AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation
Jul 12, 2020
Sprecher:innen
Jae Hyun Lim
Sprecher:in · 0 Follower:innen
Aaron Courville
Sprecher:in · 3 Follower:innen
Christopher Pal
Sprecher:in · 0 Follower:innen
Chin-Wei Huang
Sprecher:in · 0 Follower:innen
Über
Entropy is ubiquitous in machine learning, but it is in general intractable to compute the entropy of the distribution of an arbitrary continuous random variable. In this paper, we propose the amortized residual denoising autoencoder (AR-DAE) to approximate the gradient of the log density function, which can be used to estimate the gradient of entropy. Amortization allows us to significantly reduce the error of the gradient approximator by approaching asymptotic optimality of a regular DAE, in which case the estimation is in theory unbiased. We conduct theoretical and experimental analyses on the approximation error of the proposed method, which includes extensive studies on heuristics to ensure its robustness. Finally, using the proposed gradient approximator to estimate the gradient of entropy, we demonstrate state-of-the-art performance on density estimation with variational autoencoders, and show that our approach can provide reliable exploration signals in the context of reinforcement learning.Entropy is ubiquitous in machine learning, but it is in general intractable to compute the entropy of the distribution of an arbitrary continuous random variable. In this paper, we propose the amortized residual denoising autoencoder (AR-DAE) to approximate the gradient of the log density function, which can be used to estimate the gradient of entropy. Amortization allows us to significantly reduce the error of the gradient approximator by approaching asymptotic optimality of a regular DAE, in w…
Kategorien
KI und Datenwissenschaft
Kategorie · 10,8k Präsentationen
Über ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Gradient Based Memory Editing for Task-Free Continual Learning
Später ansehen
Xisen Jin, …
Graph Clustering with Graph Neural Networks
Später ansehen
Evaluating Logical Generalization in Graph Neural Networks
Später ansehen
Retrospective on DeepIV and some general thoughts on research strategy
Später ansehen
Learning Factorized Weight Matrix for Joint Image Filtering
Später ansehen
Xiangyu Xu, …
