English
Related papers

Related papers: Fast learning rates with heavy-tailed losses

200 papers

In this paper, we study the learning rate of generalized Bayes estimators in a general setting where the hypothesis class can be uncountable and have an irregular shape, the loss function can have heavy tails, and the optimal hypothesis may…

Statistics Theory · Mathematics 2021-11-22 Lam Si Tung Ho , Binh T. Nguyen , Vu Dinh , Duy Nguyen

We study generalization properties of weakly supervised learning. That is, learning where only a few "strong" labels (the actual target of our prediction) are present but many more "weak" labels are available. In particular, we show that…

Machine Learning · Computer Science 2020-02-21 Joshua Robinson , Stefanie Jegelka , Suvrit Sra

Bernstein's condition is a key assumption that guarantees fast rates in machine learning. For example, the Gibbs algorithm with prior $\pi$ has an excess risk in $O(d_{\pi}/n)$, as opposed to the standard $O(\sqrt{d_{\pi}/n})$, where $n$…

Machine Learning · Statistics 2025-03-03 Charles Riou , Pierre Alquier , Badr-Eddine Chérief-Abdellatif

The speed with which a learning algorithm converges as it is presented with more data is a central problem in machine learning --- a fast rate of convergence means less data is needed for the same level of performance. The pursuit of fast…

Machine Learning · Computer Science 2021-08-31 Tim van Erven , Peter D. Grünwald , Nishant A. Mehta , Mark D. Reid , Robert C. Williamson

This paper investigates the phenomenon of benign overfitting in binary classification problems with heavy-tailed input distributions, extending the analysis of maximum margin classifiers to $\alpha$ sub-exponential distributions ($\alpha…

Machine Learning · Computer Science 2024-10-17 Kota Okudo , Kei Kobayashi

The natural world often follows a long-tailed data distribution where only a few classes account for most of the examples. This long-tail causes classifiers to overfit to the majority class. To mitigate this, prior solutions commonly adopt…

Machine Learning · Computer Science 2020-09-15 Rahul Duggal , Scott Freitas , Sunny Dhamnani , Duen Horng Chau , Jimeng Sun

We analyze neural scaling laws in a solvable model of last-layer fine-tuning where targets have intrinsic, instance-heterogeneous difficulty. In our Latent Instance Difficulty (LID) model, each input's target variance is governed by a…

Machine Learning · Computer Science 2026-01-08 Noam Levi

The masses of data now available have opened up the prospect of discovering weak signals using machine-learning algorithms, with a view to predictive or interpretation tasks. As this survey of recent results attempts to show, bringing…

Statistics Theory · Mathematics 2026-05-06 Stephan Clémençon , Anne Sabourin

A recent line of works, initiated by Russo and Xu, has shown that the generalization error of a learning algorithm can be upper bounded by information measures. In most of the relevant works, the convergence rate of the expected…

Information Theory · Computer Science 2022-05-16 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

The generalization error of a learning algorithm refers to the discrepancy between the loss of a learning algorithm on training data and that on unseen testing data. Various information-theoretic bounds on the generalization error have been…

Information Theory · Computer Science 2025-06-24 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples. While existing supervised learning approaches have been…

Computer Vision and Pattern Recognition · Computer Science 2023-09-18 Ci-Siang Lin , Min-Hung Chen , Yu-Chiang Frank Wang

In this paper, we consider the problem of linear regression with heavy-tailed distributions. Different from previous studies that use the squared loss to measure the performance, we choose the absolute loss, which is capable of estimating…

Machine Learning · Computer Science 2018-10-26 Lijun Zhang , Zhi-Hua Zhou

We study learning algorithms that seek to minimize the conditional value-at-risk (CVaR), when all the learner knows is that the losses incurred may be heavy-tailed. We begin by studying a general-purpose estimator of CVaR for potentially…

Machine Learning · Statistics 2020-06-04 Matthew J. Holland , El Mehdi Haress

We propose a simple data model inspired from natural data such as text or images, and use it to study the importance of learning features in order to achieve good generalization. Our data model follows a long-tailed distribution in the…

Machine Learning · Computer Science 2023-01-02 Thomas Laurent , James H. von Brecht , Xavier Bresson

We propose statistically robust and computationally efficient linear learning methods in the high-dimensional batch setting, where the number of features $d$ may exceed the sample size $n$. We employ, in a generic learning setting, two…

Machine Learning · Statistics 2023-05-30 Ibrahim Merad , Stéphane Gaïffas

This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution patterns. The head classes have a relatively large spatial…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Jialun Liu , Yifan Sun , Chuchu Han , Zhaopeng Dou , Wenhui Li

We present a framework to derive bounds on the test loss of randomized learning algorithms for the case of bounded loss functions. Drawing from Steinke & Zakynthinou (2020), this framework leads to bounds that depend on the conditional…

Machine Learning · Computer Science 2021-03-11 Fredrik Hellström , Giuseppe Durisi

The dominant approaches to text representation in natural language rely on learning embeddings on massive corpora which have convenient properties such as compositionality and distance preservation. In this paper, we develop a novel method…

Choosing a suitable loss function is essential when learning by empirical risk minimisation. In many practical cases, the datasets used for training a classifier may contain incorrect labels, which prompts the interest for using loss…

Machine Learning · Computer Science 2024-05-15 Henrique K. Miyamoto , Fábio C. C. Meneghetti , Sueli I. R. Costa

Time series regression models are commonly used in time series analysis. However, in modern real-world applications, serially correlated data with an ultra-high dimension and fat tails are prevalent. This presents a challenge in developing…

Statistics Theory · Mathematics 2023-04-21 Linbo Liu , Danna Zhang
‹ Prev 1 2 3 10 Next ›