English
Related papers

Related papers: Learning General Halfspaces with General Massart N…

200 papers

We study learning in a noisy bisection model: specifically, Bayesian algorithms to learn a target value V given access only to noisy realizations of whether V is less than or greater than a threshold theta. At step t = 0, 1, 2, ..., the…

Machine Learning · Computer Science 2012-02-20 Mithun Chakraborty , Sanmay Das , Malik Magdon-Ismail

Meta-learning synthesizes and leverages the knowledge from a given set of tasks to rapidly learn new tasks using very little data. Meta-learning of linear regression tasks, where the regressors lie in a low-dimensional subspace, is an…

Machine Learning · Computer Science 2021-05-19 Kiran Koshy Thekumparampil , Prateek Jain , Praneeth Netrapalli , Sewoong Oh

We introduce a new approach for designing computationally efficient learning algorithms that are tolerant to noise, and demonstrate its effectiveness by designing algorithms with improved noise tolerance guarantees for learning linear…

Machine Learning · Computer Science 2018-06-05 Pranjal Awasthi , Maria Florina Balcan , Philip M. Long

Recovering linear subspaces from data is a fundamental and important task in statistics and machine learning. Motivated by heterogeneity in Federated Learning settings, we study a basic formulation of this problem: the principal component…

Machine Learning · Computer Science 2022-10-26 John Duchi , Vitaly Feldman , Lunjia Hu , Kunal Talwar

We give a $2^{\tilde{O}(\sqrt{n}/\epsilon)}$-time algorithm for properly learning monotone Boolean functions under the uniform distribution over $\{0,1\}^n$. Our algorithm is robust to adversarial label noise and has a running time nearly…

Data Structures and Algorithms · Computer Science 2023-03-29 Jane Lange , Ronitt Rubinfeld , Arsen Vasilyan

Mixtures of Gaussian (or normal) distributions arise in a variety of application areas. Many heuristics have been proposed for the task of finding the component Gaussians given samples from the mixture, such as the EM algorithm, a…

Probability · Mathematics 2007-05-23 Sanjeev Arora , Ravi Kannan

We study the estimation capacity of the generalized Lasso, i.e., least squares minimization combined with a (convex) structural constraint. While Lasso-type estimators were originally designed for noisy linear regression problems, it has…

Statistics Theory · Mathematics 2019-09-12 Martin Genzel , Gitta Kutyniok

We study the problem of learning mixtures of $k$ Gaussians in $d$ dimensions. We make no separation assumptions on the underlying mixture components: we only require that the covariance matrices have bounded condition number and that the…

Data Structures and Algorithms · Computer Science 2024-11-20 Sitan Chen , Vasilis Kontonis , Kulin Shah

We consider the problem of estimating a rank-one matrix in Gaussian noise under a probabilistic model for the left and right factors of the matrix. The probabilistic model can impose constraints on the factors including sparsity and…

Information Theory · Computer Science 2015-09-16 Alyson K. Fletcher , Sundeep Rangan

We generalize the PAC (probably approximately correct) learning model to the quantum world by generalizing the concepts from classical functions to quantum processes, defining the problem of \emph{PAC learning quantum process}, and study…

Quantum Physics · Physics 2021-05-20 Kai-Min Chung , Han-Hsuan Lin

We propose a method for improving the prediction accuracy of learned robot dynamics models on out-of-distribution (OOD) states. We achieve this by leveraging two key sources of structure often present in robot dynamics: 1) sparsity, i.e.,…

Robotics · Computer Science 2024-03-21 Yating Lin , Glen Chou , Dmitry Berenson

The ultimate performance of machine learning algorithms for classification tasks is usually measured in terms of the empirical error probability (or accuracy) based on a testing dataset. Whereas, these algorithms are optimized through the…

Machine Learning · Computer Science 2021-12-13 Matias Vera , Leonardo Rey Vega , Pablo Piantanida

This paper analyzes the convergence and generalization of training a one-hidden-layer neural network when the input features follow the Gaussian mixture model consisting of a finite number of Gaussian distributions. Assuming the labels are…

Machine Learning · Computer Science 2023-01-30 Hongkang Li , Shuai Zhang , Meng Wang

This paper develops several average-case reduction techniques to show new hardness results for three central high-dimensional statistics problems, implying a statistical-computational gap induced by robustness, a detection-recovery gap and…

Computational Complexity · Computer Science 2020-05-20 Matthew Brennan , Guy Bresler

This paper derives fundamental limits on the performance of compressive classification when the source is a mixture of Gaussians. It provides an asymptotic analysis of a Bhattacharya based upper bound on the misclassification probability…

Information Theory · Computer Science 2014-01-28 Hugo Reboredo , Francesco Renna , Robert Calderbank , Miguel R. D. Rodrigues

The seminal paper by Mazumdar and Saha \cite{MS17a} introduced an extensive line of work on clustering with noisy queries. Yet, despite significant progress on the problem, the proposed methods depend crucially on knowing the exact…

Machine Learning · Computer Science 2022-07-22 Alberto Del Pia , Mingchen Ma , Christos Tzamos

Adversarially robust PAC learning has proved to be challenging, with the currently best known learners [Montasser et al., 2021a] relying on improper methods based on intricate compression schemes, resulting in sample complexity exponential…

Machine Learning · Computer Science 2025-02-12 Hassan Ashtiani , Vinayak Pathak , Ruth Urner

Domain adaptation solves image classification problems in the target domain by taking advantage of the labelled source data and unlabelled target data. Usually, the source and target domains share the same set of classes. As a special case,…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Qian Wang , Fanlin Meng , Toby P. Breckon

This work proposes a novel method for semi-supervised learning from partially labeled massive network-structured datasets, i.e., big data over networks. We model the underlying hypothesis, which relates data points to labels, as a graph…

Machine Learning · Computer Science 2017-05-16 Alexander Jung , Alfred O. Hero , Alexandru Mara , Saeed Jahromi

We study the problem of learning directed acyclic graphs from continuous observational data, generated according to a linear Gaussian structural equation model. State-of-the-art structure learning methods for this setting have at least one…

Methodology · Statistics 2025-04-03 Tong Xu , Armeen Taeb , Simge Küçükyavuz , Ali Shojaie