paper-with-me

Papers

Gradient Estimation with Stochastic Softmax Tricks

2020-06-15 · NeurIPS 2020 12 · Max B. Paulus, Dami Choi, Daniel Tarlow, Andreas Krause, Chris J. Maddison

The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to large combinatorial distributions is still outstanding. Working within the perturbation model framework, we introduce stochastic softmax tricks, which generalize the Gumbel-Softmax trick to combinatorial spaces. Our framework is a unified perspective on existing relaxed estimators for perturbation models, and it contains many novel relaxations. We design structured relaxations for subset selection, spanning trees, arborescences, and others. When compared to less structured baselines, we find that stochastic softmax tricks can be used to train latent variable models that perform better and discover more latent structure.

📄 PDF Abstract BibTeX arXiv:2006.08063

Code (1)

choidami/sst 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Efficient Learning of Discrete-Continuous Computation Graphs

2023-07-26 · NeurIPS 2021 12 · David Friede, Mathias Niepert

Numerous models for supervised and reinforcement learning benefit from combinations of discrete and continuous model components. End-to-end learnable discrete-continuous models are compositional, tend to generalize bette…

Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables

2020-03-04 · Weonyoung Joo, Dongjun Kim, Seungjae Shin, Il-Chul Moon

Estimating the gradients of stochastic nodes in stochastic computational graphs is one of the crucial research questions in the deep generative modeling community, which enables the gradient descent optimization on neura…

Topic Models

On Uniform Scalar Quantization for Learned Image Compression

2023-09-29 · Haotian Zhang, Li Li, Dong Liu

Learned image compression possesses a unique challenge when incorporating non-differentiable quantization into the gradient-based training of the networks. Several quantization surrogates have been proposed to fulfill th…

Image CompressionQuantization

Low Bias Low Variance Gradient Estimates for Hierarchical Boolean Stochastic Networks

2020-01-01 · ICML 2020 1 · Adeel Pervez, Taco Cohen, Efstratios Gavves

Stochastic neural networks with discrete random variables are an important class of models for their expressiveness and interpretability. Since direct differentiation and backpropagation is not possible, Monte Carlo grad…

Softmax Deep Double Deterministic Policy Gradients

2020-10-19 · NeurIPS 2020 12 · Ling Pan, Qingpeng Cai, Longbo Huang

A widely-used actor-critic reinforcement learning algorithm for continuous control, Deep Deterministic Policy Gradients (DDPG), suffers from the overestimation problem, which can negatively affect the performance. Althou…

continuous-controlContinuous Control