English
Related papers

Related papers: Bennett-type Generalization Bounds: Large-deviatio…

200 papers

We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods.…

Machine Learning · Computer Science 2019-05-17 Mikhail Khodak , Maria-Florina Balcan , Ameet Talwalkar

Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very…

Machine Learning · Computer Science 2019-11-28 Yuan Cao , Quanquan Gu

Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time adaptation has yielded encouraging results in this setting, we…

Machine Learning · Computer Science 2022-12-26 Thomas Duboudin , Emmanuel Dellandréa , Corentin Abgrall , Gilles Hénaff , Liming Chen

Meta-learning automatically infers an inductive bias by observing data from a number of related tasks. The inductive bias is encoded by hyperparameters that determine aspects of the model class or training algorithm, such as initialization…

Machine Learning · Computer Science 2020-11-10 Sharu Theresa Jose , Osvaldo Simeone , Giuseppe Durisi

This work invokes the notion of $f$-divergence to introduce a novel upper bound on the Bayes error rate of a general classification task. We show that the proposed bound can be computed by sampling from the output of a parameterized model.…

Machine Learning · Computer Science 2025-01-15 Mohammadreza Tavasoli Naeini , Ali Bereyhi , Morteza Noshad , Ben Liang , Alfred O. Hero

Prompt learning is a popular fine-tuning method for vision-language models due to its efficiency. It requires a small number of additional learnable parameters while significantly enhancing performance on target tasks. However, most…

Artificial Intelligence · Computer Science 2025-04-22 Mingyu Kim , Jongwoo Ko , Mijung Park

A bound uniform over various loss-classes is given for data generated by stationary and phi-mixing processes, where the mixing time (the time needed to obtain approximate independence) enters the sample complexity only in an additive way.…

Machine Learning · Computer Science 2023-06-02 Andreas Maurer

We study the generalization properties of ridge regression with random features in the statistical learning framework. We show for the first time that $O(1/\sqrt{n})$ learning bounds can be achieved with only $O(\sqrt{n}\log n)$ random…

Machine Learning · Statistics 2021-04-16 Alessandro Rudi , Lorenzo Rosasco

Recent advances in optimization theory have shown that smooth strongly convex finite sums can be minimized faster than by treating them as a black box "batch" problem. In this work we introduce a new method in this class with a theoretical…

Machine Learning · Computer Science 2014-07-11 Aaron J. Defazio , Tibério S. Caetano , Justin Domke

Stagewise training strategy is widely used for learning neural networks, which runs a stochastic algorithm (e.g., SGD) starting with a relatively large step size (aka learning rate) and geometrically decreasing the step size after a number…

Machine Learning · Statistics 2019-02-05 Zhuoning Yuan , Yan Yan , Rong Jin , Tianbao Yang

Hypergraph neural networks have been promising tools for handling learning tasks involving higher-order data, with notable applications in web graphs, such as modeling multi-way hyperlink structures and complex user interactions. Yet, their…

Machine Learning · Computer Science 2025-01-28 Yifan Wang , Gonzalo R. Arce , Guangmo Tong

We establish a Bernstein-type inequality for a class of stochastic processes that include the classical geometrically $\phi$-mixing processes, Rio's generalization of these processes, as well as many time-discrete dynamical systems. Modulo…

Probability · Mathematics 2015-01-14 H. Hang , I. Steinwart

Motivated by the learned iterative soft thresholding algorithm (LISTA), we introduce a general class of neural networks suitable for sparse reconstruction from few linear measurements. By allowing a wide range of degrees of weight-sharing…

Machine Learning · Computer Science 2022-01-19 Ekkehard Schnoor , Arash Behboodi , Holger Rauhut

Stochastic gradient descent (SGD) with mini-batching is a standard tool in large-scale optimization, yet its theoretical properties under heavy-tailed gradient noise remain largely unexplored. In this paper we study SGD with increasing…

Probability · Mathematics 2026-05-11 Bartosz Glowacki , Rafal Kulik , Philippe Soulier

Large-margin classifiers are popular methods for classification. We derive the asymptotic expression for the generalization error of a family of large-margin classifiers in the limit of both sample size $n$ and dimension $p$ going to…

Machine Learning · Statistics 2020-12-02 Hanwen Huang , Qinglong Yang

Recently, contrastive learning has found impressive success in advancing the state of the art in solving various machine learning tasks. However, the existing generalization analysis is very limited or even not meaningful. In particular,…

Machine Learning · Computer Science 2023-03-01 Yunwen Lei , Tianbao Yang , Yiming Ying , Ding-Xuan Zhou

In risk-sensitive learning, one aims to find a hypothesis that minimizes a risk-averse (or risk-seeking) measure of loss, instead of the standard expected loss. In this paper, we propose to study the generalization properties of…

Machine Learning · Statistics 2021-01-05 Jaeho Lee , Sejun Park , Jinwoo Shin

Most generalization bounds in learning theory are based on some measure of the complexity of the hypothesis class used, independently of any algorithm. In contrast, the notion of algorithmic stability can be used to derive tight…

Machine Learning · Computer Science 2008-11-12 Mehryar Mohri , Afshin Rostamizadeh

We develop minimax optimal risk bounds for the general learning task consisting in predicting as well as the best function in a reference set $\mathcal{G}$ up to the smallest possible additive term, called the convergence rate. When the…

Statistics Theory · Mathematics 2009-09-09 Jean-Yves Audibert

Algorithm-dependent generalization error bounds are central to statistical learning theory. A learning algorithm may use a large hypothesis space, but the limited number of iterations controls its model capacity and generalization error.…

Machine Learning · Computer Science 2017-07-20 Wenlong Mou , Liwei Wang , Xiyu Zhai , Kai Zheng