paper-with-me

Papers

An Explicit Sampling Dependent Spectral Error Bound for Column Subset Selection

2015-05-04 · Tianbao Yang, Lijun Zhang, Rong Jin, Shenghuo Zhu

In this paper, we consider the problem of column subset selection. We present a novel analysis of the spectral norm reconstruction for a simple randomized algorithm and establish a new bound that depends explicitly on the sampling probabilities. The sampling dependent error bound (i) allows us to better understand the tradeoff in the reconstruction error due to sampling probabilities, (ii) exhibits more insights than existing error bounds that exploit specific probability distributions, and (iii) implies better sampling distributions. In particular, we show that a sampling distribution with probabilities proportional to the square root of the statistical leverage scores is always better than uniform sampling and is better than leverage-based sampling when the statistical leverage scores are very nonuniform. And by solving a constrained optimization problem related to the error bound with an efficient bisection search we are able to achieve better performance than using either the leverage-based distribution or that proportional to the square root of the statistical leverage scores. Numerical simulations demonstrate the benefits of the new sampling distributions for low-rank matrix approximation and least square approximation compared to state-of-the art algorithms.

📄 PDF Abstract BibTeX arXiv:1505.00526

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels

2018-10-09 · NeurIPS 2018 12 · Shahin Shahrampour, Vahid Tarokh

Nonlinear kernels can be approximated using finite-dimensional feature maps for efficient risk minimization. Due to the inherent trade-off between the dimension of the (mapped) feature space and the approximation accurac…

A Uniform Generalization Error Bound for Generative Adversarial Networks

2019-09-25 · Hao Chen, Zhanfeng Mo, Qingyi Gao, Zhouwang Yang 외

This paper focuses on the theoretical investigation of unsupervised generalization theory of generative adversarial networks (GANs). We first formulate a more reasonable definition of general error and generalization bo…

Generalization Bounds

Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling

2015-12-01 · NeurIPS 2015 12 · Zheng Qu, Peter Richtarik, Tong Zhang

We study the problem of minimizing the average of a large number of smooth convex functions penalized with a strongly convex regularizer. We propose and analyze a novel primal-dual method (Quartz) which at every iteratio…

Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries

2026-05-22 · Dongmin Lee, Anuran Makur, Japneet Singh arxiv

Bradley-Terry-Luce (BTL) model estimation is a well-established strategy to rank a collection of items given a dataset of pairwise comparisons. Although the theoretical performance of BTL estimation methods, such as spec…

Randomized Dual Coordinate Ascent with Arbitrary Sampling

2014-11-21 · Zheng Qu, Peter Richtárik, Tong Zhang

We study the problem of minimizing the average of a large number of smooth convex functions penalized with a strongly convex regularizer. We propose and analyze a novel primal-dual method (Quartz) which at every iteratio…