paper-with-me

Papers

GO Gradient for Expectation-Based Objectives

2019-01-17 · ICLR 2019 5 · Yulai Cong, Miaoyun Zhao, Ke Bai, Lawrence Carin

Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Ebb_{q_{\gammav} (\yv)} [f(\yv)]$. Most existing methods either (i) suffer from high variance, seeking help from (often) complicated variance-reduction techniques; or (ii) they only apply to reparameterizable continuous random variables and employ a reparameterization trick. To address these limitations, we propose a General and One-sample (GO) gradient that (i) applies to many distributions associated with non-reparameterizable continuous or discrete random variables, and (ii) has the same low-variance as the reparameterization trick. We find that the GO gradient often works well in practice based on only one Monte Carlo sample (although one can of course use more samples if desired). Alongside the GO gradient, we develop a means of propagating the chain rule through distributions, yielding statistical back-propagation, coupling neural networks to common random variables.

📄 PDF Abstract BibTeX arXiv:1901.06020

Code (1)

YulaiCong/GOgradient 공식 구현 tf

Similar Papers 제목 키워드 기반

Stochastic Weakly Convex Optimization Under Heavy-Tailed Noises

2025-07-17 · Tianxi Zhu, Yi Xu, Xiangyang Ji

An increasing number of studies have focused on stochastic first-order methods (SFOMs) under heavy-tailed gradient noises, which have been observed in the training of practical deep learning models. In this paper, we foc…

GO Hessian for Expectation-Based Objectives

2020-06-16 · Yulai Cong, Miaoyun Zhao, Jianqiao Li, Junya Chen 외

An unbiased low-variance gradient estimator, termed GO gradient, was proposed recently for expectation-based objectives $\mathbb{E}_{q_{\boldsymbol{\gamma}}(\boldsymbol{y})} [f(\boldsymbol{y})]$, where the random variabl…

Ranking via Sinkhorn Propagation

2011-06-09 · Ryan Prescott Adams, Richard S. Zemel

It is of increasing importance to develop learning methods for ranking. In contrast to many learning objectives, however, the ranking problem presents difficulties due to the fact that the space of permutations is not sm…

Information RetrievalRetrieval

Stochastic Primal-Dual Proximal ExtraGradient Descent for Compositely Regularized Optimization

2017-08-20 · Tianyi Lin, Linbo Qiao, Teng Zhang, Jiashi Feng 외

We consider a wide range of regularized stochastic minimization problems with two regularization terms, one of which is composed with a linear function. This optimization model abstracts a number of important application…

regression

AlgaeDICE: Policy Gradient from Arbitrary Experience

2019-12-04 · Ofir Nachum, Bo Dai, Ilya Kostrikov, Yin-Lam Chow 외

In many real-world applications of reinforcement learning (RL), interactions with the environment are limited due to cost or feasibility. This presents a challenge to traditional RL algorithms since the max-return object…

Reinforcement LearningReinforcement Learning (RL)