English
Related papers

Related papers: A Fast Spectral Algorithm for Mean Estimation with…

200 papers

We study smooth stochastic optimization problems on Riemannian manifolds. Via adapting the recently proposed SPIDER algorithm \citep{fang2018spider} (a variance reduced stochastic method) to Riemannian manifold, we can achieve faster rate…

Optimization and Control · Mathematics 2018-12-17 Jingzhao Zhang , Hongyi Zhang , Suvrit Sra

A long series of recent results and breakthroughs have led to faster and better distributed approximation algorithms for single source shortest paths (SSSP) and related problems in the CONGEST model. The runtime of all these algorithms,…

Data Structures and Algorithms · Computer Science 2018-08-09 Bernhard Haeupler , Jason Li

Large language models and deep neural networks achieve strong performance but suffer from reliability issues and high computational cost. This thesis proposes a unified framework based on spectral geometry and random matrix theory to…

Machine Learning · Computer Science 2026-01-27 Davide Ettori

We give the first polynomial-time algorithm for performing linear or polynomial regression resilient to adversarial corruptions in both examples and labels. Given a sufficiently large (polynomial-size) training set drawn i.i.d. from…

Machine Learning · Computer Science 2020-06-05 Adam Klivans , Pravesh K. Kothari , Raghu Meka

We provide an algorithm for properly learning mixtures of two single-dimensional Gaussians without any separability assumptions. Given $\tilde{O}(1/\varepsilon^2)$ samples from an unknown mixture, our algorithm outputs a mixture that is…

Data Structures and Algorithms · Computer Science 2014-05-20 Constantinos Daskalakis , Gautam Kamath

Estimating the geometric median of a dataset is a robust counterpart to mean estimation, and is a fundamental problem in computational geometry. Recently, [HSU24] gave an $(\varepsilon, \delta)$-differentially private algorithm obtaining an…

Data Structures and Algorithms · Computer Science 2025-05-27 Syamantak Kumar , Daogao Liu , Kevin Tian , Chutong Yang

Gradient clipping is a standard safeguard for training neural networks under noisy, heavy-tailed stochastic gradients; yet, most clipping rules treat all parameters as vectors and ignore the matrix structure of modern architectures. We show…

Machine Learning · Computer Science 2026-05-13 Alexander Yukhimchuk , Mladen Kolar , Martin Takáč , Sayantan Choudhury

For a tall $n\times d$ matrix $A$ and a random $m\times n$ sketching matrix $S$, the sketched estimate of the inverse covariance matrix $(A^\top A)^{-1}$ is typically biased: $E[(\tilde A^\top\tilde A)^{-1}]\ne(A^\top A)^{-1}$, where…

Data Structures and Algorithms · Computer Science 2021-07-13 Michał Dereziński , Zhenyu Liao , Edgar Dobriban , Michael W. Mahoney

We consider stochastic convex optimization problems where the objective is an expectation over smooth functions. For this setting we suggest a novel gradient estimate that combines two recent mechanism that are related to notion of…

Machine Learning · Computer Science 2025-03-06 Tehila Dahan , Kfir Y. Levy

In this work, we study the asymptotic randomness of an algorithmic estimator of the saddle point of a globally convex-concave and locally strongly-convex strongly-concave objective. Specifically, we show that the averaged iterates of a…

Optimization and Control · Mathematics 2023-11-07 Abhishek Roy , Yi-An Ma

We present an $\mathcal{O}^\star(2^{0.5n})$ time and $\mathcal{O}^\star(2^{0.249999n})$ space randomized algorithm for solving worst-case Subset Sum instances with $n$ integers. This is the first improvement over the long-standing…

Data Structures and Algorithms · Computer Science 2021-04-13 Jesper Nederlof , Karol Węgrzycki

We give a $2^{n+o(n)}$-time and space randomized algorithm for solving the exact Closest Vector Problem (CVP) on $n$-dimensional Euclidean lattices. This improves on the previous fastest algorithm, the deterministic…

Data Structures and Algorithms · Computer Science 2019-01-28 Divesh Aggarwal , Daniel Dadush , Noah Stephens-Davidowitz

In this paper, we investigate diagonal estimation for large or implicit matrices, aiming to develop a novel and efficient stochastic algorithm that incorporates adaptive parameter selection. We explore the influence of different eigenvalue…

Machine Learning · Statistics 2024-10-16 Zongyuan Han , Wenhao Li , Shengxin Zhu

We use a rank one Gaussian perturbation to derive a smooth stochastic approximation of the maximum eigenvalue function. We then combine this smoothing result with an optimal smooth stochastic optimization algorithm to produce an efficient…

Optimization and Control · Mathematics 2014-03-05 Alexandre d'Aspremont , Noureddine El Karoui

We propose a nonconvex estimator for joint multivariate regression and precision matrix estimation in the high dimensional regime, under sparsity constraints. A gradient descent algorithm with hard thresholding is developed to solve the…

Machine Learning · Statistics 2016-06-03 Jinghui Chen , Quanquan Gu

We develop an efficient simulation algorithm for computing the tail probabilities of the infinite series $S = \sum_{n \geq 1} a_n X_n$ when random variables $X_n$ are heavy-tailed. As $S$ is the sum of infinitely many random variables, any…

Probability · Mathematics 2016-09-08 Henrik Hult , Sandeep Juneja , Karthyek Murthy

We study the estimation of high-dimensional covariance matrices under elliptical factor models with 2 + {\epsilon}th moment. For such heavy-tailed data, robust estimators like the Huber-type estimator in Fan, Liu and Wang (2018) can not…

Statistics Theory · Mathematics 2024-06-27 Yi Ding , Xinghua Zheng

We consider convex stochastic optimization problems under different assumptions on the properties of available stochastic subgradient. It is known that, if the value of the objective function is available, one can obtain, in parallel,…

Optimization and Control · Mathematics 2017-01-19 Pavel Dvurechensky , Alexander Gasnikov , Anastasia Lagunovskaya

Datasets with extreme observations and/or heavy-tailed error distributions are commonly encountered and should be analyzed with careful consideration of these features from a statistical perspective. Small deviations from an assumed model,…

Methodology · Statistics 2023-01-12 Meadhbh O'Neill , Kevin Burke

We use the Sum of Squares method to develop new efficient algorithms for learning well-separated mixtures of Gaussians and robust mean estimation, both in high dimensions, that substantially improve upon the statistical guarantees achieved…

Data Structures and Algorithms · Computer Science 2017-11-21 Samuel B. Hopkins , Jerry Li