English
Related papers

Related papers: Understanding the Generalization Ability of Deep L…

200 papers

Stochastic gradient descent (SGD) now acts as a fundamental part of optimization in current machine learning. Meanwhile, deep learning architectures have shown outstanding performance in a wide range of fields, such as natural language…

Machine Learning · Computer Science 2026-01-27 Zhao Song , Song Yue

Empirical data can often be considered as samples from a set of probability distributions. Kernel methods have emerged as a natural approach for learning to classify these distributions. Although numerous kernels between distributions have…

Machine Learning · Computer Science 2024-12-02 Oleksii Kachaiev , Stefano Recanatesi

We introduce an alternative closed form lower bound on the Gaussian process ($\mathcal{GP}$) likelihood based on the R\'enyi $\alpha$-divergence. This new lower bound can be viewed as a convex combination of the Nystr\"om approximation and…

Machine Learning · Statistics 2023-07-04 Xubo Yue , Raed Kontar

R\'enyi's information provides a theoretical foundation for tractable and data-efficient non-parametric density estimation, based on pair-wise evaluations in a reproducing kernel Hilbert space (RKHS). This paper extends this framework to…

Machine Learning · Computer Science 2022-03-09 Bo Hu , Shujian Yu , Jose C. Principe

The use of low-bit quantization has emerged as an indispensable technique for enabling the efficient training of large-scale models. Despite its widespread empirical success, a rigorous theoretical understanding of its impact on learning…

Machine Learning · Statistics 2026-02-17 Dechen Zhang , Junwei Su , Difan Zou

Counting problems such as determining how many bit strings satisfy a given Boolean logic formula are notoriously hard. In many cases, even getting an approximate count is difficult. Here we propose that entanglement, a common concept in…

Statistical Mechanics · Physics 2013-04-03 Claudio Chamon , Eduardo R. Mucciolo

We establish in-expectation and tail bounds on the generalization error of representation learning type algorithms. The bounds are in terms of the relative entropy between the distribution of the representations extracted from the training…

Machine Learning · Statistics 2025-03-21 Milad Sefidgaran , Abdellatif Zaidi , Piotr Krasnowski

Understanding the informative behaviour of deep neural networks is challenged by misused estimators and the complexity of network structure, which leads to inconsistent observations and diversified interpretation. Here we propose the LogDet…

Machine Learning · Computer Science 2021-05-11 Zhanghao Zhouyin , Ding Liu

Modern regression problems often involve high-dimensional data and a careful tuning of the regularization hyperparameters is crucial to avoid overly complex models that may overfit the training data while guaranteeing desirable properties…

Machine Learning · Computer Science 2026-04-08 Maria-Florina Balcan , Saumya Goyal , Dravyansh Sharma

Why does training deep neural networks using stochastic gradient descent (SGD) result in a generalization error that does not worsen with the number of parameters in the network? To answer this question, we advocate a notion of effective…

Machine Learning · Computer Science 2019-01-15 Vaishnavh Nagarajan , J. Zico Kolter

We present a theoretically well-founded deep learning algorithm for nonparametric regression. It uses over-parametrized deep neural networks with logistic activation function, which are fitted to the given data via gradient descent. We…

Statistics Theory · Mathematics 2025-04-14 Michael Kohler , Adam Krzyzak

As shown in recent research, deep neural networks can perfectly fit randomly labeled data, but with very poor accuracy on held out data. This phenomenon indicates that loss functions such as cross-entropy are not a reliable indicator of…

Machine Learning · Statistics 2019-06-13 Yiding Jiang , Dilip Krishnan , Hossein Mobahi , Samy Bengio

Symmetries (transformations by group actions) are present in many datasets, and leveraging them holds considerable promise for improving predictions in machine learning. In this work, we aim to understand when and how deep networks -- with…

Machine Learning · Computer Science 2025-06-27 Andrea Perin , Stephane Deny

We study to what extent may stochastic gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex…

Machine Learning · Computer Science 2023-01-13 Tomer Koren , Roi Livni , Yishay Mansour , Uri Sherman

Generalization error bounds from learning theory provide statistical guarantees on how well an algorithm will perform on previously unseen data. In this paper, we characterize the impacts of data non-IIDness due to censored feedback (a.k.a.…

Machine Learning · Computer Science 2025-04-14 Yifan Yang , Ali Payani , Parinaz Naghizadeh

The goal of this thesis is to improve our understanding of the internal mechanisms by which deep artificial neural networks create meaningful representations and are able to generalize. We focus on the challenge of characterizing the…

Machine Learning · Computer Science 2025-10-29 Diego Doimo

In this paper, we propose a new covering technique localized for the trajectories of SGD. This localization provides an algorithm-specific complexity measured by the covering number, which can have dimension-independent cardinality in…

Machine Learning · Statistics 2022-09-20 Sejun Park , Umut Şimşekli , Murat A. Erdogdu

Stochastic gradient descent (SGD) is a foundational algorithm for large-scale statistical learning and stochastic optimization. However, statistical inference based on SGD iterates remains challenging when stochastic gradients have infinite…

Machine Learning · Statistics 2026-05-26 Jose Blanchet , Peter Glynn , Wenhao Yang

In this note, we consider appropriately regularized $\ell_2-$empirical risk of depth $2$ nets with any number of gates and show bounds on how the empirical loss evolves for SGD iterates on it -- for arbitrary data and if the activation is…

Machine Learning · Computer Science 2024-12-24 Pulkit Gopalani , Anirbit Mukherjee

Doubly stochastic learning algorithms are scalable kernel methods that perform very well in practice. However, their generalization properties are not well understood and their analysis is challenging since the corresponding learning…

Machine Learning · Statistics 2018-03-12 Junhong Lin , Lorenzo Rosasco