Key papers

• Explicit Iteration Complexity of Exact Data-Driven Inverse Optimization for Integer Linear Programs (2026)
  Akira Kitaoka
  5.49
• Singular value soft-thresholding via the polar decomposition (2026)
  Stephen Becker
  5.49
• On the Role of Normalization in Binary Iterative Hard Thresholding for 1-bit Compressed Sensing (2026)
  Arya Mazumdar et al.
  5.01
• Prior laundering: learned priors with inherited, undetectable overconfidence (2026)
  Ali Siahkoohi et al.
  5.01
• Distributional Determinantal Point Process for Repulsive Clustering of Distributions (2026)
  Khai Nguyen et al.
  5.01
• On the Convergence of Stochastic Low-Rank Adaptation (2026)
  Ru Wang et al.
  5.01
• Convergence analysis of a family of Zermelo-type iterations for the Bradley--Terry model (2026)
  Ruijian Han et al.
  5.01
• The V-fold jackknife for semiparametric inference: variance estimation, confidence intervals, and simultaneous confidence bands (2026)
  Yi Li et al.
  5.01
• D2PO: Optimizing Diffusion Samplers via Dynamic Preference (2026)
  Jinkyu Kim et al.
  4.39
• The Anatomy of Implicit Bias: Information Allocation in Neural Network Training (2026)
  Zhang Gongyue et al.
  4.39
• Nonlinear Bandit (2026)
  Tianshuo Zheng et al.
  4.39
• Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance (2026)
  Shiheng Zhang
  4.39
• Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF (2026)
  Eric Zhu et al.
  4.39
• Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks (2026)
  Abdeladhim Tahimi
  4.39
• Reassessing Muon for Matrix Factorization (2026)
  Ali Parviz et al.
  4.39
• Weight Feedback Computes the Jacobian Transpose Locally in Modern Deep Networks (2026)
  Junlong Shen et al.
  4.39
• Price of Fairness in Bandits: A Tight Minimax Characterization (2026)
  Dhruv Sarkar et al.
  4.39
• Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration (2026)
  Dhruv Sarkar et al.
  4.39
• Parallel gradient boosting for flexible estimation of conditional distributions (2026)
  R\'emy Chapelle (CESP et al.
  4.39
• Approximation of solutions of parameter-dependent problems by residual neural networks (2026)
  Ana Carpio
  4.39
• Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation (2026)
  Hao Qin et al.
  4.39
• An Efficient Newton Algorithm for Nonnegative Matrix Factorization with the Kullback-Leibler Divergence (2026)
  Damien Lesens et al.
  4.39
• Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum (2026)
  Slava Andrejev
  4.39
• Minimax Theory of Likelihood-Based Deep Learning for Speckle Regression (2026)
  Soham Jana
  4.39
• Integro-differential equations in angular stabilization of drone motion by distributed feedback control (2026)
  Alexander Domoshnitsky et al.
  4.39
• Lipschitzian SLLNs for random functions (2026)
  Lai Tian et al.
  4.39
• GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries (2026)
  Miguel P. Bento et al.
  4.39
• Reliability-Aware Bayesian Optimization of 1310 nm PCSELs with FDTD Verification (2026)
  Jinglin Yu et al.
  4.39
• Data eccentricity, asymptotics of Gaussian RBF reproducing kernel Hilbert space, and kernel PCA (2026)
  Sergio A. Alvarez
  4.39
• Searching the Space of Feed-Forward Neural-Network Weight-Update Rules with Fixed Depth Symbolic Regression (2026)
  Charles Brum et al.
  4.39
• Variance-Reduced Q-Learning over Static and Time-Varying Networks (2026)
  Sreejeet Maity et al.
  4.39
• From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning (2026)
  Jiaxin Deng et al.
  4.39
• Multiplicity of Stable Attractors in Disordered Neural Models (2026)
  Raffaele Marino et al.
  4.39
• Optimization of time-consuming experimental conditions using pseudo-experimental data guided by adaptive polynomial regression (2026)
  Hirotaka Sugawara et al.
  4.39
• Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition (2026)
  Yi-Hang Zhu et al.
  4.39
• Hyperball May Not Be a Free Lunch (2026)
  Yihao Xiao et al.
  4.39
• Complexity Bounds and Approaches to Learning Projected Gradient Descent Solver Iterates (2026)
  Anjian Li et al.
  4.39
• Beyond Negative-Ridge Endpoints: Mixed-Sign Spectral Regularization via Negative-Shifted Gradient Descent (2026)
  Peng Zhao
  4.39
• \k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating (2026)
  Jianghui Wang et al.
  4.39
• Directional Influence Function: Estimating Training Data Influence in Constrained Learning (2026)
  Xin Wang (Jeff) et al.
  4.39
• A Structural Interpretation of GELU and Threshold-Transmission Activations via the First-Order Loss Function (2026)
  Roberto Rossi
  3.51
• Characterization of the Basin of Convexity for Multi-Snapshot Spike Deconvolution via Variable Projection (2026)
  Meghna Kalra et al.
  3.51
• Learned Pairwise Deep Dual-Optimal Inequalities for Stabilizing Column Generation (2026)
  Zhengzhong Ricky You et al.
  3.51
• Beyond the $d^{2.5}$-mixing bound for Dikin walks on polytopes (2026)
  Yunbum Kook
  3.51
• Identity-Paired Progressive Depth Training: When Trainability Persists Beyond Expressibility (2026)
  Athanasios Hadjidimoulas et al.
  3.51
• A Deep Reinforcement Learning Algorithm for the Vehicle Routing Problem with Stochastic Demands and Outsourcing (2026)
  Mohsen Dastpak et al.
  3.51
• Local Stability and Gaussian Smoothing of Quantized Neural Networks (2026)
  Sergey Salishev et al.
  3.51
• DriftXpress: Faster Drifting Models via Projected RKHS Fields (2026)
  Ali Falahati et al.
  3.39
• Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation (2025)
  Jean Barbier et al.
  2.60
• Online Pricing and Allocation with Demand Learning and Fulfillment Cost (2025)
  Jianyu Xu et al.
  2.06
• Wasserstein gradient flows for Coulomb discrepancies (2026)
  Antonin Chodron de Courcel et al.
  2.00
• When Kernel Ridge Regression Meets the H\"older-Zygmund Class: Minimax Optimality and Failure of Properness (2026)
  Yuxuan Hou
  2.00
• Randomizing the Number of Centers in k-means++ (2026)
  Vaclav Rozhon
  2.00
• Retrospective Orthogonal Design: Response-Surface Reconstruction from Observational Data (2026)
  Lawrence Fulton et al.
  2.00
• Between Gradient and Natural Gradient: A Continuum of LoRA Initializations (2026)
  Dianze Liu et al.
  2.00
• Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection (2026)
  Nicolas Gutowski et al.
  2.00
• Denoising growth complexity: Data geometry and certified schedules for diffusion sampling (2026)
  Martin J. Wainwright
  2.00
• Origins and mitigation of double descent in reduced order modeling (2026)
  Andrei A. Klishin et al.
  2.00
• Existence-Field Diffusion Model for Spatial Point Processes with Variable Cardinality (2026)
  Xiaoyin Pan et al.
  2.00
• Adaptive Gradient-Based Methods for a Broader Class of Optimization Problems under Performative Prediction (2026)
  Hiroki Hamaguchi et al.
  2.00