English
Related papers

Related papers: Sharpened Error Bounds for Random Sampling Based $…

200 papers

In recent years, there have been significant advances in efficiently solving $\ell_s$-regression using linear system solvers and $\ell_2$-regression [Adil-Kyng-Peng-Sachdeva, J. ACM'24]. Would efficient smoothed $\ell_p$-norm solvers lead…

Optimization and Control · Mathematics 2026-01-16 Deeksha Adil , Brian Bullins , Arun Jambulapati , Aaron Sidford

The optimization problem that arises out of the least median of squared residuals method in linear regression is analyzed. To simplify the analysis, the problem is replaced by an equivalent one of minimizing the median of absolute…

Optimization and Control · Mathematics 2015-10-15 Nikolai Krivulin

We provide faster algorithms for approximately solving $\ell_{\infty}$ regression, a fundamental problem prevalent in both combinatorial and continuous optimization. In particular, we provide accelerated coordinate descent methods capable…

Data Structures and Algorithms · Computer Science 2020-04-03 Aaron Sidford , Kevin Tian

Least squares (LS)-based subset selection methods are popular in linear regression modeling. Best subset selection (BS) is known to be NP-hard and has a computational cost that grows exponentially with the number of predictors. Recently,…

Methodology · Statistics 2021-03-09 Sen Tian , Clifford M. Hurvich , Jeffrey S. Simonoff

For multiple index models, it has recently been shown that the sliced inverse regression (SIR) is consistent for estimating the sufficient dimension reduction (SDR) space if and only if $\rho=\lim\frac{p}{n}=0$, where $p$ is the dimension…

Statistics Theory · Mathematics 2018-06-19 Qian Lin , Zhigen Zhao , Jun S. Liu

Stochastic convex optimization is one of the most well-studied models for learning in modern machine learning. Nevertheless, a central fundamental question in this setup remained unresolved: "How many data points must be observed so that…

Machine Learning · Computer Science 2023-11-10 Daniel Carmon , Roi Livni , Amir Yehudayoff

In this paper, we investigate the sample size requirement for exact recovery of a high order tensor of low rank from a subset of its entries. We show that a gradient descent algorithm with initial value obtained from a spectral method can,…

Machine Learning · Statistics 2017-02-27 Dong Xia , Ming Yuan

The mean squared error loss is widely used in many applications, including auto-encoders, multi-target regression, and matrix factorization, to name a few. Despite computational advantages due to its differentiability, it is not robust to…

Machine Learning · Computer Science 2021-07-01 Armin Moharrer , Khashayar Kamran , Edmund Yeh , Stratis Ioannidis

Sampling from Diffusion Models can alternatively be seen as solving differential equations, where there is a challenge in balancing speed and image visual quality. ODE-based samplers offer rapid sampling time but reach a performance limit,…

Machine Learning · Computer Science 2025-02-28 Qinpeng Cui , Xinyi Zhang , Qiqi Bao , Qingmin Liao

We provide faster algorithms and improved sample complexities for approximating the top eigenvector of a matrix. Offline Setting: Given an $n \times d$ matrix $A$, we show how to compute an $\epsilon$ approximate top eigenvector in time…

Data Structures and Algorithms · Computer Science 2016-05-31 Chi Jin , Sham M. Kakade , Cameron Musco , Praneeth Netrapalli , Aaron Sidford

This study focuses on addressing the challenge of solving the reduced biquaternion equality constrained least squares (RBLSE) problem. We develop algebraic techniques to derive real and complex solutions for the RBLSE problem by utilizing…

Numerical Analysis · Mathematics 2025-05-05 Sk. Safique Ahmad , Neha Bhadala

A framework previously introduced in [3] for solving a sequence of stochastic optimization problems with bounded changes in the minimizers is extended and applied to machine learning problems such as regression and classification. The…

Machine Learning · Computer Science 2019-04-08 Craig Wilson , Yuheng Bu , Venugopal Veeravalli

Classical probabilistic rounding error analysis is particularly well suited to stochastic rounding (SR), and it yields strong results when dealing with floating-point algorithms that rely heavily on summation. For many numerical linear…

Numerical Analysis · Mathematics 2025-02-26 El-Mehdi El Arar , Massimiliano Fasi , Silviu-Ioan Filip , Mantas Mikaitis

This paper is concerned with the ordered statistic decoding with local constraints (LC-OSD) of binary linear block codes, which is a near maximum-likelihood decoding algorithm. Compared with the conventional OSD, the LC-OSD significantly…

Information Theory · Computer Science 2024-01-31 Jifan Liang , Xiao Ma

We study fast algorithms for statistical regression problems under the strong contamination model, where the goal is to approximately optimize a generalized linear model (GLM) given adversarially corrupted samples. Prior works in this line…

Data Structures and Algorithms · Computer Science 2021-06-23 Arun Jambulapati , Jerry Li , Tselil Schramm , Kevin Tian

We consider the problem of heteroscedastic linear regression, where, given $n$ samples $(\mathbf{x}_i, y_i)$ from $y_i = \langle \mathbf{w}^{*}, \mathbf{x}_i \rangle + \epsilon_i \cdot \langle \mathbf{f}^{*}, \mathbf{x}_i \rangle$ with…

Machine Learning · Statistics 2023-07-04 Dheeraj Baby , Aniket Das , Dheeraj Nagaraj , Praneeth Netrapalli

If uncorrelated random variables have a common expected value and decreasing variances then the variance of a sample mean is decreasing with the number of observations. Unfortunately, this natural and desirable Variance Reduction Property…

Statistics Theory · Mathematics 2013-04-11 Andrzej S. Kozek , Brian Jersky

We consider the online sparse linear regression problem, which is the problem of sequentially making predictions observing only a limited number of features in each round, to minimize regret with respect to the best sparse linear regressor,…

Machine Learning · Computer Science 2016-03-08 Dean Foster , Satyen Kale , Howard Karloff

Previous studies yielded discouraging results for item-level locally differentially private linear regression with $s^*$-sparsity assumption, where the minimax rate for $nm$ samples is $\mathcal{O}(s^{*}d / nm\varepsilon^2)$. This can be…

Machine Learning · Statistics 2024-08-09 Yuheng Ma , Ke Jia , Hanfang Yang

The recovery of sparse data is at the core of many applications in machine learning and signal processing. While such problems can be tackled using $\ell_1$-regularization as in the LASSO estimator and in the Basis Pursuit approach,…

Optimization and Control · Mathematics 2021-11-15 Christian Kümmerle , Claudio Mayrink Verdun , Dominik Stöger