English
Related papers

Related papers: Determinantal Point Processes for Mini-Batch Diver…

200 papers

We propose mS2GD: a method incorporating a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient descent (S2GD). We consider the problem of minimizing a strongly convex function…

Machine Learning · Computer Science 2016-04-20 Jakub Konečný , Jie Liu , Peter Richtárik , Martin Takáč

A determinantal point process (DPP) is an elegant model that assigns a probability to every subset of a collection of $n$ items. While conventionally a DPP is parameterized by a symmetric kernel matrix, removing this symmetry constraint,…

Machine Learning · Computer Science 2022-07-04 Insu Han , Mike Gartrell , Elvis Dohmatob , Amin Karbasi

In this dissertation we propose alternative analysis of distributed stochastic gradient descent (SGD) algorithms that rely on spectral properties of the data covariance. As a consequence we can relate questions pertaining to speedups and…

Optimization and Control · Mathematics 2016-09-03 Avleen S. Bijral

Determinantal Point Processes (DPPs) provide an elegant and versatile way to sample sets of items that balance the point-wise quality with the set-wise diversity of selected items. For this reason, they have gained prominence in many…

Machine Learning · Statistics 2019-01-09 Zelda Mariet , Yaniv Ovadia , Jasper Snoek

We propose a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient descent applied to the problem of minimizing a strongly convex composite function represented as the sum of an…

Machine Learning · Computer Science 2014-10-20 Jakub Konečný , Jie Liu , Peter Richtárik , Martin Takáč

We present a determinantal point process (DPP) inspired alternative to non-maximum suppression (NMS) which has become an integral step in all state-of-the-art object detection frameworks. DPPs have been shown to encourage diversity in…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Samik Some , Mithun Das Gupta , Vinay P. Namboodiri

We introduce data structures for solving robust regression through stochastic gradient descent (SGD) by sampling gradients with probability proportional to their norm, i.e., importance sampling. Although SGD is widely used for large scale…

Machine Learning · Computer Science 2022-07-19 Sepideh Mahabadi , David P. Woodruff , Samson Zhou

We study the Stochastic Gradient Descent (SGD) method in nonconvex optimization problems from the point of view of approximating diffusion processes. We prove rigorously that the diffusion process can approximate the SGD algorithm weakly…

Machine Learning · Statistics 2018-03-06 Wenqing Hu , Chris Junchi Li , Lei Li , Jian-Guo Liu

Determinantal point processes (DPPs) have emerged as a kernelized alternative to vanilla independent sampling for generating efficient minibatches, coresets and other parsimonious representations of large-scale datasets. While theoretical…

Machine Learning · Statistics 2026-05-14 Hoang-Son Tran , Pranav Gupta , Rémi Bardenet , Subhroshekhar Ghosh

Conventional machine learning applications typically assume that data samples are independently and identically distributed (i.i.d.). However, practical scenarios often involve a data-generating process that produces highly dependent data…

Machine Learning · Computer Science 2022-04-04 Shaocong Ma , Ziyi Chen , Yi Zhou , Kaiyi Ji , Yingbin Liang

Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However,…

Machine Learning · Computer Science 2020-02-18 Tao Lin , Sebastian U. Stich , Kumar Kshitij Patel , Martin Jaggi

Determinantal point processes (DPPs) are elegant probabilistic models of repulsion that arise in quantum physics and random matrix theory. In contrast to traditional structured models like Markov random fields, which become intractable and…

Machine Learning · Statistics 2013-01-11 Alex Kulesza , Ben Taskar

Random restart of a given algorithm produces many partitions to yield a consensus clustering. Ensemble methods such as consensus clustering have been recognized as more robust approaches for data clustering than single clustering…

Machine Learning · Statistics 2021-02-09 Serge Vicente , Alejandro Murua

Determinantal point processes (DPPs) are probability models over subsets of a ground set that favor diverse selections while suppressing redundancy. That is, they tend to assign higher likelihood to collections whose elements complement one…

Optimization and Control · Mathematics 2026-04-13 Mohamad H. Kazma , Ahmad F. Taha

Determinantal point processes (DPPs) are random point processes well-suited for modeling repulsion. In machine learning, the focus of DPP-based models has been on diverse subset selection from a discrete and finite base set. This discrete…

Machine Learning · Statistics 2013-11-14 Raja Hafiz Affandi , Emily B. Fox , Ben Taskar

A very popular approach for solving stochastic optimization problems is the stochastic gradient descent method (SGD). Although the SGD iteration is computationally cheap and the practical performance of this method may be satisfactory under…

Optimization and Control · Mathematics 2017-06-21 Andrei Patrascu , Ion Necoara

Dimensionality reduction is a first step of many machine learning pipelines. Two popular approaches are principal component analysis, which projects onto a small number of well chosen but non-interpretable directions, and feature selection,…

Machine Learning · Statistics 2018-12-27 Ayoub Belhadji , Rémi Bardenet , Pierre Chainais

In this technical report, we discuss several sampling algorithms for Determinantal Point Processes (DPP). DPPs have recently gained a broad interest in the machine learning and statistics literature as random point processes with negative…

Computation · Statistics 2018-02-26 Nicolas Tremblay , Simon Barthelme , Pierre-Olivier Amblard

Stochastic gradient descent (SGD) is a widely adopted iterative method for optimizing differentiable objective functions. In this paper, we propose and discuss a novel approach to scale up SGD in applications involving non-convex functions…

Machine Learning · Statistics 2022-10-07 Saad Mohamad , Hamad Alamri , Abdelhamid Bouchachia

One of the most common methods to train machine learning algorithms today is the stochastic gradient descent (SGD). In a distributed setting, SGD-based algorithms have been shown to converge theoretically under specific circumstances. A…

Machine Learning · Computer Science 2025-08-22 Soumya Sarkar , Shweta Jain