English
Related papers

Related papers: Debiasing Mini-Batch Quadratics for Applications i…

200 papers

Solving symmetric positive definite linear problems is a fundamental computational task in machine learning. The exact solution, famously, is cubicly expensive in the size of the matrix. To alleviate this problem, several linear-time…

Machine Learning · Computer Science 2017-06-02 Filip de Roos , Philipp Hennig

In many contemporary optimization problems such as those arising in machine learning, it can be computationally challenging or even infeasible to evaluate an entire function or its derivatives. This motivates the use of stochastic…

Optimization and Control · Mathematics 2021-07-01 El-houcine Bergou , Youssef Diouane , Vladimir Kunc , Vyacheslav Kungurtsev , Clément W. Royer

In this paper, we develop a novel second-order method for training feed-forward neural nets. At each iteration, we construct a quadratic approximation to the cost function in a low-dimensional subspace. We minimize this approximation inside…

Computer Vision and Pattern Recognition · Computer Science 2018-05-25 Viacheslav Dudar , Giovanni Chierchia , Emilie Chouzenoux , Jean-Christophe Pesquet , Vladimir Semenov

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

Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes, making them unsuitable for applications where computational resources are limited. To solve this, we perform probabilistic reasoning over…

Machine Learning · Statistics 2020-12-08 Javier Antorán , James Urquhart Allingham , José Miguel Hernández-Lobato

Enabling low precision implementations of deep learning models, without considerable performance degradation, is necessary in resource and latency constrained settings. Moreover, exploiting the differences in sensitivity to quantization…

Machine Learning · Computer Science 2022-10-28 Ignacio Hounie , Juan Elenter , Alejandro Ribeiro

Stochastic gradient descent and other first-order variants, such as Adam and AdaGrad, are commonly used in the field of deep learning due to their computational efficiency and low-storage memory requirements. However, these methods do not…

Optimization and Control · Mathematics 2025-02-19 Aditya Ranganath , Mukesh Singhal , Roummel Marcia

The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in constructing Bayesian neural networks. It is theoretically compelling since it can be seen as a Gaussian process posterior with the mean function…

Machine Learning · Computer Science 2023-07-13 Agustinus Kristiadi , Alexander Immer , Runa Eschenhagen , Vincent Fortuin

The use of mini-batches of data in training artificial neural networks is nowadays very common. Despite its broad usage, theories explaining quantitatively how large or small the optimal mini-batch size should be are missing. This work…

Disordered Systems and Neural Networks · Physics 2024-01-17 Raffaele Marino , Federico Ricci-Tersenghi

We study the effect of mini-batching on the loss landscape of deep neural networks using spiked, field-dependent random matrix theory. We demonstrate that the magnitude of the extremal values of the batch Hessian are larger than those of…

Machine Learning · Statistics 2021-11-08 Diego Granziol , Stefan Zohren , Stephen Roberts

Modern deep neural network training is typically based on mini-batch stochastic gradient optimization. While the use of large mini-batches increases the available computational parallelism, small batch training has been shown to provide…

Machine Learning · Computer Science 2018-04-23 Dominic Masters , Carlo Luschi

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow…

Optimization and Control · Mathematics 2026-05-18 Jeremy Bertoncini , Alberto De Marchi , Matthias Gerdts , Simon Gottschalk

Establishing a fast rate of convergence for optimization methods is crucial to their applicability in practice. With the increasing popularity of deep learning over the past decade, stochastic gradient descent and its adaptive variants…

Optimization and Control · Mathematics 2022-01-03 Adityanarayanan Radhakrishnan , Mikhail Belkin , Caroline Uhler

High-dimensional representations, such as radial basis function networks or tile coding, are common choices for policy evaluation in reinforcement learning. Learning with such high-dimensional representations, however, can be expensive,…

Machine Learning · Computer Science 2017-08-07 Yangchen Pan , Erfan Sadeqi Azer , Martha White

This paper addresses the optimization problem of minimizing non-convex continuous functions, which is relevant in the context of high-dimensional machine learning applications characterized by over-parametrization. We analyze a randomized…

Machine Learning · Computer Science 2025-02-28 Jim Zhao , Aurelien Lucchi , Nikita Doikov

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.…

Machine Learning · Computer Science 2017-11-15 Hao Li , Soham De , Zheng Xu , Christoph Studer , Hanan Samet , Tom Goldstein

Large-scale distributed training of deep neural networks suffer from the generalization gap caused by the increase in the effective mini-batch size. Previous approaches try to solve this problem by varying the learning rate and batch size…

Machine Learning · Computer Science 2019-04-02 Kazuki Osawa , Yohei Tsuji , Yuichiro Ueno , Akira Naruse , Rio Yokota , Satoshi Matsuoka

Distributed training in deep learning (DL) is common practice as data and models grow. The current practice for distributed training of deep neural networks faces the challenges of communication bottlenecks when operating at scale, and…

Machine Learning · Computer Science 2020-12-21 Shubhankar Gahlot , Junqi Yin , Mallikarjun Shankar

Laplace approximations are commonly used to approximate high-dimensional integrals in statistical applications, but the quality of such approximations as the dimension of the integral grows is not well understood. In this paper, we prove a…

Statistics Theory · Mathematics 2018-08-21 Helen Ogden

Deep CCA is a recently proposed deep neural network extension to the traditional canonical correlation analysis (CCA), and has been successful for multi-view representation learning in several domains. However, stochastic optimization of…

Machine Learning · Computer Science 2015-10-08 Weiran Wang , Raman Arora , Karen Livescu , Nathan Srebro