivariate GMMs with component-specific unknown diagonal covariance matrices-…

Crosslisted article(s) found for cs.IT. https://arxiv.org/list/cs.IT/new
[1/1]:
- Functional Donoho-Elad-Gribonval-Nielsen-Fuchs Sparsity Theorem
K. Mahesh Krishna

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…

Learning Neural Networks by Neuron Pursuit
Akshay Kumar, Jarvis Haupt
https://arxiv.org/abs/2509.12154 https://arxiv.org/pdf/2509.12154

Learning Neural Networks by Neuron Pursuit
The first part of this paper studies the evolution of gradient flow for homogeneous neural networks near a class of saddle points exhibiting a sparsity structure. The choice of these saddle points is motivated from previous works on homogeneous networks, which identified the first saddle point encountered by gradient flow after escaping the origin. It is shown here that, when initialized sufficiently close to such saddle points, gradient flow remains near the saddle point for a sufficiently lon…

Efficient In-Memory Acceleration of Sparse Block Diagonal LLMs
Jo\~ao Paulo Cardoso de Lima, Marc Dietrich, Jeronimo Castrillon, Asif Ali Khan
https://arxiv.org/abs/2510.11192 h…

Efficient In-Memory Acceleration of Sparse Block Diagonal LLMs
Structured sparsity enables deploying large language models (LLMs) on resource-constrained systems. Approaches like dense-to-sparse fine-tuning are particularly compelling, achieving remarkable structured sparsity by reducing the model size by over 6.7x, while still maintaining acceptable accuracy. Despite this reduction, LLM inference, especially the decode stage being inherently memory-bound, is extremely expensive on conventional Von-Neumann architectures. Compute-in-memory (CIM) architectur…

Utilizing Sparsity in the GPU-accelerated Assembly of Schur Complement Matrices in Domain Decomposition Methods
Jakub Homola, Ond\v{r}ej Meca, Lubom\'ir \v{R}\'iha, Tom\'a\v{s} Brzobohat\'y
https://arxiv.org/abs/2509.21037

Utilizing Sparsity in the GPU-accelerated Assembly of Schur Complement Matrices in Domain Decomposition Methods
Schur complement matrices emerge in many domain decomposition methods that can solve complex engineering problems using supercomputers. Today, as most of the high-performance clusters' performance lies in GPUs, these methods should also be accelerated. Typically, the offloaded components are the explicitly assembled dense Schur complement matrices used later in the iterative solver for multiplication with a vector. As the explicit assembly is expensive, it represents a significant overhead as…

SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion
Mengxue Yang, Chun Yang, Jiaqi Zhu, Jiafan Li, Jingqi Zhang, Yuyang Li, Ying Li
https://arxiv.org/abs/2509.06531

SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion
Link prediction in knowledge graphs requires integrating structural information and semantic context to infer missing entities. While large language models offer strong generative reasoning capabilities, their limited exploitation of structural signals often results in structural sparsity and semantic ambiguity, especially under incomplete or zero-shot settings. To address these challenges, we propose SLiNT (Structure-aware Language model with Injection and coNtrastive Training), a modular fram…

SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
Binhao Wang, Yutian Xiao, Maolin Wang, Zhiqi Li, Tianshuo Wei, Ruocheng Guo, Xiangyu Zhao
https://arxiv.org/abs/2509.11094

SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
Knowledge Graphs (KGs) enhance recommender systems but face challenges from inherent noise, sparsity, and Euclidean geometry's inadequacy for complex relational structures, critically impairing representation learning, especially for long-tail entities. Existing methods also often lack adaptive multi-source signal fusion tailored to item popularity. This paper introduces SPARK, a novel multi-stage framework systematically tackling these issues. SPARK first employs Tucker low-rank decomposition …

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…

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…

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…

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…

The Honest Truth About Causal Trees: Accuracy Limits for Heterogeneous Treatment Effect Estimation
Matias D. Cattaneo, Jason M. Klusowski, Ruiqi Rae Yu
https://arxiv.org/abs/2509.11381

The Honest Truth About Causal Trees: Accuracy Limits for Heterogeneous Treatment Effect Estimation
Recursive decision trees have emerged as a leading methodology for heterogeneous causal treatment effect estimation and inference in experimental and observational settings. These procedures are fitted using the celebrated CART (Classification And Regression Tree) algorithm [Breiman et al., 1984], or custom variants thereof, and hence are believed to be "adaptive" to high-dimensional data, sparsity, or other specific features of the underlying data generating process. Athey and Imbens [2016] pr…

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…

Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
Patrick Amadeus Irawan, Ryandito Diandaru, Belati Jagad Bintang Syuhada, Randy Zakya Suchrady, Alham Fikri Aji, Genta Indra Winata, Fajri Koto, Samuel Cahyawijaya
https://arxiv.org/abs/2509.05060

Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
We introduce Entropy2Vec, a novel framework for deriving cross-lingual language representations by leveraging the entropy of monolingual language models. Unlike traditional typological inventories that suffer from feature sparsity and static snapshots, Entropy2Vec uses the inherent uncertainty in language models to capture typological relationships between languages. By training a language model on a single language, we hypothesize that the entropy of its predictions reflects its structural sim…

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…

Approximate Message Passing for Multi-Preamble Detection in OTFS Random Access
Alessandro Mirri, Vishnu Teja Kunde, Enrico Paolini, Jean-Francois Chamberland
https://arxiv.org/abs/2509.03980

Approximate Message Passing for Multi-Preamble Detection in OTFS Random Access
This article addresses the problem of multiple preamble detection in random access systems based on orthogonal time frequency space (OTFS) signaling. This challenge is formulated as a structured sparse recovery problem in the complex domain. To tackle it, the authors propose a new approximate message passing (AMP) algorithm that enforces double sparsity: the sparse selection of preambles and the inherent sparsity of OTFS signals in the delay-Doppler domain. From an algorithmic standpoint, the n…

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

SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training
Rongsheng Wang, Fenghe Tang, Qingsong Yao, Rui Yan, Xu Zhang, Zhen Huang, Haoran Lai, Zhiyang He, Xiaodong Tao, Zihang Jiang, Shaohua Kevin Zhou
https://arxiv.org/abs/2509.08311

SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training
Medical vision-language pre-training shows great potential in learning representative features from massive paired radiographs and reports. However, in computed tomography (CT) scans, the distribution of lesions which contain intricate structures is characterized by spatial sparsity. Besides, the complex and implicit relationships between different pathological descriptions in each sentence of the report and their corresponding sub-regions in radiographs pose additional challenges. In this pape…

Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts
Julius Neumann, Robert Lange, Yuni Susanti, Michael F\"arber
https://arxiv.org/abs/2509.04982

Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts
Sentiment classification in short text datasets faces significant challenges such as class imbalance, limited training samples, and the inherent subjectivity of sentiment labels -- issues that are further intensified by the limited context in short texts. These factors make it difficult to resolve ambiguity and exacerbate data sparsity, hindering effective learning. In this paper, we evaluate the effectiveness of small Transformer-based models (i.e., BERT and RoBERTa, with fewer than 1 billion …

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…

HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
Xinyi Wang, Jinyi Han, Zishang Jiang, Tingyun Li, Jiaqing Liang, Sihang Jiang, Zhaoqian Dai, Shuguang Ma, Fei Yu, Yanghua Xiao
https://arxiv.org/abs/2510.09388

HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods like GRPO often fail when task difficulty exceeds the model's capacity, leading to reward sparsity and inefficient training. While prior work attempts to mitigate this using off-policy data, such as mixing RL with Supervised Fine-Tuning (SFT) or using hints, they often misguide policy updates In this work, we identif…

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…

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…

ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
Lawrence Liu, Alexander Liu, Mengdi Wang, Tuo Zhao, Lin F. Yang
https://arxiv.org/abs/2510.05528

ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
Large language models (LLMs) present significant deployment challenges due to their immense computational and memory requirements. While semi-structured pruning, particularly 2:4 sparsity, offers a path to practical hardware acceleration, existing methods often incur substantial performance degradation. To bridge this gap, we introduce ARMOR: (Adaptive Representation with Matrix-factORization), a novel one-shot post-training pruning algorithm. Instead of directly pruning weights, ARMOR factoriz…

Revisiting Mixout: An Overlooked Path to Robust Finetuning
Masih Aminbeidokhti, Heitor Rapela Medeiros, Eric Granger, Marco Pedersoli
https://arxiv.org/abs/2510.06982 https://…

Revisiting Mixout: An Overlooked Path to Robust Finetuning
Finetuning vision foundation models often improves in-domain accuracy but comes at the cost of robustness under distribution shift. We revisit Mixout, a stochastic regularizer that intermittently replaces finetuned weights with their pretrained reference, through the lens of a single-run, weight-sharing implicit ensemble. This perspective reveals three key levers that govern robustness: the \emph{masking anchor}, \emph{resampling frequency}, and \emph{mask sparsity}. Guided by this analysis, we…

ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL
Egor Cherepanov, Alexey K. Kovalev, Aleksandr I. Panov
https://arxiv.org/abs/2510.07151 https://

ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL
Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without incorporating insights from the past. Standard recurrent or transformer models struggle with retaining and leveraging long-term dependencies: context windows truncate history, while naive memory extensions fail under scale and sparsity. We propose ELMUR (External Laye…