Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis
Optimization algorithms that leverage gradient covariance information, such as variants of natural gradient descent (Amari, 1998), offer the prospect of yielding more effective descent directions. For models with many parameters, the covari- ance matrix they are based on becomes gigantic, making them inapplicable in their original form. This has motivated research into both simple diagonal approxima- tions and more sophisticated factored approximations such as KFAC (Heskes, 2000; Martens & Grosse, 2015; Grosse & Martens, 2016). In the present work we draw inspiration from both to propose a novel approximation that is provably better than KFAC and amendable to cheap partial updates. It consists in tracking a diagonal variance, not in parameter coordinates, but in a Kronecker-factored eigenbasis, in which the diagonal approximation is likely to be more effective. Experiments show improvements over KFAC in optimization speed for several deep network architectures.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Kronecker-factored approximate Fisher matrix for convolution layers
Second-order optimization methods such as natural gradient descent have the potential to speed up training of neural networks by correcting for the curvature of the loss function. Unfortunately, the exact natural gradien…
Stochastic OptimizationOptimizing Neural Networks with Kronecker-factored Approximate Curvature
We propose an efficient method for approximating natural gradient descent in neural networks which we call Kronecker-Factored Approximate Curvature (K-FAC). K-FAC is based on an efficiently invertible approximation of a …
Stochastic OptimizationFast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis
Optimization algorithms that leverage gradient covariance information, such as variants of natural gradient descent (Amari, 1998), offer the prospect of yielding more effective descent directions. For models with many pa…
SKFAC:Training Neural Networks with Faster Kronecker-Factored Approximate Curvature
The bottleneck of computation burden limits the widespread use of the 2nd order optimization algorithms for training deep neural networks. In this paper, we present a computationally efficient approximation for natural g…
Dimensionality ReductionSKFAC: Training Neural Networks With Faster Kronecker-Factored Approximate Curvature
The bottleneck of computation burden limits the widespread use of the 2nd order optimization algorithms for training deep neural networks. In this paper, we present a computationally efficient approximation for natur…
Dimensionality Reduction