paper-with-me

Papers

Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms

2015-06-22 · Christopher De Sa, Ce Zhang, Kunle Olukotun, Christopher Ré

Stochastic gradient descent (SGD) is a ubiquitous algorithm for a variety of machine learning problems. Researchers and industry have developed several techniques to optimize SGD's runtime performance, including asynchronous execution and reduced precision. Our main result is a martingale-based analysis that enables us to capture the rich noise models that may arise from such techniques. Specifically, we use our new analysis in three ways: (1) we derive convergence rates for the convex case (Hogwild!) with relaxed assumptions on the sparsity of the problem; (2) we analyze asynchronous SGD algorithms for non-convex matrix problems including matrix completion; and (3) we design and analyze an asynchronous SGD algorithm, called Buckwild!, that uses lower-precision arithmetic. We show experimentally that our algorithms run efficiently for a variety of problems on modern hardware.

📄 PDF Abstract BibTeX arXiv:1506.06438

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix Completion

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

Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms

2015-12-01 · NeurIPS 2015 12 · Christopher M. De Sa, Ce Zhang, Kunle Olukotun, Christopher Ré

Stochastic gradient descent (SGD) is a ubiquitous algorithm for a variety of machine learning problems. Researchers and industry have developed several techniques to optimize SGD's runtime performance, including asynchro…

Matrix Completion

CYCLADES: Conflict-free Asynchronous Machine Learning

2016-05-31 · NeurIPS 2016 12 · Xinghao Pan, Maximilian Lam, Stephen Tu, Dimitris Papailiopoulos 외

We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting. CYCLADES is asynchronous during shared model updates, and requires no memory locking mechanisms, s…

BIG-bench Machine LearningStochastic Optimization

HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent

2011-06-28 · Feng Niu, Benjamin Recht, Christopher Re, Stephen J. Wright

Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve state-of-the-art performance on a variety of machine learning tasks. Several researchers have recently proposed schemes to parallelize SGD, but al…

Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent

2011-12-01 · NeurIPS 2011 12 · Benjamin Recht, Christopher Re, Stephen Wright, Feng Niu

Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve state-of-the-art performance on a variety of machine learning tasks. Several researchers have recently proposed schemes to parallelize SGD, but…

Clone MCMC: Parallel High-Dimensional Gaussian Gibbs Sampling

2017-12-01 · NeurIPS 2017 12 · Andrei-Cristian Barbos, Francois Caron, Jean-François Giovannelli, Arnaud Doucet

We propose a generalized Gibbs sampler algorithm for obtaining samples approximately distributed from a high-dimensional Gaussian distribution. Similarly to Hogwild methods, our approach does not target the original Gaus…

Vocal Bursts Intensity Prediction