paper-with-me

홈 › Papers

ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables

2019-05-04 · Mingzhang Yin, Yuguang Yue, Mingyuan Zhou

To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation, REINFORCE, and Rao-Blackwellization to re-express the gradient as an expectation under the Dirichlet distribution, then uses variable swapping to construct differently expressed but equivalent expectations, and finally shares common random numbers between these expectations to achieve significant variance reduction. Experimental results show ARSM closely resembles the performance of the true gradient for optimization in univariate settings; outperforms existing estimators by a large margin when applied to categorical variational auto-encoders; and provides a "try-and-see self-critic" variance reduction method for discrete-action policy gradient, which removes the need of estimating baselines by generating a random number of pseudo actions and estimating their action-value functions.

📄 PDF Abstract BibTeX arXiv:1905.01413

Code (1)

ARM-gradient/ARSM 공식 구현 tf

Methods 이 논문이 사용한 방법론

REINFORCE REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to…

Similar Papers 제목 키워드 기반

ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary Networks

2018-07-30 · ICLR 2019 5 · Mingzhang Yin, Mingyuan Zhou

To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable a…

Data AugmentationVariational Inference

Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy

2019-03-13 · Yunhao Tang, Mingzhang Yin, Mingyuan Zhou

Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-…

MazeNet: An Accurate, Fast, and Scalable Deep Learning Solution for Steiner Minimum Trees

2024-10-24 · Gabriel Díaz Ramos, Toros Arikan, Richard G. Baraniuk

The Obstacle Avoiding Rectilinear Steiner Minimum Tree (OARSMT) problem, which seeks the shortest interconnection of a given number of terminals in a rectilinear plane while avoiding obstacles, is a critical task in inte…

ARSM Gradient Estimator for Supervised Learning to Rank

2019-11-01 · Siamak Zamani Dadaneh, Shahin Boluki, Mingyuan Zhou, Xiaoning Qian

We propose a new model for supervised learning to rank. In our model, the relevance labels are assumed to follow a categorical distribution whose probabilities are constructed based on a scoring function. We optimize the…

Learning-To-Rank

DisARM: An Antithetic Gradient Estimator for Binary Latent Variables

2020-06-18 · NeurIPS 2020 12 · Zhe Dong, andriy mnih, George Tucker

Training models with discrete latent variables is challenging due to the difficulty of estimating the gradients accurately. Much of the recent progress has been achieved by taking advantage of continuous relaxations of t…