English
Related papers

Related papers: Step-Size Decay and Structural Stagnation in Greed…

200 papers

Kernel based methods provide a way to reconstruct potentially high-dimensional functions from meshfree samples, i.e., sampling points and corresponding target values. A crucial ingredient for this to be successful is the distribution of the…

Numerical Analysis · Mathematics 2021-05-19 Tizian Wenzel , Gabriele Santin , Bernard Haasdonk

There is mounting evidence of emergent phenomena in the capabilities of deep learning methods as we scale up datasets, model sizes, and training times. While there are some accounts of how these resources modulate statistical capacity, far…

Machine Learning · Computer Science 2023-01-18 Boaz Barak , Benjamin L. Edelman , Surbhi Goel , Sham Kakade , Eran Malach , Cyril Zhang

In this work, we consider learning sparse models in large scale settings, where the number of samples and the feature dimension can grow as large as millions or billions. Two immediate issues occur under such challenging scenario: (i)…

Machine Learning · Statistics 2023-01-31 Atul Dhingra , Jie Shen , Nicholas Kleene

Despite impressive performance, deep neural networks require significant memory and computation costs, prohibiting their application in resource-constrained scenarios. Sparse training is one of the most common techniques to reduce these…

Machine Learning · Computer Science 2023-12-06 Bowen Lei , Dongkuan Xu , Ruqi Zhang , Shuren He , Bani K. Mallick

It has been experimentally observed that the efficiency of distributed training with stochastic gradient (SGD) depends decisively on the batch size and -- in asynchronous implementations -- on the gradient staleness. Especially, it has been…

Machine Learning · Computer Science 2021-03-04 Sebastian U. Stich , Amirkeivan Mohtashami , Martin Jaggi

Many problems in signal processing and machine learning can be formalized as weak submodular optimization tasks. For such problems, a simple greedy algorithm (\textsc{Greedy}) is guaranteed to find a solution achieving the objective with a…

Discrete Mathematics · Computer Science 2021-11-24 Abolfazl Hashemi , Haris Vikalo , Gustavo de Veciana

Efficient computation of min-max problems is a central question in optimization, learning, games, and controls. Arguably the most natural algorithm is gradient-descent-ascent (GDA). However, since the 1970s, conventional wisdom has argued…

Optimization and Control · Mathematics 2025-05-05 Henry Shugart , Jason M. Altschuler

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

In a standard NP-complete optimization problem we introduce an interpolating algorithm between the quick decrease along the gradient (greedy dynamics) and a slow decrease close to the level curves (reluctant dynamics). We find that for a…

Mathematical Physics · Physics 2007-05-23 P. Contucci , C. Giardina' , C. Giberti , F. Unguendoli , C. Vernia

We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror descent that exploits the naturally incurred sparsity by alternating between periods of static and dynamic sparsity pattern updates. The key…

Machine Learning · Computer Science 2026-05-19 Yannick Lunk , Sebastian J. Scott , Leon Bungert

This paper considers optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network to lie in…

Multiagent Systems · Computer Science 2020-04-22 Roula Nassif , Stefan Vlaski , Ali H. Sayed

In this paper we prove the efficacy of a simple greedy algorithm for a finite horizon online resource allocation/matching problem, when the corresponding static planning linear program (SPP) exhibits a non-degeneracy condition called the…

Data Structures and Algorithms · Computer Science 2022-07-26 Varun Gupta

We empirically analyze a simple heuristic for large sparse set cover problems. It uses the weighted greedy algorithm as a basic building block. By multiplicative updates of the weights attached to the elements, the greedy solution is…

Data Structures and Algorithms · Computer Science 2020-10-30 Marc Alexa

Stochastic Gradient Descent (SGD) is widely used in machine learning problems to efficiently perform empirical risk minimization, yet, in practice, SGD is known to stall before reaching the actual minimizer of the empirical risk. SGD…

Machine Learning · Statistics 2017-02-09 Vivak Patel

This paper describes a hierarchical learning strategy for generating sparse representations of multivariate datasets. The hierarchy arises from approximation spaces considered at successively finer scales. A detailed analysis of stability,…

Machine Learning · Statistics 2019-10-23 Prashant Shekhar , Abani Patra

Greedy Pursuits are very popular in Compressed Sensing for sparse signal recovery. Though many of the Greedy Pursuits possess elegant theoretical guarantees for performance, it is well known that their performance depends on the statistical…

Applications · Statistics 2012-06-20 Sooraj K. Ambat , Saikat Chatterjee , K. V. S. Hari

A major enterprise in compressed sensing and sparse approximation is the design and analysis of computationally tractable algorithms for recovering sparse, exact or approximate, solutions of underdetermined linear systems of equations. Many…

Information Theory · Computer Science 2010-04-13 Jeffrey D. Blanchard , Coralia Cartis , Jared Tanner , Andrew Thompson

Data-dependent greedy algorithms in kernel spaces are known to provide fast converging interpolants, while being extremely easy to implement and efficient to run. Despite this experimental evidence, no detailed theory has yet been…

Numerical Analysis · Mathematics 2022-10-31 Tizian Wenzel , Gabriele Santin , Bernard Haasdonk

Distributed optimization is pivotal for large-scale signal processing and machine learning, yet communication overhead remains a major bottleneck. Low-rank gradient compression, in which the transmitted gradients are approximated by…

Machine Learning · Computer Science 2025-10-21 Chuyan Chen , Yutong He , Pengrui Li , Weichen Jia , Kun Yuan

Parsimony, including sparsity and low rank, has been shown to successfully model data in numerous machine learning and signal processing tasks. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an…

Machine Learning · Computer Science 2012-12-18 Pablo Sprechmann , Alex M. Bronstein , Guillermo Sapiro