Non-Gaussianity

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 20

All topics

Benign Overfitting for General Norms and Distributions
Sep 27, 2026Daniel Barzilai, Ohad ShamirOverfitting Spectral Norm
Weizmann Institute of Science · University of Toronto & Vector Institute
Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime
Sep 22, 2026Tomas Gonzalez, Gonzalo MenaOptimal Transport Approach Non-Gaussianity
Department of Machine Learning, Carnegie Mellon University · Department of Statistics & Data Science, Carnegie Mellon University
Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to Gaussianity
Sep 14, 2026Yixing ZhangNon-Gaussianity Probability Measures
Thermodynamic Cyclic Processes with Markov Samplers in Bayesian Inference
Sep 7, 2026Heinrich von Campe, Bjoern Malte SchaeferBayesian Inference Markov Chain Monte Carlo
Interdisziplinäres Zentrum für wissenschaftliches Rechnen, Universität Heidelberg · Tübingen AI Center, University of Tübingen · ELLIS Institute Tübingen +2
Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails
Sep 3, 2026Shi Fu, Huibo Xu, Qixin Zhang +1Non-Gaussianity Long-Tailed Distribution
Generative AI Lab, College of Computing and Data Science, Nanyang Technological University, Singapore
Generative Diffusion Surrogates with Analytical Variance Schedule
Sep 1, 2026Patrick Reichherzer, Gianluca Gregori, David N. Hosking +1Diffusion Dynamics Diffusion Models
Department of Physics, University of Oxford, Oxford OX1 3PU, UK. · Department of Astrophysical Sciences, Princeton University, Princeton NJ 08544, USA. · Max Planck Institute for Security and Privacy, Bochum 44799, Germany. +2
Linear Independent Component Analysis via Optimal Transport
Jul 15, 2026Ashutosh Jha, Michel Besserve, Simon BuchholzIndependent Component Analysis Wasserstein Distance
Methods Center, University of Tübingen · Max Planck Institute for Intelligent Systems, Tübingen · Institute of Artificial Intelligence, TU Braunschweig
Learning Probabilistic Filters with Strictly Proper Scoring Rules
Jun 25, 2026Eviatar Bach, Ricardo Baptista, Jochen Bröcker +2Bayesian Filtering Data Assimilation
Department of Meteorology, University of Reading Brian Hoskins Building, Reading, RG6 6ET, UK · Department of Mathematics and Statistics, University of Reading Pepper Lane, Reading, RG6 6AX, UK · National Centre for Earth Observation Brian Hoskins Building, University of Reading, Reading, RG6 6ET, UK +5
Statistical Inference for Misspecified Contextual Bandits
Jun 21, 2026Yongyi Guo, Ziping XuContextual Bandit Framework Statistical Inference
Department of Statistics, University of Wisconsin–Madison · School of Data Science and Society, University of North Carolina at Chapel Hill
$Ω$ : Operator-based Mixture Ensemble for Generative Assimilation
Jun 18, 2026Pouria Behnoudfar, Nan ChenData Assimilation Non-Gaussianity
University of Wisconsin-Madison, Department of Mathematics, Madison, WI, USA
How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs
Jun 6, 2026Mark Kozdoba, Shie MannorGaussian Process Non-Gaussianity
Technion, IIT · NVIDIA
On the Subgaussianity of Quantized Linear Maps: An AI-Assisted Note
May 26, 2026Guangyi Zou, Roman VershyninNon-Gaussianity Gaussian Primitives
Department of Mathematics, University of California, Irvine
On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise
May 10, 2026Johannes Teutsch, Oleksii Molodchyk, Marion Leibold +2Non-Gaussianity Uncertainty Quantification
Chair of Automatic Control Engineering, Department of Computer Engineering, Technical University of Munich, 80333 Munich, Germany · Institute of Control Systems, Hamburg University of Technology, 21073 Hamburg, Germany · Department of Electrical and Computer Engineering, National University of Singapore, 117583 Singapore
Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
May 6, 2026Shawn RayMulti-Agent Reinforcement Learning Inhomogeneous Random Graphs
Carnegie Mellon University
Mixed Membership sub-Gaussian Models
Apr 24, 2026Huan QingGaussian Mixture Models Non-Gaussianity
School of Economics and Finance, Chongqing University of Technology, Chongqing, 400054, China
High-Dimensional Change Point Detection via Graph Spanning Ratio
Dec 8, 2025Katerina Papagiannouli, Yang-wen Sun, Vladimir SpokoinyChange-Point Detection Change Detection
Department of Mathematics, University or Pisa · Department of Mathematics, Humboldt University of Berlin · Weierstrass Institut
Robust Sparse Bayesian Learning Based on Minimum Error Entropy for Noisy High-Dimensional Brain Activity Decoding
Aug 5, 2025Yuanhao Li, Badong Chen, Wenjun Bai +2Bayesian Networks Non-Gaussianity
Center for Advanced Intelligence Project, RIKEN, Tokyo 103-0027, Japan · Department of Computational Brain Imaging, ATR Neural Information Analysis Laboratories, Kyoto 619-0237, Japan · Institute of Artificial Intelligence and Robotics (IAIR), Xi’an Jiaotong University, Xi’an 710049, China +1
Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms
Feb 27, 2025Ambroise Heurtebise, Omar Chehab, Pierre Ablin +2Causal Discovery Methods Linear Structural Equation Models
Inria, CEA, University of Paris-Saclay, France · University of Carnegie Mellon, Pittsburgh PA, USA · Apple +1
Probabilistic Analysis of Least Squares, Orthogonal Projection, and QR Factorization Algorithms Subject to Gaussian Noise
Sep 27, 2024Ali Lotfi, Julien Langou, Mohammad MeysamiSpectral Norm Singular Value Decomposition
Department of Computer Science, University of Saskatchewan, Saskatoon, SK S7N 5A2, Canada · Department of Applied Mathematics, University of Colorado Denver, Denver, Colorado2026 80201, USA · Department of Mathematics, The University of Tulsa, Tulsa, OK 74104, USA
Semidefinite programming relaxations and debiasing for MAXCUT-based clustering
Jan 16, 2024Shuheng ZhouConvex Relaxation Maximum Independent Set
University of California, Riverside, CA 92521

Sep 27, 2026, cs.LGJ/K move · Enter open · S save

Benign Overfitting for General Norms and Distributions

Daniel Barzilai, Ohad Shamir

Weizmann Institute of Science · University of Toronto & Vector Institute

Overfitting Spectral Norm Exponential Family Non-Gaussianity Norm Gradient Descent+2

Open paper AskPDF arXiv

Understanding why predictors can generalize despite interpolating noisy training data is a central puzzle in machine learning. Most work on such "benign overfitting" studies minimum-2-norm linear regression, reflecting the inductive bias of gradient descent. However, modern optimizers such as Adam and Muon use non-Euclidean update geometries, favoring solutions associated with other norms. Analyzing regression for non-Euclidean norms is substantially more difficult, with known results essentially limited to Gaussians. In this paper, we develop a method to analyze benign overfitting in linear regression for general norms and general (sub-Gaussian) distributions. As a special case, we prove that minimum-p-norm interpolation with p>1 can benignly overfit even for non-Gaussian distributions, under suitable conditions. Perhaps surprisingly, for the 1-norm, benign overfitting does not hold in general for well-behaved (but non-Gaussian) distributions, showing that existing positive 1-norm results rely crucially on Gaussianity. Our proof analyzes the geometry of the dual optimization problem, using concentration and central limit tools to show it is approximately Euclidean in many high-dimensional cases.

Momentum

Related topics

Latest papers 20