Backpropagation through the Void: Optimizing control variates for black-box gradient estimation

31 October 2017

Papers citing "Backpropagation through the Void: Optimizing control variates for black-box gradient estimation"

50 / 204 papers shown

Title
Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity Gonçalo M. Correia Vlad Niculae Wilker Aziz André F. T. Martins BDL 30 22 0 03 Jul 2020
Semi-supervised Sequential Generative Models Michael Teng T. Le Adam Scibior Frank Wood BDL AI4TS 25 3 0 30 Jun 2020
Lattice Representation Learning Luis Lastras 19 1 0 24 Jun 2020
DisARM: An Antithetic Gradient Estimator for Binary Latent Variables Zhe Dong A. Mnih George Tucker DRL 16 32 0 18 Jun 2020
GO Hessian for Expectation-Based Objectives Yulai Cong Miaoyun Zhao Jianqiao Li Junya Chen Lawrence Carin 17 0 0 16 Jun 2020
Generative Semantic Hashing Enhanced via Boltzmann Machines Lin Zheng Qinliang Su Dinghan Shen Changyou Chen 12 6 0 16 Jun 2020
Gradient Estimation with Stochastic Softmax Tricks Max B. Paulus Dami Choi Daniel Tarlow Andreas Krause Chris J. Maddison BDL 36 85 0 15 Jun 2020
Scalable Control Variates for Monte Carlo Methods via Stochastic Optimization Shijing Si Chris J. Oates Andrew B. Duncan Lawrence Carin F. Briol BDL 23 21 0 12 Jun 2020
Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks Alexander Shekhovtsov Dmitry Molchanov MQ 17 15 0 11 Jun 2020
Latent Transformations for Discrete-Data Normalising Flows Rob D. Hesselink Wilker Aziz DRL 21 1 0 11 Jun 2020
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks Alexander Shekhovtsov V. Yanush B. Flach MQ 37 10 0 04 Jun 2020
Neural Control Variates Thomas Müller Fabrice Rousselle Jan Novák A. Keller BDL 10 54 0 02 Jun 2020
Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models Zhijian Ou Yunfu Song BDL 32 8 0 28 May 2020
In search of isoglosses: continuous and discrete language embeddings in Slavic historical phonology C. Cathcart Florian Wandl 6 6 0 27 May 2020
Deep Learning for Wireless Communications T. Erpek Tim O'Shea Y. Sagduyu Yi Shi T. Clancy 34 134 0 12 May 2020
Neural Conditional Event Time Models Matthew M. Engelhard S. Berchuck Joshua DÁrcy Ricardo Henao 16 3 0 03 Apr 2020
Amortized variance reduction for doubly stochastic objectives Ayman Boustati Sattar Vakili J. Hensman S. T. John 26 5 0 09 Mar 2020
DADA: Differentiable Automatic Data Augmentation Yonggang Li Guosheng Hu Yongtao Wang Timothy M. Hospedales N. Robertson Yongxin Yang 18 107 0 08 Mar 2020
Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables Weonyoung Joo Dongjun Kim Seung-Jae Shin Il-Chul Moon 21 1 0 04 Mar 2020
Estimating Gradients for Discrete Random Variables by Sampling without Replacement W. Kool H. V. Hoof Max Welling BDL 31 49 0 14 Feb 2020
Learnable Bernoulli Dropout for Bayesian Deep Learning Shahin Boluki Randy Ardywibowo Siamak Zamani Dadaneh Mingyuan Zhou Xiaoning Qian BDL 12 34 0 12 Feb 2020
Black-Box Optimization with Local Generative Surrogates S. Shirobokov V. Belavin Michael Kagan Andrey Ustyuzhanin A. G. Baydin 8 3 0 11 Feb 2020
Discrete Action On-Policy Learning with Action-Value Critic Yuguang Yue Yunhao Tang Mingzhang Yin Mingyuan Yin OffRL 6 5 0 10 Feb 2020
Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation Xinjie Fan Yizhe Zhang Zhendong Wang Mingyuan Zhou BDL 9 4 0 31 Dec 2019
Hierarchical Variational Imitation Learning of Control Programs Roy Fox Richard Shin William Paul Yitian Zou D. Song Ken Goldberg Pieter Abbeel Ion Stoica BDL 8 4 0 29 Dec 2019
Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax Andres Potapczynski G. Loaiza-Ganem John P. Cunningham 32 29 0 19 Dec 2019
UNAS: Differentiable Architecture Search Meets Reinforcement Learning Arash Vahdat Arun Mallya Ming Liu Jan Kautz 30 33 0 16 Dec 2019
Learning with Multiplicative Perturbations Xiulong Yang Shihao Ji AAML 30 4 0 04 Dec 2019
Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution Artyom Gadetsky Kirill Struminsky Christopher Robinson Novi Quadrianto Dmitry Vetrov 8 11 0 22 Nov 2019
A Rule for Gradient Estimator Selection, with an Application to Variational Inference Tomas Geffner Justin Domke 48 6 0 05 Nov 2019
Amortized Population Gibbs Samplers with Neural Sufficient Statistics Hao Wu Heiko Zimmermann Eli Sennesh T. Le Jan-Willem van de Meent 25 7 0 04 Nov 2019
ARSM Gradient Estimator for Supervised Learning to Rank Siamak Zamani Dadaneh Shahin Boluki Mingyuan Zhou Xiaoning Qian 25 7 0 01 Nov 2019
From Importance Sampling to Doubly Robust Policy Gradient Jiawei Huang Nan Jiang OffRL 27 24 0 20 Oct 2019
A unified view of likelihood ratio and reparameterization gradients and an optimal importance sampling scheme Paavo Parmas Masashi Sugiyama 14 3 0 14 Oct 2019
Straight-Through Estimator as Projected Wasserstein Gradient Flow Pengyu Cheng YooJung Choi Yitao Liang Dinghan Shen Ricardo Henao Mathias Niepert 24 14 0 05 Oct 2019
Intensity-Free Learning of Temporal Point Processes Oleksandr Shchur Marin Bilos Stephan Günnemann AI4TS 27 167 0 26 Sep 2019
Select and Attend: Towards Controllable Content Selection in Text Generation Xiaoyu Shen Jun Suzuki Kentaro Inui Hui Su Dietrich Klakow Satoshi Sekine 29 28 0 10 Sep 2019
Neural Image Compression and Explanation Xiang Li Shihao Ji 10 10 0 09 Aug 2019
Probabilistic Models with Deep Neural Networks A. Masegosa Rafael Cabañas H. Langseth Thomas D. Nielsen Antonio Salmerón BDL 14 12 0 09 Aug 2019
Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods Ching-An Cheng Xinyan Yan Byron Boots 22 22 0 08 Aug 2019
Cooperative image captioning Gilad Vered Gal Oren Y. Atzmon Gal Chechik 31 2 0 26 Jul 2019
The Thermodynamic Variational Objective Vaden Masrani T. Le Frank Wood 19 48 0 28 Jun 2019
Policy Optimization with Stochastic Mirror Descent Long Yang Yu Zhang Gang Zheng Qian Zheng Pengfei Li Jianhang Huang Jun Wen Gang Pan 31 34 0 25 Jun 2019
Amortized Bethe Free Energy Minimization for Learning MRFs Sam Wiseman Yoon Kim TPM DRL 13 11 0 14 Jun 2019
Reinforcement Learning When All Actions are Not Always Available Yash Chandak Georgios Theocharous Blossom Metevier Philip S. Thomas 13 7 0 05 Jun 2019
Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling A. Bose Andre Cianflone William L. Hamilton OOD AAML 19 7 0 26 May 2019
Survival Function Matching for Calibrated Time-to-Event Predictions Paidamoyo Chapfuwa Chenyang Tao Lawrence Carin Ricardo Henao OOD 11 4 0 21 May 2019
Improving Discrete Latent Representations With Differentiable Approximation Bridges Jason Ramapuram Russ Webb DRL 19 9 0 09 May 2019
Smoothing Policies and Safe Policy Gradients Matteo Papini Matteo Pirotta Marcello Restelli 24 29 0 08 May 2019
ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables Mingzhang Yin Yuguang Yue Mingyuan Zhou 14 23 0 04 May 2019