中文
相关论文

相关论文: Optimal SQ Lower Bounds for Robustly Learning Disc…

200 篇论文

Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance. We present a general approach to this problem focusing on unsupervised…

机器学习 · 计算机科学 2021-02-22 Andreas Maurer , Daniela A. Parletta , Andrea Paudice , Massimiliano Pontil

We study the problem of list-decodable Gaussian mean estimation and the related problem of learning mixtures of separated spherical Gaussians. We develop a set of techniques that yield new efficient algorithms with significantly improved…

数据结构与算法 · 计算机科学 2017-11-21 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

The aim of this paper is to provide several novel upper bounds on the excess risk with a primal focus on classification problems. We suggest two approaches and the obtained bounds are represented via the distribution dependent local…

统计理论 · 数学 2018-03-13 Nikita Zhivotovskiy

Recent developments in Reinforcement learning have significantly enhanced sequential decision-making in uncertain environments. Despite their strong performance guarantees, most existing work has focused primarily on improving the…

统计理论 · 数学 2025-08-13 Bo Pan , Jianya Lu , Yafei Wang , Hao Li , Bei Jiang , Linglong Kong

We introduce a framework for proving lower bounds on computational problems over distributions against algorithms that can be implemented using access to a statistical query oracle. For such algorithms, access to the input distribution is…

计算复杂性 · 计算机科学 2016-08-16 Vitaly Feldman , Elena Grigorescu , Lev Reyzin , Santosh Vempala , Ying Xiao

Given a finite set of unknown distributions or arms that can be sampled, we consider the problem of identifying the one with the maximum mean using a $\delta$-correct algorithm (an adaptive, sequential algorithm that restricts the…

机器学习 · 计算机科学 2023-11-27 Shubhada Agrawal , Sandeep Juneja , Peter Glynn

We consider distributed online learning protocols that control the exchange of information between local learners in a round-based learning scenario. The learning performance of such a protocol is intuitively optimal if approximately the…

分布式、并行与集群计算 · 计算机科学 2019-12-02 Michael Kamp , Mario Boley , Michael Mock , Daniel Keren , Assaf Schuster , Izchak Sharfman

Bayesian quadrature optimization (BQO) maximizes the expectation of an expensive black-box integrand taken over a known probability distribution. In this work, we study BQO under distributional uncertainty in which the underlying…

机器学习 · 计算机科学 2020-01-22 Thanh Tang Nguyen , Sunil Gupta , Huong Ha , Santu Rana , Svetha Venkatesh

This paper introduces and analyzes an improved Q-learning algorithm for discrete-time linear time-invariant systems. The proposed method does not require any knowledge of the system dynamics, and it enjoys significant efficiency advantages…

系统与控制 · 电气工程与系统科学 2023-04-03 Victor G. Lopez , Mohammad Alsalti , Matthias A. Müller

We prove risk bounds for binary classification in high-dimensional settings when the sample size is allowed to be smaller than the dimensionality of the training set observations. In particular, we prove upper bounds for both 'compressive…

统计理论 · 数学 2017-09-29 Ata Kaban , Robert J. Durrant

In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse…

最优化与控制 · 数学 2019-10-14 Salar Fattahi , Nikolai Matni , Somayeh Sojoudi

We study the fundamental problem of high-dimensional mean estimation in a robust model where a constant fraction of the samples are adversarially corrupted. Recent work gave the first polynomial time algorithms for this problem with…

机器学习 · 计算机科学 2018-11-26 Yu Cheng , Ilias Diakonikolas , Rong Ge

$Q$-learning is one of the most fundamental reinforcement learning algorithms. It is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence until the recent work…

机器学习 · 计算机科学 2025-05-28 Xinyu Liu , Zixuan Xie , Shangtong Zhang

The classic problems of testing uniformity of and learning a discrete distribution, given access to independent samples from it, are examined under general $\ell_p$ metrics. The intuitions and results often contrast with the classic…

数据结构与算法 · 计算机科学 2015-03-24 Bo Waggoner

We study the problem of list-decodable linear regression, where an adversary can corrupt a majority of the examples. Specifically, we are given a set $T$ of labeled examples $(x, y) \in \mathbb{R}^d \times \mathbb{R}$ and a parameter $0<…

数据结构与算法 · 计算机科学 2021-06-18 Ilias Diakonikolas , Daniel M. Kane , Ankit Pensia , Thanasis Pittas , Alistair Stewart

We propose a distributionally robust approach to learning hyperparameters for first-order methods in convex optimization. Given a dataset of problem instances, we minimize a Wasserstein distributionally robust version of the performance…

机器学习 · 计算机科学 2026-05-08 Vinit Ranjan , Jisun Park , Bartolomeo Stellato

We revisit the problem of robust linear regression under Gaussian covariates with an unknown covariance matrix of condition number $\kappa$. For this fundamental problem, significant gaps remain in our understanding of the trade-offs among…

数据结构与算法 · 计算机科学 2026-05-19 Deeksha Adil , Jarosław Błasiok , Hongjie Chen , Deepak Narayanan Sridharan

The recent work by Dong & Yang (2023) showed for misspecified sparse linear bandits, one can obtain an $O\left(\epsilon\right)$-optimal policy using a polynomial number of samples when the sparsity is a constant, where $\epsilon$ is the…

机器学习 · 计算机科学 2024-07-19 Ally Yalei Du , Lin F. Yang , Ruosong Wang

We study how to utilize (possibly erroneous) predictions in a model for computing under uncertainty in which an algorithm can query unknown data. Our aim is to minimize the number of queries needed to solve the minimum spanning tree…

数据结构与算法 · 计算机科学 2022-07-01 Thomas Erlebach , Murilo Santos de Lima , Nicole Megow , Jens Schlöter

Motivated by the study of $Q$-learning algorithms in reinforcement learning, we study a class of stochastic approximation procedures based on operators that satisfy monotonicity and quasi-contractivity conditions with respect to an…

机器学习 · 计算机科学 2019-06-25 Martin J. Wainwright