English
Related papers

Related papers: Benign Overfitting in Linear Classifiers and Leaky…

200 papers

Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but labels are also prone to be noisy due to human input. In this…

Machine Learning · Computer Science 2025-05-09 Weipeng Huang , Qin Li , Yang Xiao , Cheng Qiao , Tie Cai , Junwei Liang , Neil J. Hurley , Guangyuan Piao

Statistically consistent methods based on the noise transition matrix ($T$) offer a theoretically grounded solution to Learning with Noisy Labels (LNL), with guarantees of convergence to the optimal clean-data classifier. In practice,…

Machine Learning · Computer Science 2026-03-16 Chen Feng , Zhuo Zhi , Zhao Huang , Jiawei Ge , Ling Xiao , Nicu Sebe , Georgios Tzimiropoulos , Ioannis Patras

We study the problem of PAC learning one-hidden-layer ReLU networks with $k$ hidden units on $\mathbb{R}^d$ under Gaussian marginals in the presence of additive label noise. For the case of positive coefficients, we give the first…

Machine Learning · Computer Science 2020-06-23 Ilias Diakonikolas , Daniel M. Kane , Vasilis Kontonis , Nikos Zarifis

Pre-trained models are widely used in fine-tuning downstream tasks with linear classifiers optimized by the cross-entropy loss, which might face robustness and stability problems. These problems can be improved by learning representations…

Computation and Language · Computer Science 2021-10-07 Linyang Li , Demin Song , Ruotian Ma , Xipeng Qiu , Xuanjing Huang

Recent efforts to accelerate LLM pretraining have focused on computationally-efficient approximations that exploit second-order structure. This raises a key question for large-scale training: how much performance is forfeited by these…

Machine Learning · Computer Science 2026-04-21 Natalie Abreu , Nikhil Vyas , Sham Kakade , Depen Morwani

We establish the asymptotic implicit bias of gradient descent (GD) for generic non-homogeneous deep networks under exponential loss. Specifically, we characterize three key properties of GD iterates starting from a sufficiently small…

Machine Learning · Computer Science 2025-07-17 Yuhang Cai , Kangjie Zhou , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

We examine gradient descent on unregularized logistic regression problems, with homogeneous linear predictors on linearly separable datasets. We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. The…

Machine Learning · Statistics 2024-10-29 Daniel Soudry , Elad Hoffer , Mor Shpigel Nacson , Suriya Gunasekar , Nathan Srebro

Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…

Machine Learning · Computer Science 2018-06-29 Alessandro Achille , Stefano Soatto

In this work, we investigate the behavior of ridge regression in an overparameterized binary classification task. We assume examples are drawn from (anisotropic) class-conditional cluster distributions with opposing means and we allow for…

Machine Learning · Statistics 2025-03-12 Alexander Tsigler , Luiz F. O. Chamon , Spencer Frei , Peter L. Bartlett

We study the implicit bias of gradient flow (i.e., gradient descent with infinitesimal step size) on linear neural network training. We propose a tensor formulation of neural networks that includes fully-connected, diagonal, and…

Machine Learning · Computer Science 2021-09-13 Chulhee Yun , Shankar Krishnan , Hossein Mobahi

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Generative models that maximize model likelihood have gained traction in many practical settings. Among them, perturbation based approaches underpin many strong likelihood estimation models, yet they often face slow convergence and limited…

Information Theory · Computer Science 2025-10-27 Yirong Shen , Lu Gan , Cong Ling

Deep neural networks generalize well despite being exceedingly overparameterized and being trained without explicit regularization. This curious phenomenon has inspired extensive research activity in establishing its statistical principles:…

Machine Learning · Statistics 2021-09-16 Ke Wang , Christos Thrampoulidis

Class imbalance poses a challenge for developing unbiased, accurate predictive models. In particular, in image segmentation neural networks may overfit to the foreground samples from small structures, which are often heavily…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Zeju Li , Konstantinos Kamnitsas , Ben Glocker

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world…

Machine Learning · Computer Science 2025-01-22 Linchao Pan , Can Gao , Jie Zhou , Jinbao Wang

We establish the fundamental limits in the approximation of Lipschitz functions by deep ReLU neural networks with finite-precision weights. Specifically, three regimes, namely under-, over-, and proper quantization, in terms of minimax…

Machine Learning · Statistics 2024-05-06 Weigutian Ou , Philipp Schenkel , Helmut Bölcskei

Classifiers used in the wild, in particular for safety-critical systems, should not only have good generalization properties but also should know when they don't know, in particular make low confidence predictions far away from the training…

Machine Learning · Computer Science 2019-05-08 Matthias Hein , Maksym Andriushchenko , Julian Bitterwolf

A recent line of research on deep learning focuses on the extremely over-parameterized setting, and shows that when the network width is larger than a high degree polynomial of the training sample size $n$ and the inverse of the target…

Machine Learning · Computer Science 2022-01-03 Zixiang Chen , Yuan Cao , Difan Zou , Quanquan Gu

Learning with noisy labels has become imperative in the Big Data era, which saves expensive human labors on accurate annotations. Previous noise-transition-based methods have achieved theoretically-grounded performance under the…

Machine Learning · Computer Science 2023-02-21 Jiangchao Yao , Bo Han , Zhihan Zhou , Ya Zhang , Ivor W. Tsang

The successful training of neural networks hinges on the use of first order optimization methods, yet the theoretical characterization of these methods remains incomplete. This is especially true in settings with mild overparameterization.…

Machine Learning · Computer Science 2026-05-27 James Town , Etienne Boursier , Ben Lewis , Matthias Englert , Ranko Lazic