Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Energy-Inspired Models: Learning with Sampler-Induced Distributions

Oct 31, 2019
Dieterich Lawson, George Tucker, Bo Dai, Rajesh Ranganath


  Access Paper or Ask Questions

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives

Oct 09, 2018
George Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison


  Access Paper or Ask Questions

Filtering Variational Objectives

Nov 12, 2017
Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Mohammad Norouzi, Andriy Mnih, Arnaud Doucet, Yee Whye Teh


  Access Paper or Ask Questions

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

Nov 06, 2017
George Tucker, Andriy Mnih, Chris J. Maddison, Dieterich Lawson, Jascha Sohl-Dickstein

* NIPS 2017 

  Access Paper or Ask Questions

Learning Hard Alignments with Variational Inference

Nov 01, 2017
Dieterich Lawson, Chung-Cheng Chiu, George Tucker, Colin Raffel, Kevin Swersky, Navdeep Jaitly


  Access Paper or Ask Questions

An online sequence-to-sequence model for noisy speech recognition

Jun 16, 2017
Chung-Cheng Chiu, Dieterich Lawson, Yuping Luo, George Tucker, Kevin Swersky, Ilya Sutskever, Navdeep Jaitly

* arXiv admin note: substantial text overlap with arXiv:1608.01281 

  Access Paper or Ask Questions

Training a Subsampling Mechanism in Expectation

Apr 08, 2017
Colin Raffel, Dieterich Lawson

* Camera-ready version. Includes additional figures in an appendix 

  Access Paper or Ask Questions

Particle Value Functions

Mar 16, 2017
Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh


  Access Paper or Ask Questions

Changing Model Behavior at Test-Time Using Reinforcement Learning

Feb 24, 2017
Augustus Odena, Dieterich Lawson, Christopher Olah

* Submitted to ICLR 2017 Workshop Track 

  Access Paper or Ask Questions