paper-with-me

Papers

A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta

2022-06-22 · Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky

Mini-batch SGD with momentum is a fundamental algorithm for learning large predictive models. In this paper we develop a new analytic framework to analyze noise-averaged properties of mini-batch SGD for linear models at constant learning rates, momenta and sizes of batches. Our key idea is to consider the dynamics of the second moments of model parameters for a special family of "Spectrally Expressible" approximations. This allows to obtain an explicit expression for the generating function of the sequence of loss values. By analyzing this generating function, we find, in particular, that 1) the SGD dynamics exhibits several convergent and divergent regimes depending on the spectral distributions of the problem; 2) the convergent regimes admit explicit stability conditions, and explicit loss asymptotics in the case of power-law spectral distributions; 3) the optimal convergence rate can be achieved at negative momenta. We verify our theoretical predictions by extensive experiments with MNIST, CIFAR10 and synthetic problems, and find a good quantitative agreement.

📄 PDF Abstract BibTeX arXiv:2206.11124

Code (1)

godofnothing/powerlawoptimization 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

SGD with Momentum 설명 없음
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

2016-09-15 · Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy 외

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ d…

SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation

2020-06-18 · Robert M. Gower, Othmane Sebbouh, Nicolas Loizou

Stochastic Gradient Descent (SGD) is being used routinely for optimizing non-convex functions. Yet, the standard convergence theory for SGD in the smooth non-convex setting gives a slow sublinear convergence to a station…

Twin actor twin delayed deep deterministic policy gradient (TATD3) learning for batch process control

2021-02-25 · Tanuja Joshi, Shikhar Makker, Hariprasad Kodamana, Harikumar Kandath

Control of batch processes is a difficult task due to their complex nonlinear dynamics and unsteady-state operating conditions within batch and batch-to-batch. It is expected that some of these challenges can be addresse…

continuous-controlContinuous ControlReinforcement Learning (RL)

Generating Adversarial Samples in Mini-Batches May Be Detrimental To Adversarial Robustness

2023-03-30 · Timothy Redgrave, Colton Crum

Neural networks have been proven to be both highly effective within computer vision, and highly vulnerable to adversarial attacks. Consequently, as the use of neural networks increases due to their unrivaled performance,…

Adversarial Robustness

Learning a Metric Embedding for Face Recognition using the Multibatch Method

2016-05-24 · NeurIPS 2016 12 · Oren Tadmor, Yonatan Wexler, Tal Rosenwein, Shai Shalev-Shwartz 외

This work is motivated by the engineering task of achieving a near state-of-the-art face recognition on a minimal computing budget running on an embedded system. Our main technical contribution centers around a novel tra…

Face RecognitionGPU