paper-with-me

Papers

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

2017-10-31 · ICLR 2018 1 · Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud

Gradient-based optimization is the foundation of deep learning and reinforcement learning. Even when the mechanism being optimized is unknown or not differentiable, optimization using high-variance or biased gradient estimates is still often the best strategy. We introduce a general framework for learning low-variance, unbiased gradient estimators for black-box functions of random variables. Our method uses gradients of a neural network trained jointly with model parameters or policies, and is applicable in both discrete and continuous settings. We demonstrate this framework for training discrete latent-variable models. We also give an unbiased, action-conditional extension of the advantage actor-critic reinforcement learning algorithm.

📄 PDF Abstract BibTeX arXiv:1711.00123

Code (7)

duvenaud/relax 공식 구현 tf
Bonnevie/rebar tf
ElleryL/gradient_estimator pytorch
TalkToTheGAN/REGAN pytorch
brain-research/mirage-rl tf
thlautenschlaeger/bpttv-lax pytorch
wgrathwohl/BackpropThroughTheVoidRL tf

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

RAPTOR: End-to-end Risk-Aware MDP Planning and Policy Learning by Backpropagation

2021-06-14 · Noah Patton, Jihwan Jeong, Michael Gimelfarb, Scott Sanner

Planning provides a framework for optimizing sequential decisions in complex environments. Recent advances in efficient planning in deterministic or stochastic high-dimensional domains with continuous action spaces lever…

Invariant Representation Learning for Treatment Effect Estimation

2020-11-24 · Claudia Shi, Victor Veitch, David Blei

The defining challenge for causal inference from observational data is the presence of `confounders', covariates that affect both treatment assignment and the outcome. To address this challenge, practitioners collect and…

Causal IdentificationCausal InferenceRepresentation Learningvalid

You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts

2025-05-12 · Hongkun Dou, Zeyu Li, Xingyu Jiang, Hongjue Li 외

Diffusion models (DMs) have recently demonstrated remarkable success in modeling large-scale data distributions. However, many downstream tasks require guiding the generated content based on specific differentiable metri…

Denoising

Probabilistic Model Incorporating Auxiliary Covariates to Control FDR

2022-10-06 · Lin Qiu, Nils Murrugarra-Llerena, Vítor Silva, Lin Lin 외

Controlling False Discovery Rate (FDR) while leveraging the side information of multiple hypothesis testing is an emerging research topic in modern data science. Existing methods rely on the test-level covariates while i…

model

Revisiting Counterfactual Regression through the Lens of Gromov-Wasserstein Information Bottleneck

2024-05-24 · Hao Yang, Zexu Sun, Hongteng Xu, Xu Chen

As a promising individualized treatment effect (ITE) estimation method, counterfactual regression (CFR) maps individuals' covariates to a latent space and predicts their counterfactual outcomes. However, the selection bi…

counterfactualregressionSelection bias