Tootfinder

SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
Jiehui Luo, Yuguo Yin, Yuxin Xie, Jinghan Ru, Xianwei Zhuang, Minghua He, Aofan Liu, Zihan Xiong, Dongchao Yang
https://arxiv.org/abs/2509.21033

SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
Contrastive language-audio pretraining, which aims to unify multimodal representations in a shared embedding space, serves as a cornerstone for building a wide range of applications, from cross-modal retrieval to cutting-edge multimodal large language models. However, we find that the perpendicular component of the pushing force from negative samples in contrastive learning is a double-edged sword: it contains rich supplementary information from negative samples, yet its unconstrained nature ca…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/8]:
- Regularization can make diffusion models more efficient
Mahsa Taheri, Johannes Lederer

Learning to Look: Cognitive Attention Alignment with Vision-Language Models
Ryan L. Yang, Dipkamal Bhusal, Nidhi Rastogi
https://arxiv.org/abs/2509.21247 https://

Learning to Look: Cognitive Attention Alignment with Vision-Language Models
Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of attention in robust human perception, recent methods have sought to guide model attention using concept-based supervision and explanation regularization. However, these techniques depend on labor-intensive, expert-provided annotations, limiting their scalability. We …

Optimal Transport Based Hyperspectral Unmixing for Highly Mixed Observations
D. Doutsas, B. Figliuzzi
https://arxiv.org/abs/2509.20417 https://arxiv.org/pd…

Optimal Transport Based Hyperspectral Unmixing for Highly Mixed Observations
We propose a novel approach based on optimal transport (OT) for tackling the problem of highly mixed data in blind hyperspectral unmixing. Our method constrains the distribution of the estimated abundance matrix to resemble a targeted Dirichlet distribution more closely. The novelty lies in using OT to measure the discrepancy between the targeted and true abundance distributions, which we incorporate as a regularization term in our optimization problem. We demonstrate the efficiency of our meth…

Relaxation to equilibrium of conservative dynamics II: non-gradient exclusion processes
Chenlin Gu, Linzhi Yang
https://arxiv.org/abs/2509.20797 https://ar…

Relaxation to equilibrium of conservative dynamics II: non-gradient exclusion processes
For the speed-change exclusion process on $\mathbb{Z}^d$ reversible with respect to the product Bernoulli measure, we prove that its semigroup $P_t$ satisfies a variance decay $\operatorname{Var}[P_t u] = C_u t^{-\frac{d}{2}} + o(t^{-\frac{d+δ}{2}})$ for every local function $u$, with the constant $C_u$ explicitly characterized. This extends the result of Janvresse, Landim, Quastel and Yau in [Ann. Probab. 27(1) 325--360, 1999] to a non-gradient model. The proof combines the regularization arg…

Simplifying Optimal Transport through Schatten-$p$ Regularization
Tyler Maunu
https://arxiv.org/abs/2510.11910 https://arxiv.org/pdf/2510.11910

Simplifying Optimal Transport through Schatten-$p$ Regularization
We propose a new general framework for recovering low-rank structure in optimal transport using Schatten-$p$ norm regularization. Our approach extends existing methods that promote sparse and interpretable transport maps or plans, while providing a unified and principled family of convex programs that encourage low-dimensional structure. The convexity of our formulation enables direct theoretical analysis: we derive optimality conditions and prove recovery guarantees for low-rank couplings and …

Why the noise model matters: A performance gap in learned regularization
Sebastian Banert, Christoph Brauer, Dirk Lorenz, Lionel Tondji
https://arxiv.org/abs/2510.12521 https://…

Why the noise model matters: A performance gap in learned regularization
This article addresses the challenge of learning effective regularizers for linear inverse problems. We analyze and compare several types of learned variational regularization against the theoretical benchmark of the optimal affine reconstruction, i.e. the best possible affine linear map for minimizing the mean squared error. It is known that this optimal reconstruction can be achieved using Tikhonov regularization, but this requires precise knowledge of the noise covariance to properly weight …

Generalized Mandelstam-Leibbrandt regularization
Jorge Alfaro
https://arxiv.org/abs/2510.01200 https://arxiv.org/pdf/2510.01200

Generalized Mandelstam-Leibbrandt regularization
Algebraic non-covariant gauges are used often in string theory, Chern-Simons theory, gravitation and gauge theories. Loop integrals, however, have spurious singularities that need to be regularized. The most popular and consistent regularization is the Mandelstam- Leibbrandt(ML) prescription. This paper extends the ML prescription outside the light cone. It shares all the properties of light-cone ML regularization: It preserves naive power counting and gauge invariance. Moreover, using di…

Optimal Regularization Under Uncertainty: Distributional Robustness and Convexity Constraints
Oscar Leong, Eliza O'Reilly, Yong Sheng Soh
https://arxiv.org/abs/2510.03464 ht…

Optimal Regularization Under Uncertainty: Distributional Robustness and Convexity Constraints
Regularization is a central tool for addressing ill-posedness in inverse problems and statistical estimation, with the choice of a suitable penalty often determining the reliability and interpretability of downstream solutions. While recent work has characterized optimal regularizers for well-specified data distributions, practical deployments are often complicated by distributional uncertainty and the need to enforce structural constraints such as convexity. In this paper, we introduce a frame…

Approximate Proximal Operators for Analog Compressed Sensing Using PN-junction Diode
Soma Furusawa, Taisei Kato, Ryo Hayakawa, Kazunori Hayashi
https://arxiv.org/abs/2510.12065 …

Approximate Proximal Operators for Analog Compressed Sensing Using PN-junction Diode
In order to realize analog compressed sensing, the paper considers approximate proximal operators of the $\ell_1$ and minimax concave penalty (MCP) regularization functions. Specifically, we propose to realize the approximate functions by an electric analog circuit using forward voltage-current (V-I) characteristics of the PN-junction diodes. To confirm the validity of the proposed approach, we employ the proposed approximate proximal operators for the $\ell_1$ and MCP regularization functions …

DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation
Guowei Zou, Haitao Wang, Hejun Wu, Yukun Qian, Yuhang Wang, Weibing Li
https://arxiv.org/abs/2510.07865

DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation
The ability to learn multi-modal action distributions is indispensable for robotic manipulation policies to perform precise and robust control. Flow-based generative models have recently emerged as a promising solution to learning distributions of actions, offering one-step action generation and thus achieving much higher sampling efficiency compared to diffusion-based methods. However, existing flow-based policies suffer from representation collapse, the inability to distinguish similar visual…

Mitigating Forgetting in Low Rank Adaptation
Joanna Sliwa, Frank Schneider, Philipp Hennig, Jose Miguel Hernandez-Lobato
https://arxiv.org/abs/2512.17720 https://arxiv.org/pdf/2512.17720 https://arxiv.org/html/2512.17720
arXiv:2512.17720v1 Announce Type: new
Abstract: Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), enable fast specialization of large pre-trained models to different downstream applications. However, this process often leads to catastrophic forgetting of the model's prior domain knowledge. We address this issue with LaLoRA, a weight-space regularization technique that applies a Laplace approximation to Low-Rank Adaptation. Our approach estimates the model's confidence in each parameter and constrains updates in high-curvature directions, preserving prior knowledge while enabling efficient target-domain learning. By applying the Laplace approximation only to the LoRA weights, the method remains lightweight. We evaluate LaLoRA by fine-tuning a Llama model for mathematical reasoning and demonstrate an improved learning-forgetting trade-off, which can be directly controlled via the method's regularization strength. We further explore different loss landscape curvature approximations for estimating parameter confidence, analyze the effect of the data used for the Laplace approximation, and study robustness across hyperparameters.
toXiv_bot_toot

Beyond Regularization: Inherently Sparse Principal Component Analysis
Jan O. Bauer
https://arxiv.org/abs/2510.03729 https://arxiv.org/pdf/2510.03729…

Beyond Regularization: Inherently Sparse Principal Component Analysis
Sparse principal component analysis (sparse PCA) is a widely used technique for dimensionality reduction in multivariate analysis, addressing two key limitations of standard PCA. First, sparse PCA can be implemented in high-dimensional low sample size settings, such as genetic microarrays. Second, it improves interpretability as components are regularized to zero. However, over-regularization of sparse singular vectors can cause them to deviate greatly from the population singular vectors, pote…

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
Wenpu Li, Bangyan Liao, Yi Zhou, Qi Xu, Pian Wan, Peidong Liu
https://arxiv.org/abs/2510.12753

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
The estimation of optical flow and 6-DoF ego-motion, two fundamental tasks in 3D vision, has typically been addressed independently. For neuromorphic vision (e.g., event cameras), however, the lack of robust data association makes solving the two problems separately an ill-posed challenge, especially in the absence of supervision via ground truth. Existing works mitigate this ill-posedness by either enforcing the smoothness of the flow field via an explicit variational regularizer or leveraging…

Exploring rapidity regularization schemes at low $x$ with the DIS longitudinal structure function
Tolga Altinoluk, Guillaume Beuf, Jani Penttala
https://arxiv.org/abs/2510.08550

Exploring rapidity regularization schemes at low $x$ with the DIS longitudinal structure function
We propose three possible rapidity regulators for higher-order calculations in low $x$ QCD with gluon saturation, as alternatives to the usual lower cut-off for the integrals over the light-cone momentum $k^+$. These rapidity regulators are closely related to the $η$ regulator and to the pure rapidity regulator, which have been used primarily in studies of transverse-momentum-dependent (TMD) factorization within the soft-collinear effective theory (SCET). By choosing one of the three rapidity …

Randomized flexible Krylov methods for $\ell_p$ regularization
Malena Sabat\'e Landman, Yuji Nakatsukasa
https://arxiv.org/abs/2510.11237 https://arxiv…

Randomized flexible Krylov methods for $\ell_p$ regularization
The computation of sparse solutions of large-scale linear discrete ill-posed problems remains a computationally demanding task. A powerful framework in this context is the use of iteratively reweighted schemes, which are based on constructing a sequence of quadratic tangent majorants of the $\ell_2$-$\ell_1$ regularization functional (with additional smoothing to ensure differentiability at the origin), and solving them successively. Recently, flexible Krylov-Tikhonov methods have been used to …

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…

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/3]:
- Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforc...
Xiaoyun Zhang, Xiaojian Yuan, Di Huang, Wang You, Chen Hu, Jingqing Ruan, Kejiang Chen, Xing Hu

A Comprehensive Survey of Website Fingerprinting Attacks and Defenses in Tor: Advances and Open Challenges
Yuwen Cui, Guangjing Wang, Khanh Vu, Kai Wei, Kehan Shen, Zhengyuan Jiang, Xiao Han, Ning Wang, Zhuo Lu, Yao Liu
https://arxiv.org/abs/2510.11804

A Comprehensive Survey of Website Fingerprinting Attacks and Defenses in Tor: Advances and Open Challenges
The Tor network provides users with strong anonymity by routing their internet traffic through multiple relays. While Tor encrypts traffic and hides IP addresses, it remains vulnerable to traffic analysis attacks such as the website fingerprinting (WF) attack, achieving increasingly high fingerprinting accuracy even under open-world conditions. In response, researchers have proposed a variety of defenses, ranging from adaptive padding, traffic regularization, and traffic morphing to adversarial…

Re$^3$MCN: Cubic Newton Variance Reduction Momentum Quadratic Regularization for Finite-sum Non-convex Problems
Dmitry Pasechnyuk-Vilensky, Dmitry Kamzolov, Martin Tak\'a\v{c}
https://arxiv.org/abs/2510.08714

Re$^3$MCN: Cubic Newton + Variance Reduction + Momentum + Quadratic Regularization for Finite-sum Non-convex Problems
We analyze a stochastic cubic regularized Newton method for finite sum optimization $\textstyle\min_{x\in\mathbb{R}^d} F(x) \;=\; \frac{1}{n}\sum_{i=1}^n f_i(x)$, that uses SARAH-type recursive variance reduction with mini-batches of size $b\sim n^{1/2}$ and exponential moving averages (EMA) for gradient and Hessian estimators. We show that the method achieves a $(\varepsilon,\sqrt{L_2\varepsilon})$-second-order stationary point (SOSP) with total stochastic oracle calls $n + \widetilde{\mathcal…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[4/8]:
- DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation
Guowei Zou, Haitao Wang, Hejun Wu, Yukun Qian, Yuhang Wang, Weibing Li

Contrastive Representation Regularization for Vision-Language-Action Models
Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin
https://arxiv.org/abs/2510.01711

Contrastive Representation Regularization for Vision-Language-Action Models
Vision-Language-Action (VLA) models have shown its capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive states. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for VLA models, designed to bridge the gap betwee…

Beyond Real Data: Synthetic Data through the Lens of Regularization
Amitis Shidani, Tyler Farghly, Yang Sun, Habib Ganjgahi, George Deligiannidis
https://arxiv.org/abs/2510.08095

Beyond Real Data: Synthetic Data through the Lens of Regularization
Synthetic data can improve generalization when real data is scarce, but excessive reliance may introduce distributional mismatches that degrade performance. In this paper, we present a learning-theoretic framework to quantify the trade-off between synthetic and real data. Our approach leverages algorithmic stability to derive generalization error bounds, characterizing the optimal synthetic-to-real data ratio that minimizes expected test error as a function of the Wasserstein distance between t…

Instance-Aware Robust Consistency Regularization for Semi-Supervised Nuclei Instance Segmentation
Zenan Lin, Wei Li, Jintao Chen, Zihao Wu, Wenxiong Kang, Changxin Gao, Liansheng Wang, Jin-Gang Yu
https://arxiv.org/abs/2510.09329

Instance-Aware Robust Consistency Regularization for Semi-Supervised Nuclei Instance Segmentation
Nuclei instance segmentation in pathological images is crucial for downstream tasks such as tumor microenvironment analysis. However, the high cost and scarcity of annotated data limit the applicability of fully supervised methods, while existing semi-supervised methods fail to adequately regularize consistency at the instance level, lack leverage of the inherent prior knowledge of pathological structures, and are prone to introducing noisy pseudo-labels during training. In this paper, we propo…

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
Zhenglin Wan, Jingxuan Wu, Xingrui Yu, Chubin Zhang, Mingcong Lei, Bo An, Ivor Tsang
https://arxiv.org/abs/2510.09222

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based policies are inherently limited by their lack of environmental interaction and exploration. This leads to poor generalization in unseen scenarios beyond the expert demonstrations, underscoring the necessity of online interaction with environment. Unfortunately…

Geometric Spatio-Spectral Total Variation for Hyperspectral Image Denoising and Destriping
Shingo Takemoto, Shunsuke Ono
https://arxiv.org/abs/2510.00562 https://

Geometric Spatio-Spectral Total Variation for Hyperspectral Image Denoising and Destriping
This article proposes a novel regularization method, named Geometric Spatio-Spectral Total Variation (GeoSSTV), for hyperspectral (HS) image denoising and destriping. HS images are inevitably affected by various types of noise due to the measurement equipment and environment. Total Variation (TV)-based regularization methods that model the spatio-spectral piecewise smoothness inherent in HS images are promising approaches for HS image denoising and destriping. However, existing TV-based methods…

Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials
Jaesun Kim, Jinmu You, Yutack Park, Yunsung Lim, Yujin Kang, Jisu Kim, Haekwan Jeon, Deokgi Hong, Seung Yul Lee, Saerom Choi, Yongdeok Kim, Jae W. Lee, Seungwu Han
https://arxiv.org/abs/2510.11241

Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials
Accurate yet transferable machine-learning interatomic potentials (MLIPs) are essential for accelerating materials and chemical discovery. However, most universal MLIPs overfit to narrow datasets or computational protocols, limiting their reliability across chemical and functional domains. We introduce a transferable multi-domain training strategy that jointly optimizes universal and task-specific parameters through selective regularization, coupled with a domain-bridging set (DBS) that aligns …

Macroeconomic Forecasting and Machine Learning
Ta-Chung Chi (Kevin), Ting-Han Fan (Kevin), Raffaele M. Ghigliazza (Kevin), Domenico Giannone (Kevin), Zixuan (Kevin), Wang
https://arxiv.org/abs/2510.11008

Macroeconomic Forecasting and Machine Learning
We forecast the full conditional distribution of macroeconomic outcomes by systematically integrating three key principles: using high-dimensional data with appropriate regularization, adopting rigorous out-of-sample validation procedures, and incorporating nonlinearities. By exploiting the rich information embedded in a large set of macroeconomic and financial predictors, we produce accurate predictions of the entire profile of macroeconomic risk in real time. Our findings show that regulariza…

Well-Posedness and Efficient Algorithms for Inverse Optimal Transport with Bregman Regularization
Chenglong Bao, Zanyu Li, Yunan Yang
https://arxiv.org/abs/2510.03803 https://…

Well-Posedness and Efficient Algorithms for Inverse Optimal Transport with Bregman Regularization
This work analyzes the inverse optimal transport (IOT) problem under Bregman regularization. We establish well-posedness results, including existence, uniqueness (up to equivalence classes of solutions), and stability, under several structural assumptions on the cost matrix. On the computational side, we investigate the existence of solutions to the optimization problem with general constraints on the cost matrix and provide a sufficient condition guaranteeing existence. In addition, we propose…

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
Xingyu Lin, Yilin Wen, En Wang, Du Su, Wenbin Liu, Chenfu Bao, Zhonghou Lv
https://arxiv.org/abs/2510.09369

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance. However, GRPO and related entropy-regularization methods still face challenges rooted in the sparse token rewards inherent to chain-of-thought (CoT). Current approaches often rely on undifferentiated token-level entropy adjustments, which frequently lead to entropy collapse or model collapse. In this work, we propose…

Self-supervised Physics-guided Model with Implicit Representation Regularization for Fast MRI Reconstruction
Jingran Xu, Yuanyuan Liu, Yanjie Zhu
https://arxiv.org/abs/2510.06611

Self-supervised Physics-guided Model with Implicit Representation Regularization for Fast MRI Reconstruction
Magnetic Resonance Imaging (MRI) is a vital clinical diagnostic tool, yet its widespread application is limited by prolonged scan times. Fast MRI reconstruction techniques effectively reduce acquisition duration by reconstructing high-fidelity MR images from undersampled k-space data. In recent years, deep learning-based methods have demonstrated remarkable progress in this field, with self-supervised and unsupervised learning approaches proving particularly valuable in scenarios where fully sa…

A Random Matrix Perspective of Echo State Networks: From Precise Bias--Variance Characterization to Optimal Regularization
Yessin Moakher, Malik Tiomoko, Cosme Louart, Zhenyu Liao
https://arxiv.org/abs/2509.22011

A Random Matrix Perspective of Echo State Networks: From Precise Bias--Variance Characterization to Optimal Regularization
We present a rigorous asymptotic analysis of Echo State Networks (ESNs) in a teacher student setting with a linear teacher with oracle weights. Leveraging random matrix theory, we derive closed form expressions for the asymptotic bias, variance, and mean-squared error (MSE) as functions of the input statistics, the oracle vector, and the ridge regularization parameter. The analysis reveals two key departures from classical ridge regression: (i) ESNs do not exhibit double descent, and (ii) ESNs …

Rethinking Entropy Regularization in Large Reasoning Models
Yuxian Jiang, Yafu Li, Guanxu Chen, Dongrui Liu, Yu Cheng, Jing Shao
https://arxiv.org/abs/2509.25133 https://…

Rethinking Entropy Regularization in Large Reasoning Models
Reinforcement learning with verifiable rewards (RLVR) has shown great promise in enhancing the reasoning abilities of large reasoning models (LRMs). However, it suffers from a critical issue: entropy collapse and premature convergence. Naive entropy regularization, a common approach for encouraging exploration in the traditional RL literature, fails to address this problem in the context of LRM. Our analysis reveals that this failure stems from the vast action space and long trajectories in LRM…

Waves, structures, and the Riemann problem for a system of hyperbolic conservation laws
A. P. Chugainova, D. V. Treschev
https://arxiv.org/abs/2510.02070 https://

Waves, structures, and the Riemann problem for a system of hyperbolic conservation laws
A system of hyperbolic conservation laws $$ \partial_t u + \partial_x \partial_u Q = 0, \quad Q = u_1^3 / 3 + u_1 u_2^2, \qquad u = u(x,t) \in\mR^2, $$ as well as its viscous regularization $$ \partial_t u + \partial_x \partial_u Q = \calM \partial_x^2 u, \qquad \calM = \diag (μ_1,μ_2), \quad μ_1>0,\, μ_2>0, $$ are studied. It is assumed that admissible shocks are those that satisfy the requirement of existence of a structure (the traveling wave criterion). A solution of the Riemann…

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…

Calibrated Counterfactual Conformal Fairness ($C^3F$): Post-hoc, Shift-Aware Coverage Parity via Conformal Prediction and Counterfactual Regularization
Faruk Alpay, Taylan Alpay
https://arxiv.org/abs/2509.25295

Calibrated Counterfactual Conformal Fairness ($C^3F$): Post-hoc, Shift-Aware Coverage Parity via Conformal Prediction and Counterfactual Regularization
We present Calibrated Counterfactual Conformal Fairness ($C^3F$), a post-hoc procedure that targets group-conditional coverage parity under covariate shift. $C^3F$ combines importance-weighted conformal calibration with a counterfactual regularizer based on path-specific effects in a structural causal model. The method estimates group-specific nonconformity quantiles using likelihood-ratio weights so that coverage degrades gracefully with the second moment of the weights. We derive finite-sampl…

Improving Speech Emotion Recognition with Mutual Information Regularized Generative Model
Chung-Soo Ahn, Rajib Rana, Sunil Sivadas, Carlos Busso, Jagath C. Rajapakse
https://arxiv.org/abs/2510.10078

Improving Speech Emotion Recognition with Mutual Information Regularized Generative Model
Although speech emotion recognition (SER) research has been advanced, thanks to deep learning methods, it still suffers from obtaining inputs from large quality-labelled training data. Data augmentation methods have been attempted to mitigate this issue, generative models have shown success among them recently. We propose a data augmentation framework that is aided by cross-modal information transfer and mutual information regularization. Mutual information based metric can serve as an indicato…

Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization
Kanglei Zhou, Qingyi Pan, Xingxing Zhang, Hubert P. H. Shum, Frederick W. B. Li, Xiaohui Liang, Liyuan Wang
https://arxiv.org/abs/2510.06842

Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization
Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation. A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios, which limits the generalization ability of conventional methods. We introduce Continual AQA (CAQA), which equips AQA with Continual Learning (CL) capabilities to handle evolving distributions while mitigating catastrophic forgetting. Although param…

Crosslisted article(s) found for math.MG. https://arxiv.org/list/math.MG/new
[1/1]:
- Optimal Regularization Under Uncertainty: Distributional Robustness and Convexity Constraints
Oscar Leong, Eliza O'Reilly, Yong Sheng Soh

Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
Valentyn Melnychuk, Dennis Frauen, Jonas Schweisthal, Stefan Feuerriegel
https://arxiv.org/abs/2509.24962

Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
The conditional average treatment effect (CATE) is widely used in personalized medicine to inform therapeutic decisions. However, state-of-the-art methods for CATE estimation (so-called meta-learners) often perform poorly in the presence of low overlap. In this work, we introduce a new approach to tackle this issue and improve the performance of existing meta-learners in the low-overlap regions. Specifically, we introduce Overlap-Adaptive Regularization (OAR) that regularizes target models prop…

Lectures on stochastic sewing with applications
Oleg Butkovsky
https://arxiv.org/abs/2510.12165 https://arxiv.org/pdf/2510.12165

Lectures on stochastic sewing with applications
These are lecture notes for a mini-course on stochastic sewing, taught at the University of Edinburgh and Beijing Institute of Technology in Spring/Summer 2025. The aim is to introduce the reader to stochastic sewing techniques and to show how they can be successfully applied to study various problems in stochastic analysis, including: regularization by noise for stochastic differential equations driven by Brownian motion or fractional Brownian motion, well-posedness of stochastic PDEs with irr…

General Divergence Regularized Optimal Transport: Sample Complexity and Central Limit Theorems
Jiaping Yang, Yunxin Zhang
https://arxiv.org/abs/2510.02489 https://

General Divergence Regularized Optimal Transport: Sample Complexity and Central Limit Theorems
Optimal transport has emerged as a fundamental methodology with applications spanning multiple research areas in recent years. However, the convergence rate of the empirical estimator to its population counterpart suffers from the curse of dimensionality, which prevents its application in high-dimensional spaces. While entropic regularization has been proven to effectively mitigate the curse of dimensionality and achieve a parametric convergence rate under mild conditions, these statistical gua…

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,…

Adaptive double-phase Rudin--Osher--Fatemi denoising model
Wojciech G\'orny, Micha{\l} {\L}asica, Alexandros Matsoukas
https://arxiv.org/abs/2510.04382 https://

Adaptive double-phase Rudin--Osher--Fatemi denoising model
We propose a new image denoising model based on a variable-growth total variation regularization of double-phase type with adaptive weight. It is designed to reduce staircasing with respect to the classical Rudin--Osher--Fatemi model, while preserving the edges of the image in a similar fashion. We implement the model and test its performance on synthetic and natural images in 1D and 2D over a range of noise levels.

A Source Identification Problem for the Bi-Parabolic Equation Containing a Poly-harmonic Operator
Dang Duc Trong, Bui Thanh Duy, Nguyen Dang Minh
https://arxiv.org/abs/2509.24470

A Source Identification Problem for the Bi-Parabolic Equation Containing a Poly-harmonic Operator
In this paper, we address the source identification problem for the bi-parabolic equation involving a operator. Specifically, we investigate the equation $(\partial_t +\frak A)^2u(t)=ψ(t)f$, where $\frak A$ denotes a poly-harmonic operator. Given the perturbed data of $ψ$ and $u(T)$ (where $T>0$), our objective is to determine $f$. Although several scientific publications have explored regularization techniques for bi-parabolic problems, the existing literature remains limited. By relaxing ce…

Contraction and entropy production in continuous-time Sinkhorn dynamics
Anand Srinivasan, Jean-Jacques Slotine
https://arxiv.org/abs/2510.12639 https://arx…

Contraction and entropy production in continuous-time Sinkhorn dynamics
Recently, the vanishing-step-size limit of the Sinkhorn algorithm at finite regularization parameter $\varepsilon$ was shown to be a mirror descent in the space of probability measures. We give $L^2$ contraction criteria in two time-dependent metrics induced by the mirror Hessian, which reduce to the coercivity of certain conditional expectation operators. We then give an exact identity for the entropy production rate of the Sinkhorn flow, which was previously known only to be nonpositive. Exam…

Regularized Random Fourier Features and Finite Element Reconstruction for Operator Learning in Sobolev Space
Xinyue Yu, Hayden Schaeffer
https://arxiv.org/abs/2512.17884 https://arxiv.org/pdf/2512.17884 https://arxiv.org/html/2512.17884
arXiv:2512.17884v1 Announce Type: new
Abstract: Operator learning is a data-driven approximation of mappings between infinite-dimensional function spaces, such as the solution operators of partial differential equations. Kernel-based operator learning can offer accurate, theoretically justified approximations that require less training than standard methods. However, they can become computationally prohibitive for large training sets and can be sensitive to noise. We propose a regularized random Fourier feature (RRFF) approach, coupled with a finite element reconstruction map (RRFF-FEM), for learning operators from noisy data. The method uses random features drawn from multivariate Student's $t$ distributions, together with frequency-weighted Tikhonov regularization that suppresses high-frequency noise. We establish high-probability bounds on the extreme singular values of the associated random feature matrix and show that when the number of features $N$ scales like $m \log m$ with the number of training samples $m$, the system is well-conditioned, which yields estimation and generalization guarantees. Detailed numerical experiments on benchmark PDE problems, including advection, Burgers', Darcy flow, Helmholtz, Navier-Stokes, and structural mechanics, demonstrate that RRFF and RRFF-FEM are robust to noise and achieve improved performance with reduced training time compared to the unregularized random feature model, while maintaining competitive accuracy relative to kernel and neural operator tests.
toXiv_bot_toot

Replaced article(s) found for eess.SY. https://arxiv.org/list/eess.SY/new
[1/1]:
- Sparse dynamic network reconstruction through L1-regularization of a Lyapunov equation
Belaustegui, Arango, Rossi-Pool, Leonard, Franci

Irrationality as a mean of regularization in Bayesian Persuasion
Romain Duboscq (IMT, INSA Toulouse), Fr\'ed\'eric de Gournay (IMT, INSA Toulouse)
https://arxiv.org/abs/2510.01759

Irrationality as a mean of regularization in Bayesian Persuasion
We study a regularized variant of the Bayesian Persuasion problem, where the receiver's decision process includes a divergence-based penalty that accounts for deviations from perfect rationality. This modification smooths the underlying optimization landscape and mitigates key theoretical issues, such as measurability and ill-posedness, commonly encountered in the classical formulation. It also enables the use of scalable second-order optimization methods to compute numerically the optimal sign…

Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
Wei Tang, Yin-Fang Yang, Weijia Zhang, Min-Ling Zhang
https://arxiv.org/abs/2512.17788 https://arxiv.org/pdf/2512.17788 https://arxiv.org/html/2512.17788
arXiv:2512.17788v1 Announce Type: new
Abstract: Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to address the challenges of inexact supervision in both instance and label spaces. However, existing MIPL approaches often suffer from poor calibration, undermining classifier reliability. In this work, we propose a plug-and-play calibratable disambiguation loss (CDL) that simultaneously improves classification accuracy and calibration performance. The loss has two instantiations: the first one calibrates predictions based on probabilities from the candidate label set, while the second one integrates probabilities from both candidate and non-candidate label sets. The proposed CDL can be seamlessly incorporated into existing MIPL and PLL frameworks. We provide a theoretical analysis that establishes the lower bound and regularization properties of CDL, demonstrating its superiority over conventional disambiguation losses. Experimental results on benchmark and real-world datasets confirm that our CDL significantly enhances both classification and calibration performance.
toXiv_bot_toot

Beyond the Euler--Mascheroni Constant: A Family of Functionals
Ken Nagai
https://arxiv.org/abs/2509.22289 https://arxiv.org/pdf/2509.22289

Beyond the Euler--Mascheroni Constant: A Family of Functionals
We introduce a family of regularized functionals $g_n(x)$ that generalize the Euler--Mascheroni constant $γ$. They arise from a weighted regularization of Clausen-type trigonometric sums, and admit explicit integral representations, differential and ladder relations, together with an umbral generating function.

FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation
Ding-Ruei Shen
https://arxiv.org/abs/2510.02114 https://arxiv.org/pdf/2510…

FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation
Federeated Learning (FL) offers a privacy-preserving solution for Semantic Segmentation (SS) tasks to adapt to new domains, but faces significant challenges from these domain shifts, particularly when client data is unlabeled. However, most existing FL methods unrealistically assume access to labeled data on remote clients or fail to leverage the power of modern Vision Foundation Models (VFMs). Here, we propose a novel and challenging task, FFREEDG, in which a model is pretrained on a server's …

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 …

Bayesian Transfer Learning for High-Dimensional Linear Regression via Adaptive Shrinkage
Parsa Jamshidian, Donatello Telesca
https://arxiv.org/abs/2510.03449 https://

Bayesian Transfer Learning for High-Dimensional Linear Regression via Adaptive Shrinkage
We introduce BLAST, Bayesian Linear regression with Adaptive Shrinkage for Transfer, a Bayesian multi-source transfer learning framework for high-dimensional linear regression. The proposed analytical framework leverages global-local shrinkage priors together with Bayesian source selection to balance information sharing and regularization. We show how Bayesian source selection allows for the extraction of the most useful data sources, while discounting biasing information that may lead to negat…

Data-Driven Filtering of the Spherical Harmonics Method
Benjamin Plumridge, Cory Hauck, Steffen Schotthofer
https://arxiv.org/abs/2510.05452 https://arxiv.…

Data-Driven Filtering of the Spherical Harmonics Method
We investigate a data-driven approach for tuning the filtered spherical harmonics method (\fpn) when solving the radiation transport equation (RTE). The \fpn method extends the classical spherical harmonics approach (\pn) by introducing regularization through a filter operator, which mitigates spurious oscillations caused by Gibbs' phenomenon. This filter includes a tunable parameter, the {filter strength}, that controls the degree of smoothing applied to the solution. However, selecting an opt…

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[1/2]:
- Multiparameter regularization and aggregation in the context of polynomial functional regression
Gizewski, Holzleitner, Mayer-Suess, Pereverzyev, Pereverzyev

Generalization Analysis for Classification on Korobov Space
Yuqing Liu
https://arxiv.org/abs/2509.22748 https://arxiv.org/pdf/2509.22748

Generalization Analysis for Classification on Korobov Space
In this paper, the classification algorithm arising from Tikhonov regularization is discussed. The main intention is to derive learning rates for the excess misclassification error according to the convex $η$-norm loss function $ϕ(v)=(1 - v)_{+}^η$, $η\geq1$. Following the argument, the estimation of error under Tsybakov noise conditions is studied. In addition, we propose the rate of $L_p$ approximation of functions from Korobov space $X^{2, p}([-1,1]^{d})$, $1\leq p \leq \infty$, by the s…

Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar, Hanxue Liang, Wanru Zhao, Paul Whatmough
https://arxiv.org/abs/2510.01185

Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
Upcycling pre-trained dense models into sparse Mixture-of-Experts (MoEs) efficiently increases model capacity but often suffers from poor expert specialization due to naive weight replication. Our analysis reveals that upcycled MoEs, even with conventional regularization, exhibit low-confidence, weakly differentiated routing, hindering performance. We introduce Dirichlet-Prior Shaping Loss (DPSL), a novel router regularization technique that directly shapes routing probability distributions by …

On fundamental properties of high-order forward-backward envelope
Alireza Kabgani, Masoud Ahookhosh
https://arxiv.org/abs/2511.10421 https://arxiv.org/pdf/2511.10421 https://arxiv.org/html/2511.10421
arXiv:2511.10421v1 Announce Type: new
Abstract: This paper studies the fundamental properties of the high-order forward-backward splitting mapping (HiFBS) and its associated forward-backward envelope (HiFBE) through the lens of high-order regularization for nonconvex composite functions. Specifically, we (i) establish the boundedness and uniform boundedness of HiFBS, along with the H\"older and Lipschitz continuity of HiFBE; (ii) derive an explicit form for the subdifferentials of HiFBE; and (iii) investigate necessary and sufficient conditions for the differentiability and weak smoothness of HiFBE under suitable assumptions. By leveraging the prox-regularity of $g$ and the concept of $p$-calmness, we further demonstrate the local single-valuedness and continuity of HiFBS, which in turn guarantee the differentiability of HiFBE in neighborhoods of calm points. This paves the way for the development of gradient-based algorithms tailored to nonconvex composite optimization problems.
toXiv_bot_toot

A convergent adaptive finite element method for a phase-field model of dynamic fracture
Ram Manohar, S. M. Mallikarjuaniah
https://arxiv.org/abs/2510.05407 https://

A convergent adaptive finite element method for a phase-field model of dynamic fracture
We propose and analyze an adaptive finite element method for a phase-field model of dynamic brittle fracture. The model couples a second-order hyperbolic equation for elastodynamics with the Ambrosio-Tortorelli regularization of the Francfort-Marigo variational fracture energy, which circumvents the need for explicit crack tracking. Our numerical scheme combines a staggered time-stepping algorithm with a variational inequality formulation to strictly enforce the irreversibility of damage. The m…

Replaced article(s) found for stat.ME. https://arxiv.org/list/stat.ME/new
[1/1]:
- Joint identification of spatially variable genes via a network-assisted Bayesian regularization a...
Mingcong Wu, Yang Li, Shuangge Ma, Mengyun Wu

Spectral Flow Learning Theory: Finite-Sample Guarantees for Vector-Field Identification
Chi Ho Leung, Philip E. Par\'e
https://arxiv.org/abs/2509.25000 https://

Spectral Flow Learning Theory: Finite-Sample Guarantees for Vector-Field Identification
We study the identification of continuous-time vector fields from irregularly sampled trajectories. We introduce Spectral Flow Learning (SFL), which learns in a windowed flow space using a lag-linear label operator that aggregates lagged Koopman actions. We provide finite-sample high-probability (FS-HP) guarantees for the class of variable-step linear multistep methods (vLLM). The FS-HP rates are constructed using spectral regularization with qualification-controlled filters for flow predictors…

Global Convergence of Four-Layer Matrix Factorization under Random Initialization
Minrui Luo, Weihang Xu, Xiang Gao, Maryam Fazel, Simon Shaolei Du
https://arxiv.org/abs/2511.09925 https://arxiv.org/pdf/2511.09925 https://arxiv.org/html/2511.09925
arXiv:2511.09925v1 Announce Type: new
Abstract: Gradient descent dynamics on the deep matrix factorization problem is extensively studied as a simplified theoretical model for deep neural networks. Although the convergence theory for two-layer matrix factorization is well-established, no global convergence guarantee for general deep matrix factorization under random initialization has been established to date. To address this gap, we provide a polynomial-time global convergence guarantee for randomly initialized gradient descent on four-layer matrix factorization, given certain conditions on the target matrix and a standard balanced regularization term. Our analysis employs new techniques to show saddle-avoidance properties of gradient decent dynamics, and extends previous theories to characterize the change in eigenvalues of layer weights.
toXiv_bot_toot

Zero-Shot Robustness of Vision Language Models Via Confidence-Aware Weighting
Nikoo Naghavian, Mostafa Tavassolipour
https://arxiv.org/abs/2510.02913 https://

Zero-Shot Robustness of Vision Language Models Via Confidence-Aware Weighting
Vision-language models like CLIP demonstrate impressive zero-shot generalization but remain highly vulnerable to adversarial attacks. In this work, we propose Confidence-Aware Weighting (CAW) to enhance zero-shot robustness in vision-language models. CAW consists of two components: (1) a Confidence-Aware loss that prioritizes uncertain adversarial examples by scaling the KL divergence between clean and adversarial predictions, and (2) a feature alignment regularization that preserves semantic c…

Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
Yash Jhaveri, Harley Wiltzer, Patrick Shafto, Marc G. Bellemare, David Meger
https://arxiv.org/abs/2510.08526

Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
In the pursuit of finding an optimal policy, reinforcement learning (RL) methods generally ignore the properties of learned policies apart from their expected return. Thus, even when successful, it is difficult to characterize which policies will be learned and what they will do. In this work, we present a theoretical framework for policy optimization that guarantees convergence to a particular optimal policy, via vanishing entropy regularization and a temperature decoupling gambit. Our approac…

A Warm-basis Method for Bridging Learning and Iteration: a Case Study in Fluorescence Molecular Tomography
Ruchi Guo, Jiahua Jiang, Bangti Jin, Wuwei Ren, Jianru Zhang
https://arxiv.org/abs/2510.05926 …

A Warm-basis Method for Bridging Learning and Iteration: a Case Study in Fluorescence Molecular Tomography
Fluorescence Molecular Tomography (FMT) is a widely used non-invasive optical imaging technology in biomedical research. It usually faces significant accuracy challenges in depth reconstruction, and conventional iterative methods struggle with poor $z$-resolution even with advanced regularization. Supervised learning approaches can improve recovery accuracy but rely on large, high-quality paired training dataset that is often impractical to acquire in practice. This naturally raises the questio…

Transformed $\ell_1$ Regularizations for Robust Principal Component Analysis: Toward a Fine-Grained Understanding
Kun Zhao, Haoke Zhang, Jiayi Wang, Yifei Lou
https://arxiv.org/abs/2510.03624

Transformed $\ell_1$ Regularizations for Robust Principal Component Analysis: Toward a Fine-Grained Understanding
Robust Principal Component Analysis (RPCA) aims to recover a low-rank structure from noisy, partially observed data that is also corrupted by sparse, potentially large-magnitude outliers. Traditional RPCA models rely on convex relaxations, such as nuclear norm and $\ell_1$ norm, to approximate the rank of a matrix and the $\ell_0$ functional (the number of non-zero elements) of another. In this work, we advocate a nonconvex regularization method, referred to as transformed $\ell_1$ (TL1), to im…

S-D-RSM: Stochastic Distributed Regularized Splitting Method for Large-Scale Convex Optimization Problems
Maoran Wang, Xingju Cai, Yongxin Chen
https://arxiv.org/abs/2511.10133 https://arxiv.org/pdf/2511.10133 https://arxiv.org/html/2511.10133
arXiv:2511.10133v1 Announce Type: new
Abstract: This paper investigates the problems large-scale distributed composite convex optimization, with motivations from a broad range of applications, including multi-agent systems, federated learning, smart grids, wireless sensor networks, compressed sensing, and so on. Stochastic gradient descent (SGD) and its variants are commonly employed to solve such problems. However, existing algorithms often rely on vanishing step sizes, strong convexity assumptions, or entail substantial computational overhead to ensure convergence or obtain favorable complexity. To bridge the gap between theory and practice, we integrate consensus optimization and operator splitting techniques (see Problem Reformulation) to develop a novel stochastic splitting algorithm, termed the \emph{stochastic distributed regularized splitting method} (S-D-RSM). In practice, S-D-RSM performs parallel updates of proximal mappings and gradient information for only a randomly selected subset of agents at each iteration. By introducing regularization terms, it effectively mitigates consensus discrepancies among distributed nodes. In contrast to conventional stochastic methods, our theoretical analysis establishes that S-D-RSM achieves global convergence without requiring diminishing step sizes or strong convexity assumptions. Furthermore, it achieves an iteration complexity of $\mathcal{O}(1/\epsilon)$ with respect to both the objective function value and the consensus error. Numerical experiments show that S-D-RSM achieves up to 2--3$\times$ speedup compared to state-of-the-art baselines, while maintaining comparable or better accuracy. These results not only validate the algorithm's theoretical guarantees but also demonstrate its effectiveness in practical tasks such as compressed sensing and empirical risk minimization.
toXiv_bot_toot

Replaced article(s) found for math.OC. https://arxiv.org/list/math.OC/new
[1/1]:
- A robust BFGS algorithm for unconstrained nonlinear optimization problems
Yaguang Yang
https://arxiv.org/abs/1212.5929
- Quantum computing and the stable set problem
Alja\v{z} Krpan, Janez Povh, Dunja Pucher
https://arxiv.org/abs/2405.12845 https://mastoxiv.page/@arXiv_mathOC_bot/112483516437815686
- Mean Field Game with Reflected Jump Diffusion Dynamics: A Linear Programming Approach
Zongxia Liang, Xiang Yu, Keyu Zhang
https://arxiv.org/abs/2508.20388 https://mastoxiv.page/@arXiv_mathOC_bot/115111048711698998
- Differential Dynamic Programming for the Optimal Control Problem with an Ellipsoidal Target Set a...
Sungjun Eom, Gyunghoon Park
https://arxiv.org/abs/2509.07546 https://mastoxiv.page/@arXiv_mathOC_bot/115179281556444440
- On the Moreau envelope properties of weakly convex functions
Marien Renaud, Arthur Leclaire, Nicolas Papadakis
https://arxiv.org/abs/2509.13960 https://mastoxiv.page/@arXiv_mathOC_bot/115224514482363803
- Automated algorithm design via Nevanlinna-Pick interpolation
Ibrahim K. Ozaslan, Tryphon T. Georgiou, Mihailo R. Jovanovic
https://arxiv.org/abs/2509.21416 https://mastoxiv.page/@arXiv_mathOC_bot/115286533597711930
- Optimal Control of a Bioeconomic Crop-Energy System with Energy Reinvestment
Othman Cherkaoui Dekkaki
https://arxiv.org/abs/2510.11381 https://mastoxiv.page/@arXiv_mathOC_bot/115372322896073250
- Point Convergence Analysis of the Accelerated Gradient Method for Multiobjective Optimization: Co...
Yingdong Yin
https://arxiv.org/abs/2510.26382 https://mastoxiv.page/@arXiv_mathOC_bot/115468018035252078
- History-Aware Adaptive High-Order Tensor Regularization
Chang He, Bo Jiang, Yuntian Jiang, Chuwen Zhang, Shuzhong Zhang
https://arxiv.org/abs/2511.05788
- Equivalence of entropy solutions and gradient flows for pressureless 1D Euler systems
Jos\'e Antonio Carrillo, Sondre Tesdal Galtung
https://arxiv.org/abs/2312.04932 https://mastoxiv.page/@arXiv_mathAP_bot/111560077272113052
- Kernel Modelling of Fading Memory Systems
Yongkang Huo, Thomas Chaffey, Rodolphe Sepulchre
https://arxiv.org/abs/2403.11945 https://mastoxiv.page/@arXiv_eessSY_bot/112121123836064435
- The Maximum Theoretical Ground Speed of the Wheeled Vehicle
Altay Zhakatayev, Mukatai Nemerebayev
https://arxiv.org/abs/2502.15341 https://mastoxiv.page/@arXiv_physicsclassph_bot/114057765769441123
- Hessian stability and convergence rates for entropic and Sinkhorn potentials via semiconcavity
Giacomo Greco, Luca Tamanini
https://arxiv.org/abs/2504.11133 https://mastoxiv.page/@arXiv_mathPR_bot/114346453424694503
- Optimizing the ground state energy of the three-dimensional magnetic Dirichlet Laplacian with con...
Matthias Baur
https://arxiv.org/abs/2504.21597 https://mastoxiv.page/@arXiv_mathph_bot/114431404740241516
- A localized consensus-based sampling algorithm
Arne Bouillon, Alexander Bodard, Panagiotis Patrinos, Dirk Nuyens, Giovanni Samaey
https://arxiv.org/abs/2505.24861 https://mastoxiv.page/@arXiv_mathNA_bot/114612580684567066
- A Novel Sliced Fused Gromov-Wasserstein Distance
Moritz Piening, Robert Beinert
https://arxiv.org/abs/2508.02364 https://mastoxiv.page/@arXiv_csLG_bot/114976243138728278
- Minimal Regret Walras Equilibria for Combinatorial Markets via Duality, Integrality, and Sensitiv...
Alo\"is Duguet, Tobias Harks, Martin Schmidt, Julian Schwarz
https://arxiv.org/abs/2511.09021 https://mastoxiv.page/@arXiv_csGT_bot/115541243299714775
toXiv_bot_toot

A Fast solver for high condition linear systems using randomized stable solutions of its blocks
Suvendu Kar, Murugesan Venkatapathi
https://arxiv.org/abs/2510.02156 https://

A Fast solver for high condition linear systems using randomized stable solutions of its blocks
We present an enhanced version of the row-based randomized block-Kaczmarz method to solve a linear system of equations. This improvement makes use of a regularization during block updates in the solution, and a dynamic proposal distribution based on the current residue and effective orthogonality between blocks. This improved method provides significant gains in solving high-condition number linear systems that are either sparse, or dense least-squares problems that are significantly over/under…

Crosslisted article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[3/3]:
- Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
Valentyn Melnychuk, Dennis Frauen, Jonas Schweisthal, Stefan Feuerriegel

Physics-informed learning under mixing: How physical knowledge speeds up learning
Anna Scampicchio, Leonardo F. Toso, Rahel Rickenbach, James Anderson, Melanie N. Zeilinger
https://arxiv.org/abs/2509.24801

Physics-informed learning under mixing: How physical knowledge speeds up learning
A major challenge in physics-informed machine learning is to understand how the incorporation of prior domain knowledge affects learning rates when data are dependent. Focusing on empirical risk minimization with physics-informed regularization, we derive complexity-dependent bounds on the excess risk in probability and in expectation. We prove that, when the physical prior information is aligned, the learning rate improves from the (slow) Sobolev minimax rate to the (fast) optimal i.i.d. one w…

Statistical Inference for Gradient Boosting Regression
Haimo Fang, Kevin Tan, Giles Hooker
https://arxiv.org/abs/2509.23127 https://arxiv.org/pdf/2509.2312…

Statistical Inference for Gradient Boosting Regression
Gradient boosting is widely popular due to its flexibility and predictive accuracy. However, statistical inference and uncertainty quantification for gradient boosting remain challenging and under-explored. We propose a unified framework for statistical inference in gradient boosting regression. Our framework integrates dropout or parallel training with a recently proposed regularization procedure that allows for a central limit theorem (CLT) for boosting. With these enhancements, we surprising…

Mixed-Derivative Total Variation
Vincent Guillemet, Michael Unser
https://arxiv.org/abs/2509.23995 https://arxiv.org/pdf/2509.23995

Mixed-Derivative Total Variation
The formulation of norms on continuous-domain Banach spaces with exact pixel-based discretization is advantageous for solving inverse problems (IPs). In this paper, we investigate a new regularization that is a convex combination of a TV term and the $\M(\R^2)$ norm of mixed derivatives. We show that the extreme points of the corresponding unit ball are indicator functions of polygons whose edges are aligned with either the $x_1$- or $x_2$-axis. We then apply this result to construct a new regu…

(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification
Luca Bergamin, Roberto Confalonieri, Fabio Aiolli
https://arxiv.org/abs/2509.22384

(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification
Deep neural networks are widely used in practical applications of AI, however, their inner structure and complexity made them generally not easily interpretable. Model transparency and interpretability are key requirements for multiple scenarios where high performance is not enough to adopt the proposed solution. In this work, a differentiable approximation of $L_0$ regularization is adapted into a logic-based neural network, the Multi-layer Logical Perceptron (MLLP), to study its efficacy in r…

Bundle Network: a Machine Learning-Based Bundle Method
Francesca Demelas, Joseph Le Roux, Antonio Frangioni, Mathieu Lacroix, Emiliano Traversi, Roberto Wolfler Calvo
https://arxiv.org/abs/2509.24736

Bundle Network: a Machine Learning-Based Bundle Method
This paper presents Bundle Network, a learning-based algorithm inspired by the Bundle Method for convex non-smooth minimization problems. Unlike classical approaches that rely on heuristic tuning of a regularization parameter, our method automatically learns to adjust it from data. Furthermore, we replace the iterative resolution of the optimization problem that provides the search direction-traditionally computed as a convex combination of gradients at visited points-with a recurrent neural mo…

An Efficient ADMM Method for Ratio-Type Nonconvex and Nonsmooth Minimization in Sparse Recovery
Lang Yu, Nanjing Huang
https://arxiv.org/abs/2509.21969 https://

An Efficient ADMM Method for Ratio-Type Nonconvex and Nonsmooth Minimization in Sparse Recovery
Sparse signal recovery based on nonconvex and nonsmooth optimization problems has significant applications and demonstrates superior performance in signal processing and machine learning. This work deals with a scale-invariant $\ell_{1/2}/\ell_{2}$ sparse minimization with nonconvex, nonseparable, ratio-type regularization to enhance the accuracy and stability of sparse recovery. Within the framework of the null space property, we analyze the conditions for exact and stable recovery in constrai…