paper-with-me

Papers

True Asymptotic Natural Gradient Optimization

2017-12-22 · Yann Ollivier

We introduce a simple algorithm, True Asymptotic Natural Gradient Optimization (TANGO), that converges to a true natural gradient descent in the limit of small learning rates, without explicit Fisher matrix estimation. For quadratic models the algorithm is also an instance of averaged stochastic gradient, where the parameter is a moving average of a "fast", constant-rate gradient descent. TANGO appears as a particular de-linearization of averaged SGD, and is sometimes quite different on non-quadratic models. This further connects averaged SGD and natural gradient, both of which are arguably optimal asymptotically. In large dimension, small learning rates will be required to approximate the natural gradient well. Still, this shows it is possible to get arbitrarily close to exact natural gradient descent with a lightweight algorithm.

📄 PDF Abstract BibTeX arXiv:1712.08449

Code (0)

등록된 구현이 없습니다.

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

AsymptoticNG: A regularized natural gradient optimization algorithm with look-ahead strategy

2020-12-24 · Zedong Tang, Fenlong Jiang, Junke Song, Maoguo Gong 외

Optimizers that further adjust the scale of gradient, such as Adam, Natural Gradient (NG), etc., despite widely concerned and used by the community, are often found poor generalization performance, compared with Stochast…

On the Global Convergence Rates of Softmax Policy Gradient Methods

2020-05-13 · ICML 2020 1 · Jincheng Mei, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans

We make three contributions toward better understanding policy gradient methods in the tabular setting. First, we show that with the true gradient, policy gradient with a softmax parametrization converges at a $O(1/t)$ r…

Open-Ended Question AnsweringPolicy Gradient Methods

HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition

2025-01-01 · CVPR 2025 1 · Zimo Wang, Cheng Wang, Taiki Yoshino, Sirui Tao 외

We propose a method, HotSpot, for optimizing neural signed distance functions. Existing losses, such as the eikonal loss, act as necessary but insufficient constraints and cannot guarantee that the recovered implicit…

Surface Reconstruction

Non-Asymptotic Convergence Analysis of Inexact Gradient Methods for Machine Learning Without Strong Convexity

2013-08-31 · Anthony Man-Cho So

Many recent applications in machine learning and data fitting call for the algorithmic solution of structured smooth convex optimization problems. Although the gradient descent method is a natural choice for this task, i…

BIG-bench Machine Learning

Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference

2023-10-25 · Dai Hai Nguyen, Tetsuya Sakurai, Hiroshi Mamitsuka

Variational inference (VI) can be cast as an optimization problem in which the variational parameters are tuned to closely align a variational distribution with the true posterior. The optimization task can be approached…

Variational Inference