paper-with-me

Papers

Saddle-free Hessian-free Optimization

2015-05-30 · Martin Arjovsky

Nonconvex optimization problems such as the ones in training deep neural networks suffer from a phenomenon called saddle point proliferation. This means that there are a vast number of high error saddle points present in the loss function. Second order methods have been tremendously successful and widely adopted in the convex optimization community, while their usefulness in deep learning remains limited. This is due to two problems: computational complexity and the methods being driven towards the high error saddle points. We introduce a novel algorithm specially designed to solve these two issues, providing a crucial first step to take the widely known advantages of Newton's method to the nonconvex optimization community, especially in high dimensional settings.

📄 PDF Abstract BibTeX arXiv:1506.00059

Code (0)

등록된 구현이 없습니다.

Tasks

Second-order methods

Similar Papers 제목 키워드 기반

Distributed Hessian-Free Optimization for Deep Neural Network

2016-06-02 · Xi He, Dheevatsa Mudigere, Mikhail Smelyanskiy, Martin Takáč

Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. How…

CPUspeech-recognitionSpeech Recognition

Series of Hessian-Vector Products for Tractable Saddle-Free Newton Optimisation of Neural Networks

2023-10-23 · Elre T. Oldewage, Ross M. Clarke, José Miguel Hernández-Lobato

Despite their popularity in the field of continuous optimisation, second-order quasi-Newton methods are challenging to apply in machine learning, as the Hessian matrix is intractably large. This computational burden is e…

Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex Optimization

2020-02-07 · Thomas O'Leary-Roseberry, Nick Alger, Omar Ghattas

In modern deep learning, highly subsampled stochastic approximation (SA) methods are preferred to sample average approximation (SAA) methods because of large data sets as well as generalization properties. Additionally, …

Second-order methods

Hessian-based Analysis of Large Batch Training and Robustness to Adversaries

2018-02-22 · NeurIPS 2018 12 · Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer 외

Large batch size training of Neural Networks has been shown to incur accuracy loss when trained with the current methods. The exact underlying reasons for this are still not completely understood. Here, we study large ba…

Efficient Projection-Free Algorithms for Saddle Point Problems

2020-10-21 · NeurIPS 2020 12 · Cheng Chen, Luo Luo, Weinan Zhang, Yong Yu

The Frank-Wolfe algorithm is a classic method for constrained optimization problems. It has recently been popular in many machine learning applications because its projection-free property leads to more efficient iterati…