English
Related papers

Related papers: Efficiently Using Second Order Information in Larg…

200 papers

The continuous nonlinear resource allocation problem (CONRAP) has broad applications in economics, engineering, production and inventory management, and often serves as a subproblem in complex programming. Without relying on monotonicity…

Optimization and Control · Mathematics 2025-01-10 Kaixiang Hu , Caixia Kou , Jianhua Yuan

To address the communication bottleneck problem in distributed optimization within a master-worker framework, we propose LocalNewton, a distributed second-order algorithm with local averaging. In LocalNewton, the worker machines update…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-05-18 Vipul Gupta , Avishek Ghosh , Michal Derezinski , Rajiv Khanna , Kannan Ramchandran , Michael Mahoney

We propose an efficient algorithm for sparse signal reconstruction problems. The proposed algorithm is an augmented Lagrangian method based on the dual sparse reconstruction problem. It is efficient when the number of unknown variables is…

Machine Learning · Statistics 2010-10-06 Ryota Tomioka , Masashi Sugiyama

The pseudo-likelihood method is one of the most popular algorithms for learning sparse binary pairwise Markov networks. In this paper, we formulate the $L_1$ regularized pseudo-likelihood problem as a sparse multiple logistic regression…

Machine Learning · Statistics 2017-04-10 Sinong Geng , Zhaobin Kuang , David Page

We propose a communicationally and computationally efficient algorithm for high-dimensional distributed sparse learning. At each iteration, local machines compute the gradient on local data and the master machine solves one shifted $l_1$…

Machine Learning · Statistics 2017-09-12 Jineng Ren , Jarvis Haupt

For the linear inverse problem with sparsity constraints, the $l_0$ regularized problem is NP-hard, and existing approaches either utilize greedy algorithms to find almost-optimal solutions or to approximate the $l_0$ regularization with…

Machine Learning · Computer Science 2024-02-14 Qinghua Tao , Xiangming Xi , Jun Xu , Johan A. K. Suykens

In recent years, a rich variety of regularization procedures have been proposed for high dimensional regression problems. However, tuning parameter choice and computational efficiency in ultra-high dimensional problems remain vexing issues.…

Computation · Statistics 2012-01-18 Hua Zhou , Artin Armagan , David B. Dunson

In distributed second order optimization, a standard strategy is to average many local estimates, each of which is based on a small sketch or batch of the data. However, the local estimates on each machine are typically biased, relative to…

Machine Learning · Computer Science 2020-07-06 Michał Dereziński , Burak Bartan , Mert Pilanci , Michael W. Mahoney

With the advent of machine learning, there have been several recent attempts to learn effective and generalizable heuristics. Local Heuristic A* (LoHA*) is one recent method that instead of learning the entire heuristic estimate, learns a…

Robotics · Computer Science 2024-05-07 Rishi Veerapaneni , Jonathan Park , Muhammad Suhail Saleem , Maxim Likhachev

Commonly employed reconstruction algorithms in compressed sensing (CS) use the $L_2$ norm as the metric for the residual error. However, it is well-known that least squares (LS) based estimators are highly sensitive to outliers present in…

Information Theory · Computer Science 2013-11-28 Rafael E. Carrillo , Kenneth E. Barner

We show that, for finite-sum minimization problems, incorporating partial second-order information of the objective function can dramatically improve the robustness to mini-batch size of variance-reduced stochastic gradient methods, making…

Optimization and Control · Mathematics 2024-04-24 Sachin Garg , Albert S. Berahas , Michał Dereziński

Scalable machine learning over big data is an important problem that is receiving a lot of attention in recent years. On popular distributed environments such as Hadoop running on a cluster of commodity machines, communication costs are…

Machine Learning · Computer Science 2015-03-18 Dhruv Mahajan , Nikunj Agrawal , S. Sathiya Keerthi , S. Sundararajan , Leon Bottou

The linear functional strategy for the regularization of inverse problems is considered. For selecting the regularization parameter therein, we propose the heuristic quasi-optimality principle and some modifications including the smoothness…

Numerical Analysis · Mathematics 2018-05-23 Stefan Kindermann , Sergiy Pereverzyev , Andrey Pilipenko

The systematization of the purely Lagrangean approach to constrained systems in the form of an algorithm involves the iterative construction of a generalized Hessian matrix W taking a rectangular form. This Hessian will exhibit as many left…

High Energy Physics - Theory · Physics 2008-11-26 Heinz J. Rothe , Klaus D. Rothe

We study the problem of learning latent variables in Gaussian graphical models. Existing methods for this problem assume that the precision matrix of the observed variables is the superposition of a sparse and a low-rank component. In this…

Machine Learning · Statistics 2017-07-12 Mohammadreza Soltani , Chinmay Hegde

Predictor screening rules, which discard predictors before fitting a model, have had considerable impact on the speed with which sparse regression problems, such as the lasso, can be solved. In this paper we present a new screening rule for…

Machine Learning · Statistics 2024-05-14 Johan Larsson , Jonas Wallin

Random projections or sketching are widely used in many algorithmic and learning contexts. Here we study the performance of iterative Hessian sketch for least-squares problems. By leveraging and extending recent results from random matrix…

Optimization and Control · Mathematics 2020-10-26 Jonathan Lacotte , Sifan Liu , Edgar Dobriban , Mert Pilanci

Rank deficient Hankel matrices are at the core of several applications. However, in practice, the coefficients of these matrices are noisy due to e.g. measurements errors and computational errors, so generically the involved matrices are…

Numerical Analysis · Mathematics 2020-12-15 Antonio Fazzi , Nicola Guglielmi , Ivan Markovsky

Joint diagonalization, the process of finding a shared set of approximate eigenvectors for a collection of matrices, arises in diverse applications such as multidimensional harmonic analysis or quantum information theory. This task is…

Optimization and Control · Mathematics 2025-02-12 Erik Troedsson , Marcus Carlsson , Herwig Wendt

Rehearsal-based approaches are a mainstay of continual learning (CL). They mitigate the catastrophic forgetting problem by maintaining a small fixed-size buffer with a subset of data from past tasks. While most rehearsal-based approaches…

Machine Learning · Computer Science 2023-05-02 Zifeng Wang , Zheng Zhan , Yifan Gong , Yucai Shao , Stratis Ioannidis , Yanzhi Wang , Jennifer Dy