paper-with-me

홈 › Papers

First-order and second-order variants of the gradient descent in a unified framework

2018-10-18 · Thomas Pierrot, Nicolas Perrin, Olivier Sigaud

In this paper, we provide an overview of first-order and second-order variants of the gradient descent method that are commonly used in machine learning. We propose a general framework in which 6 of these variants can be interpreted as different instances of the same approach. They are the vanilla gradient descent, the classical and generalized Gauss-Newton methods, the natural gradient descent method, the gradient covariance matrix approach, and Newton's method. Besides interpreting these methods within a single framework, we explain their specificities and show under which conditions some of them coincide.

📄 PDF Abstract BibTeX arXiv:1810.08102

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Escaping Saddle Points for Zeroth-order Nonconvex Optimization using Estimated Gradient Descent

2019-10-03 · Qinbo Bai, Mridul Agarwal, Vaneet Aggarwal

Gradient descent and its variants are widely used in machine learning. However, oracle access of gradient may not be available in many applications, limiting the direct use of gradient descent. This paper proposes a meth…

BIG-bench Machine Learning

Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates

2019-12-03 · Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik

We present two new remarkably simple stochastic second-order methods for minimizing the average of a very large number of sufficiently smooth and strongly convex functions. The first is a stochastic variant of Newton's m…

Second-order methods

Understanding and Exploiting the Low-Rank Structure of Deep Networks

2018-01-01 · ICLR 2018 1 · Craig Bakker, Michael J. Henry, Nathan O. Hodas

Training methods for deep networks are primarily variants on stochastic gradient descent. Techniques that use (approximate) second-order information are rarely used because of the computational cost and noise associated…

First-order Methods Almost Always Avoid Saddle Points

2017-10-20 · Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz 외

We establish that first-order methods avoid saddle points for almost all initializations. Our results apply to a wide variety of first-order methods, including gradient descent, block coordinate descent, mirror descent a…

Optimization with First-Order Surrogate Functions

2013-05-14 · Julien Mairal

In this paper, we study optimization methods consisting of iteratively minimizing surrogates of an objective function. By proposing several algorithmic variants and simple convergence analyses, we make two main contribut…

BIG-bench Machine Learning