Timezone: »
Markov chain Monte Carlo (MCMC), such as Langevin dynamics, is valid for approximating intractable distributions. However, its usage is limited in the context of deep latent variable models owing to costly datapoint-wise sampling iterations and slow convergence. This paper proposes the amortized Langevin dynamics (ALD), wherein datapoint-wise MCMC iterations are entirely replaced with updates of an encoder that maps observations into latent variables. This amortization enables efficient posterior sampling without datapoint-wise iterations. Despite its efficiency, we prove that ALD is valid as an MCMC algorithm, whose Markov chain has the target posterior as a stationary distribution under mild assumptions. Based on the ALD, we also present a new deep latent variable model named the Langevin autoencoder (LAE). Interestingly, the LAE can be implemented by slightly modifying the traditional autoencoder. Using multiple synthetic datasets, we first validate that ALD can properly obtain samples from target posteriors. We also evaluate the LAE on the image generation task, and show that our LAE can outperform existing methods based on variational inference, such as the variational autoencoder, and other MCMC-based methods in terms of the test likelihood.
Author Information
Shohei Taniguchi (The University of Tokyo)
Yusuke Iwasawa (The University of Tokyo)
Wataru Kumagai (RIKEN)
Yutaka Matsuo (University of Tokyo)
More from the Same Authors
-
2021 Spotlight: Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization »
Yusuke Iwasawa · Yutaka Matsuo -
2021 : Distributional Decision Transformer for Offline Hindsight Information Matching »
Hiroki Furuta · Yutaka Matsuo · Shixiang (Shane) Gu -
2022 : Control Graph as Unified IO for Morphology-Task Generalization »
Hiroki Furuta · Yusuke Iwasawa · Yutaka Matsuo · Shixiang (Shane) Gu -
2022 : Control Graph as Unified IO for Morphology-Task Generalization »
Hiroki Furuta · Yusuke Iwasawa · Yutaka Matsuo · Shixiang (Shane) Gu -
2022 Poster: Large Language Models are Zero-Shot Reasoners »
Takeshi Kojima · Shixiang (Shane) Gu · Machel Reid · Yutaka Matsuo · Yusuke Iwasawa -
2021 Poster: Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning »
Hiroki Furuta · Tadashi Kozuno · Tatsuya Matsushima · Yutaka Matsuo · Shixiang (Shane) Gu -
2021 Poster: Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization »
Yusuke Iwasawa · Yutaka Matsuo -
2017 Poster: Regret Analysis for Continuous Dueling Bandit »
Wataru Kumagai -
2017 Spotlight: Regret Analysis for Continuous Dueling Bandit »
Wataru Kumagai -
2016 Poster: Learning Bound for Parameter Transfer Learning »
Wataru Kumagai