Distributed Least Squares in Small Space via Sketching and Bias Reduction

• URL: http://arxiv.org/abs/2405.05343v1
• Date: Wed, 8 May 2024 18:16:37 GMT
• Title: Distributed Least Squares in Small Space via Sketching and Bias Reduction
• Authors: Sachin Garg, Kevin Tan, Michał Dereziński,
• Abstract summary: Matrix sketching is a powerful tool for reducing the size of large data matrices. We show that these limitations can be circumvented in the distributed setting by designing sketching methods that minimize the bias of the estimator, rather than its error. In particular, we give a sparse sketching method running in optimal space and current matrix multiplication time, which recovers a nearly-unbiased least squares estimator using two passes over the data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Matrix sketching is a powerful tool for reducing the size of large data matrices. Yet there are fundamental limitations to this size reduction when we want to recover an accurate estimator for a task such as least square regression. We show that these limitations can be circumvented in the distributed setting by designing sketching methods that minimize the bias of the estimator, rather than its error. In particular, we give a sparse sketching method running in optimal space and current matrix multiplication time, which recovers a nearly-unbiased least squares estimator using two passes over the data. This leads to new communication-efficient distributed averaging algorithms for least squares and related tasks, which directly improve on several prior approaches. Our key novelty is a new bias analysis for sketched least squares, giving a sharp characterization of its dependence on the sketch sparsity. The techniques include new higher-moment restricted Bai-Silverstein inequalities, which are of independent interest to the non-asymptotic analysis of deterministic equivalents for random matrices that arise from sketching.

Related papers

• Learning the Positions in CountSketch [49.57951567374372]
  We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem. In this work, we propose the first learning-based algorithms that also optimize the locations of the non-zero entries.
  arXiv  Detail & Related papers  (2023-06-11T07:28:35Z)
• Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition [14.453949553412821]
  We develop a theoretical framework for obtaining sharp guarantees on the convergence rate of sketch-and-project methods. We show that the convergence rate improves at least linearly with the sketch size, and even faster when the data matrix exhibits certain spectral decays. Our experiments support the theory and demonstrate that even extremely sparse sketches exhibit the convergence properties predicted by our framework.
  arXiv  Detail & Related papers  (2022-08-20T03:11:13Z)
• Distributed Sketching for Randomized Optimization: Exact Characterization, Concentration and Lower Bounds [54.51566432934556]
  We consider distributed optimization methods for problems where forming the Hessian is computationally challenging. We leverage randomized sketches for reducing the problem dimensions as well as preserving privacy and improving straggler resilience in asynchronous distributed systems.
  arXiv  Detail & Related papers  (2022-03-18T05:49:13Z)
• A Dimensionality Reduction Method for Finding Least Favorable Priors with a Focus on Bregman Divergence [108.28566246421742]
  This paper develops a dimensionality reduction method that allows us to move the optimization to a finite-dimensional setting with an explicit bound on the dimension. In order to make progress on the problem, we restrict ourselves to Bayesian risks induced by a relatively large class of loss functions, namely Bregman divergences.
  arXiv  Detail & Related papers  (2022-02-23T16:22:28Z)
• Fast Convex Quadratic Optimization Solvers with Adaptive Sketching-based Preconditioners [37.03247707259297]
  We consider least-squares problems with quadratic regularization and propose novel sketching-based iterative methods with an adaptive sketch size. The sketch size can be as small as the effective dimension of the data matrix to guarantee linear convergence. A major difficulty in choosing the sketch size in terms of the effective dimension lies in the fact that the latter is usually unknown in practice.
  arXiv  Detail & Related papers  (2021-04-29T04:36:41Z)
• Learning the Positions in CountSketch [51.15935547615698]
  We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem. In this work we propose the first learning algorithm that also optimize the locations of the non-zero entries. We show this algorithm gives better accuracy for low rank approximation than previous work, and apply it to other problems such as $k$-means clustering for the first time.
  arXiv  Detail & Related papers  (2020-07-20T05:06:29Z)
• Learning Minimax Estimators via Online Learning [55.92459567732491]
  We consider the problem of designing minimax estimators for estimating parameters of a probability distribution. We construct an algorithm for finding a mixed-case Nash equilibrium.
  arXiv  Detail & Related papers  (2020-06-19T22:49:42Z)
• Lower Bounds and a Near-Optimal Shrinkage Estimator for Least Squares using Random Projections [37.27708297562079]
  We derive an improved estimator for the least squares solution using the Gaussian sketch. Empirically, this estimator achieves smaller error on simulated and real datasets.
  arXiv  Detail & Related papers  (2020-06-15T06:42:18Z)
• Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization [56.05635751529922]
  We propose a new randomized algorithm for solving L2-regularized least-squares problems based on sketching. We consider two of the most popular random embeddings, namely, Gaussian embeddings and the Subsampled Randomized Hadamard Transform (SRHT)
  arXiv  Detail & Related papers  (2020-06-10T15:00:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.