English
Related papers

Related papers: List-Decodable Regression via Expander Sketching

200 papers

One approach to improving the running time of kernel-based machine learning methods is to build a small sketch of the input and use it in lieu of the full kernel matrix in the machine learning task of interest. Here, we describe a version…

Machine Learning · Statistics 2015-11-10 Ahmed El Alaoui , Michael W. Mahoney

Many datasets such as market basket data, text or hypertext documents, and sensor observations recorded in different locations or time periods, are modeled as a collection of sets over a ground set of keys. We are interested in basic…

Databases · Computer Science 2009-03-05 Edith Cohen , Haim Kaplan

This paper aims to propose and theoretically analyze a new distributed scheme for sparse linear regression and feature selection. The primary goal is to learn the few causal features of a high-dimensional dataset based on noisy observations…

Machine Learning · Statistics 2021-11-05 Hanie Barghi , Amir Najafi , Seyed Abolfazl Motahari

This paper develops conformal inference methods to construct a confidence interval for the frequency of a queried object in a very large discrete data set, based on a sketch with a lower memory footprint. This approach requires no knowledge…

Methodology · Statistics 2023-08-17 Matteo Sesia , Stefano Favaro , Edgar Dobriban

In second-order optimization, a potential bottleneck can be computing the Hessian matrix of the optimized function at every iteration. Randomized sketching has emerged as a powerful technique for constructing estimates of the Hessian which…

Optimization and Control · Mathematics 2021-07-16 Michał Dereziński , Jonathan Lacotte , Mert Pilanci , Michael W. Mahoney

Motivated by the prevalence of environments in which data is abundant while resources for storage and/or transmission might be scarce, we study linear regression when predictors, their squares, and responses are subject to single-bit…

Statistics Theory · Mathematics 2026-04-01 Daniel Hill , Martin Slawski

We study how to construct compressed datasets that suffice to recover optimal decisions in linear programs with an unknown cost vector $c$ lying in a prior set $\mathcal{C}$. Recent work by Bennouna et al. provides an exact geometric…

Optimization and Control · Mathematics 2026-05-25 Yuhan Ye , Saurabh Amin , Asuman Ozdaglar

We derive computationally tractable methods to select a small subset of experiment settings from a large pool of given design points. The primary focus is on linear regression models, while the technique extends to generalized linear models…

Machine Learning · Statistics 2017-12-21 Yining Wang , Adams Wei Yu , Aarti Singh

Calculating the diameter of an undirected graph requires quadratic running time under the Strong Exponential Time Hypothesis and this barrier works even against any approximation better than 3/2. For planar graphs with positive edge…

Data Structures and Algorithms · Computer Science 2025-07-08 Michał Włodarczyk

We provide efficient algorithms for overconstrained linear regression problems with size $n \times d$ when the loss function is a symmetric norm (a norm invariant under sign-flips and coordinate-permutations). An important class of…

Data Structures and Algorithms · Computer Science 2019-10-08 Zhao Song , Ruosong Wang , Lin F. Yang , Hongyang Zhang , Peilin Zhong

We introduce a new method for two-sample testing of high-dimensional linear regression coefficients without assuming that those coefficients are individually estimable. The procedure works by first projecting the matrices of covariates and…

Statistics Theory · Mathematics 2023-05-11 Fengnan Gao , Tengyao Wang

We develop a technique to design efficiently computable estimators for sparse linear regression in the simultaneous presence of two adversaries: oblivious and adaptive. We design several robust algorithms that outperform the state of the…

Machine Learning · Computer Science 2024-11-01 Chih-Hung Liu , Gleb Novikov

We use exponential start time clustering to design faster and more work-efficient parallel graph algorithms involving distances. Previous algorithms usually rely on graph decomposition routines with strict restrictions on the diameters of…

Data Structures and Algorithms · Computer Science 2015-06-25 Gary L. Miller , Richard Peng , Adrian Vladu , Shen Chen Xu

We initiate the study of sub-linear sketching and streaming techniques for estimating the output size of common dictionary compressors such as Lempel-Ziv '77, the run-length Burrows-Wheeler transform, and grammar compression. To this end,…

Data Structures and Algorithms · Computer Science 2024-08-20 Ruben Becker , Matteo Canton , Davide Cenzato , Sung-Hwan Kim , Bojana Kodric , Nicola Prezza

This article considers "compressive learning," an approach to large-scale machine learning where datasets are massively compressed before learning (e.g., clustering, classification, or regression) is performed. In particular, a "sketch" is…

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 new algorithms and conditional hardness for the problem of estimating effective resistances in $n$-node $m$-edge undirected, expander graphs. We provide an $\widetilde{O}(m\epsilon^{-1})$-time algorithm that produces with high…

Data Structures and Algorithms · Computer Science 2023-06-27 Rajat Vadiraj Dwaraknath , Ishani Karmarkar , Aaron Sidford

In this paper, we show that the bundle method can be applied to solve semidefinite programming problems with a low rank solution without ever constructing a full matrix. To accomplish this, we use recent results from randomly sketching…

Optimization and Control · Mathematics 2021-02-02 Lijun Ding , Benjamin Grimmer

In this paper, we propose an efficient reliability based segmentation-discarding decoding (SDD) algorithm for short block-length codes. A novel segmentation-discarding technique is proposed along with the stopping rule to significantly…

Information Theory · Computer Science 2019-01-23 Chentao Yue , Mahyar Shirvanimoghaddam , Yonghui Li , Branka Vucetic

We propose a novel algorithm for greedy forward feature selection for regularized least-squares (RLS) regression and classification, also known as the least-squares support vector machine or ridge regression. The algorithm, which we call…

Machine Learning · Statistics 2010-03-19 Tapio Pahikkala , Antti Airola , Tapio Salakoski