Awesome Machine Learning (Statistics)

Key papers

• The Spectral Dynamics and Noise Geometry of Muon (2026)
  Pierfrancesco Beneventano et al.
  9.07
• Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation (2026)
  Guo Yu et al.
  5.87
• Representation Costs in Data Science: Foundations and the Quasi-Banach Spaces of Deep Neural Networks (2026)
  Greg Ongie et al.
  5.49
• Accelerated Convex Optimization via Hamiltonian Dynamics with Deterministic Integration Time (2026)
  Xiuyuan Wang et al.
  5.49
• When Do Fewer Coordinates Suffice in DP-SGD? (2026)
  Huiqi Zhang et al.
  5.01
• Finding Most Influential Sets (2026)
  Lucas D. Konrad et al.
  5.01
• Annealed Entropic Allocation for Ranking and Selection (2026)
  Xin Fei et al.
  5.01
• Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency (2026)
  Seth Dobrin et al.
  5.01
• Valid Inference with Synthetic Data via Task Exchangeability (2026)
  Lezhi Tan et al.
  5.01
• Approximating Gaussian Whittle-Matern Fields over Well-Centered Triangulations of Riemannian Manifolds (2026)
  Srinivas Nambirajan
  5.01
• Another Look at Log-PCA for Probability Measures: A Dynamical Formulation and Statistical Convergence (2026)
  Peng Xu et al.
  5.01
• Tight $L_\infty$ Sample Complexity for Low-Degree and Sparse Boolean Polynomials (2026)
  Jasper van Doornmalen et al.
  5.01
• Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty (2026)
  Fangyuan Lin et al.
  5.01
• A Bayesian Boolean Matrix Factorization with Application to Copy Number Analysis in Cancer (2026)
  Adolphus Wagala et al.
  5.01
• Geometrical fairness in graph neural networks (2026)
  Arturo P\'erez-Peralta et al.
  5.01
• Differential Privacy of Gaussian Process Posterior Sampling (2026)
  Tomasz Maciazek
  5.01
• Fast Nonparametric Conditional Independence Testing via Two-Stage Regression (2026)
  Eric V. Strobl
  5.01
• Tensor-based second-order causal discovery (2026)
  Nathan Ouyang et al.
  5.01
• A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise (2026)
  M. Forzo et al.
  5.01
• Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds (2026)
  Hao Liang et al.
  5.01
• Anytime-Valid Federated Conformal RAG for LLM Swarms (2026)
  Prasanjit Dubey et al.
  4.95
• On Median of Incomplete U-Statistics (2026)
  Nong Minh Hieu
  4.39
• Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery (2026)
  Tyler H. McCormick
  4.39
• Exact Unlearning in Reinforcement Learning (2026)
  Thanh Nguyen-Tang et al.
  4.39
• The price of multi-group transductive learning (2026)
  Noah Bergam et al.
  4.39
• Global Sketch-Based Watermarking for Diffusion Language Models (2026)
  Daniel Zhao
  4.39
• Identifying Gems from Roman RAPIDly (2026)
  Karan Gandhi et al.
  4.39
• INFUSER: Influence-Guided Self-Evolution Improves Reasoning (2026)
  Siyu Chen et al.
  4.39
• TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts (2026)
  Jiangyang He et al.
  4.39
• A Longitudinal Attribute-Conditioned Neural Network for Modeling Health-State Transition Probabilities in Temporally Irregular Data: The LANTERN Framework (2026)
  Bright Kwaku Manu et al.
  4.39
• Learning High Coverage Discriminative Parsimonious Rulesets (2026)
  Mariamma Antony et al.
  4.39
• Implicit Variational Rejection Sampling (2026)
  Jian Xu et al.
  4.39
• EM-NeSy: Expectation Maximization for Neurosymbolic Learning (2026)
  Annegret Seibt et al.
  4.39
• One-Step Generalization Ratio Guided Optimization for Domain Generalization (2026)
  Sumin Cho et al.
  4.39
• Scalable and Interpretable Representation Alignment with Ordinal Similarity (2026)
  Diogo Soares et al.
  4.39
• A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions (2026)
  Jianghan Shen et al.
  4.39
• Deep Q-Learning on H\"older Spaces (2026)
  Qian Qi
  4.39
• Finsler Geometry, Graph Neural Networks, and You (2026)
  T. Mitchell Roddenberry et al.
  4.39
• Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization (2026)
  Xiaoyu Li
  4.39
• Uncertainty Quantification of Engineering Structures by Polynomial Chaos Expansion and Multivariate Active Learning (2026)
  Qitian Lu et al.
  4.39
• FoundCause: Causal Discovery with Latent Confounders from Observational Data (2026)
  Patrick Bl\"obaum et al.
  4.39
• The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible (2026)
  Lauri Lov\'en et al.
  4.33
• Partially Performative Prediction (2026)
  Jaewook Lee et al.
  3.51
• Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models (2026)
  Liyi Zhang et al.
  3.51
• Range Penalization: Theoretical Insights with Applications in Federated Learning (2026)
  Yiyuan She et al.
  3.51
• Fixed-Parameter Tractability of Private Synthetic Data Generation (2026)
  Badih Ghazi et al.
  3.51
• Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs (2026)
  Tianhao Wu et al.
  3.51
• Structured Noise Adaptation for Sequential Bayesian Filtering with Embedded Latent Transfer Operators (2026)
  Naichang Ke et al.
  3.51
• A Generalized Sinkhorn Algorithm for Mean-Field Schr\"odinger Bridge (2026)
  Asmaa Eldesoukey et al.
  3.39
• Optimism Stabilizes Thompson Sampling for Adaptive Inference (2026)
  Shunxing Yan et al.
  3.28
• Transition Transfer $Q$-Learning for Composite Markov Decision Processes (2025)
  Jinhang Chai et al.
  2.71
• RIDGECUT: Learning Graph Partitioning with Rings and Wedges (2025)
  Qize Jiang et al.
  2.34
• Generalization analysis with deep ReLU networks for metric and similarity learning (2026)
  Junyu Zhou et al.
  2.00
• Gradient-Discrepancy Acquisition for Pool-Based Active Learning (2026)
  Mohamadsadegh Khosravani et al.
  2.00
• On the Geometry of On-Policy Distillation (2026)
  Zhennan Shen et al.
  2.00
• Data augmented bootstrap: Unifying confidence interval construction by approximate invariance (2026)
  Kevin Han Huang
  2.00
• Towards More General Control of Diffusion Models Using Jeffrey Guidance (2026)
  Rapha\"el Razafindralambo et al.
  2.00
• Rethinking Entropy Interventions In RLVR: An Entropy Change Perspective (2026)
  Zhezheng Hao, Hong Wang, Haoyang Liu, et al.
  2.00
• Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data (2026)
  Collin Cranston et al.
  1.94
• Generative Profiling for Soft Real-Time Systems and its Applications to Resource Allocation (2026)
  Georgiy A. Bondar et al.
  1.89