English
Related papers

Related papers: Efficient Agnostic Learning with Average Smoothnes…

200 papers

The aim of this paper is to study distributional properties of integers without large or small prime factors. Define an integer to be $[y',y]$-smooth if all of its prime factors belong to the interval $[y',y]$. We identify suitable weights…

Number Theory · Mathematics 2025-09-10 Lilian Matthiesen , Mengdi Wang

This paper provides a solution to the evaluation of treatment effects in selective samples when neither instruments nor parametric assumptions are available. We provide sharp bounds for average treatment effects under a conditional…

Econometrics · Economics 2024-12-17 Phillip Heiler , Asbjørn Kaufmann , Bezirgen Veliyev

We investigate the computational efficiency of agnostic learning for several fundamental geometric concept classes in the plane. While the sample complexity of agnostic learning is well understood, its time complexity has received much less…

Data Structures and Algorithms · Computer Science 2025-10-22 Talya Eden , Ludmila Glinskih , Sofya Raskhodnikova

The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured…

Machine Learning · Computer Science 2022-01-13 Aounon Kumar , Tom Goldstein

In this paper, we consider a generic probabilistic discriminative learner from the functional viewpoint and argue that, to make it learn well, it is necessary to constrain its hypothesis space to a set of non-trivial piecewise constant…

Machine Learning · Statistics 2018-06-05 Yi-Qing Wang

In Learning Theory, the smoothness assumption on the target function (known as source condition) is a key factor in establishing theoretical convergence rates for an estimator. The existing general form of the source condition, as discussed…

Statistics Theory · Mathematics 2025-03-27 Naveen Gupta , S. Sivananthan

We provide a complete theory of optimal universal rates for binary classification in the agnostic setting. This extends the realizable-case theory of Bousquet, Hanneke, Moran, van Handel, and Yehudayoff (2021) by removing the realizability…

Machine Learning · Computer Science 2026-01-30 Steve Hanneke , Shay Moran

Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which the data is collected can differ from that of the environment…

Machine Learning · Computer Science 2024-09-05 Shengbo Wang , Nian Si , Jose Blanchet , Zhengyuan Zhou

Diffusion models achieve remarkable generation quality, yet face a fundamental challenge known as memorization, where generated samples can replicate training samples exactly. We develop a theoretical framework to explain this phenomenon by…

Machine Learning · Computer Science 2026-03-31 Xinyu Zhou , Jiawei Zhang , Stephen J. Wright

We present the first adaptive strategy for active learning in the setting of classification with smooth decision boundary. The problem of adaptivity (to unknown distributional parameters) has remained opened since the seminal work of Castro…

Machine Learning · Statistics 2017-11-28 Andrea Locatelli , Alexandra Carpentier , Samory Kpotufe

In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate…

Machine Learning · Computer Science 2021-07-21 Arnout Devos , Yatin Dandi

Transfer learning for nonparametric regression is considered. We first study the non-asymptotic minimax risk for this problem and develop a novel estimator called the confidence thresholding estimator, which is shown to achieve the minimax…

Machine Learning · Statistics 2024-01-24 T. Tony Cai , Hongming Pu

Multiple generalized additive models (GAMs) are a type of distributional regression wherein parameters of probability distributions depend on predictors through smooth functions, with selection of the degree of smoothness via $L_2$…

Machine Learning · Statistics 2018-09-26 Yousra El-Bachir , Anthony C. Davison

Providing non-conservative uncertainty quantification for function estimates derived from noisy observations remains a fundamental challenge in statistical machine learning, particularly for applications in safety-critical domains. In this…

Machine Learning · Computer Science 2026-05-12 Johannes Teutsch , Oleksii Molodchyk , Marion Leibold , Timm Faulwasser , Armin Lederer

Uncertainty sampling in active learning is heavily used in practice to reduce the annotation cost. However, there has been no wide consensus on the function to be used for uncertainty estimation in binary classification tasks and…

Machine Learning · Computer Science 2021-11-01 Anant Raj , Francis Bach

We study the problem of computationally efficient proper agnostic learning of multidimensional concept classes under the Gaussian distribution. In this setting, given i.i.d. labeled samples from an unknown distribution over $\mathbb{R}^d…

Data Structures and Algorithms · Computer Science 2026-05-28 Sergei Tikhonov , Arsen Vasilyan

Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent studies relax the smoothness assumption by allowing the…

Optimization and Control · Mathematics 2026-02-11 Dingzhi Yu , Wei Jiang , Hongyi Tao , Yuanyu Wan , Lijun Zhang

We study uniform consistency in nonparametric mixture models as well as closely related mixture of regression (also known as mixed regression) models, where the regression functions are allowed to be nonparametric and the error…

Statistics Theory · Mathematics 2022-12-29 Bryon Aragam , Ruiyi Yang

This article demonstrates how recent developments in the theory of empirical processes allow us to construct a new family of asymptotically distribution-free smooth tests. Their distribution-free property is preserved even when the…

Statistics Theory · Mathematics 2026-02-24 Xiangyu Zhang , Sara Algeri

Traditional learning approaches for classification implicitly assume that each mistake has the same cost. In many real-world problems though, the utility of a decision depends on the underlying context $x$ and decision $y$. However,…

Machine Learning · Computer Science 2021-04-20 Kush Bhatia , Peter L. Bartlett , Anca D. Dragan , Jacob Steinhardt