paper-with-me

Papers

Optimal Mini-Batch Size Selection for Fast Gradient Descent

2019-11-15 · Michael P. Perrone, Haidar Khan, Changhoan Kim, Anastasios Kyrillidis, Jerry Quinn, Valentina Salapura

This paper presents a methodology for selecting the mini-batch size that minimizes Stochastic Gradient Descent (SGD) learning time for single and multiple learner problems. By decoupling algorithmic analysis issues from hardware and software implementation details, we reveal a robust empirical inverse law between mini-batch size and the average number of SGD updates required to converge to a specified error threshold. Combining this empirical inverse law with measured system performance, we create an accurate, closed-form model of average training time and show how this model can be used to identify quantifiable implications for both algorithmic and hardware aspects of machine learning. We demonstrate the inverse law empirically, on both image recognition (MNIST, CIFAR10 and CIFAR100) and machine translation (Europarl) tasks, and provide a theoretic justification via proving a novel bound on mini-batch SGD training.

📄 PDF Abstract BibTeX arXiv:1911.06459

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

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

Asymptotically Optimal Exact Minibatch Metropolis-Hastings

2020-06-20 · NeurIPS 2020 12 · Ruqi Zhang, A. Feder Cooper, Christopher De Sa

Metropolis-Hastings (MH) is a commonly-used MCMC algorithm, but it can be intractable on large datasets due to requiring computations over the whole dataset. In this paper, we study minibatch MH methods, which instead us…

regression

SGD: General Analysis and Improved Rates

2019-01-27 · Robert Mansel Gower, Nicolas Loizou, Xun Qian, Alibek Sailanbayev 외

We propose a general yet simple theorem describing the convergence of SGD under the arbitrary sampling paradigm. Our theorem describes the convergence of an infinite array of variants of SGD, each of which is associated …

On Batch-size Selection for Stochastic Training for Graph Neural Networks

2021-01-01 · Yaochen Hu, Amit Levi, Ishaan Kumar, Yingxue Zhang 외

In recent years deep learning has become an important framework for supervised learning. It has been observed that stochastic gradient decent (SGD) method in deep learning networks performs well when the minibatch size i…

Deep Learning

The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning

2017-12-18 · ICML 2018 7 · Siyuan Ma, Raef Bassily, Mikhail Belkin

In this paper we aim to formally explain the phenomenon of fast convergence of SGD observed in modern machine learning. The key observation is that most modern learning architectures are over-parametrized and are trained…

Optimal mini-batch and step sizes for SAGA

2019-01-31 · Nidham Gazagnadou, Robert M. Gower, Joseph Salmon

Recently it has been shown that the step sizes of a family of variance reduced gradient methods called the JacSketch methods depend on the expected smoothness constant. In particular, if this expected smoothness constant…