Mutual Information Constraints for Monte-Carlo Objectives

• URL: http://arxiv.org/abs/2012.00708v1
• Date: Tue, 1 Dec 2020 18:14:08 GMT
• Title: Mutual Information Constraints for Monte-Carlo Objectives
• Authors: G\'abor Melis, Andr\'as Gy\"orgy, Phil Blunsom
• Abstract summary: A common failure mode of density models trained as variational autoencoders is to model the data without relying on their latent variables, rendering these variables useless. We weave these two strands of research together, specifically the tighter bounds of Monte-Carlo objectives and constraints on the mutual information between the observable and the latent variables. We construct estimators of the Kullback-Leibler divergence of the true posterior from the prior by recycling samples used in the objective, with which we train models of continuous and discrete latents at much improved rate-distortion and no posterior collapse.
• Score: 21.70557526001205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A common failure mode of density models trained as variational autoencoders is to model the data without relying on their latent variables, rendering these variables useless. Two contributing factors, the underspecification of the model and the looseness of the variational lower bound, have been studied separately in the literature. We weave these two strands of research together, specifically the tighter bounds of Monte-Carlo objectives and constraints on the mutual information between the observable and the latent variables. Estimating the mutual information as the average Kullback-Leibler divergence between the easily available variational posterior $q(z|x)$ and the prior does not work with Monte-Carlo objectives because $q(z|x)$ is no longer a direct approximation to the model's true posterior $p(z|x)$. Hence, we construct estimators of the Kullback-Leibler divergence of the true posterior from the prior by recycling samples used in the objective, with which we train models of continuous and discrete latents at much improved rate-distortion and no posterior collapse. While alleviated, the tradeoff between modelling the data and using the latents still remains, and we urge for evaluating inference methods across a range of mutual information values.

Related papers

• Amortizing intractable inference in diffusion models for vision, language, and control [89.65631572949702]
  This paper studies amortized sampling of the posterior over data, $mathbfxsim prm post(mathbfx)propto p(mathbfx)r(mathbfx)$, in a model that consists of a diffusion generative model prior $p(mathbfx)$ and a black-box constraint or function $r(mathbfx)$. We prove the correctness of a data-free learning objective, relative trajectory balance, for training a diffusion model that samples from
  arXiv  Detail & Related papers  (2024-05-31T16:18:46Z)
• Forward $\chi^2$ Divergence Based Variational Importance Sampling [2.841087763205822]
  We introduce a novel variational importance sampling (VIS) approach that directly estimates and maximizes the log-likelihood. We apply VIS to various popular latent variable models, including mixture models, variational auto-encoders, and partially observable generalized linear models.
  arXiv  Detail & Related papers  (2023-11-04T21:46:28Z)
• Variational Laplace Autoencoders [53.08170674326728]
  Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. We present a novel approach that addresses the limited posterior expressiveness of fully-factorized Gaussian assumption. We also present a general framework named Variational Laplace Autoencoders (VLAEs) for training deep generative models.
  arXiv  Detail & Related papers  (2022-11-30T18:59:27Z)
• Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization [41.774837419584735]
  offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy. Model-based approaches are particularly appealing since they can extract more learning signals from the logged dataset by learning a model of the environment.
  arXiv  Detail & Related papers  (2022-10-07T20:13:50Z)
• On the detrimental effect of invariances in the likelihood for variational inference [21.912271882110986]
  Variational Bayesian posterior inference often requires simplifying approximations such as mean-field parametrisation to ensure tractability. Prior work has associated the variational mean-field approximation for Bayesian neural networks with underfitting in the case of small datasets or large model sizes.
  arXiv  Detail & Related papers  (2022-09-15T09:13:30Z)
• Scalable Semi-Modular Inference with Variational Meta-Posteriors [0.0]
  The Cut posterior and Semi-Modular Inference are Generalised Bayes methods for Modular Bayesian evidence combination. We show that analysis of models with multiple cuts is feasible using a new Variational Meta-Posterior. This approximates a family of SMI posteriors indexed by $eta$ using a single set of variational parameters.
  arXiv  Detail & Related papers  (2022-04-01T09:01:20Z)
• Model-Augmented Q-learning [112.86795579978802]
  We propose a MFRL framework that is augmented with the components of model-based RL. Specifically, we propose to estimate not only the $Q$-values but also both the transition and the reward with a shared network. We show that the proposed scheme, called Model-augmented $Q$-learning (MQL), obtains a policy-invariant solution which is identical to the solution obtained by learning with true reward.
  arXiv  Detail & Related papers  (2021-02-07T17:56:50Z)
• Generative Temporal Difference Learning for Infinite-Horizon Prediction [101.59882753763888]
  We introduce the $gamma$-model, a predictive model of environment dynamics with an infinite probabilistic horizon. We discuss how its training reflects an inescapable tradeoff between training-time and testing-time compounding errors.
  arXiv  Detail & Related papers  (2020-10-27T17:54:12Z)
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling [54.94763543386523]
  Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the ( aggregate) posterior to encourage statistical independence of the latent factors. We present a novel multi-stage modeling approach where the disentangled factors are first learned using a penalty-based disentangled representation learning method. Then, the low-quality reconstruction is improved with another deep generative model that is trained to model the missing correlated latent variables.
  arXiv  Detail & Related papers  (2020-10-25T18:51:15Z)
• Meta-Learning with Shared Amortized Variational Inference [33.54630534228469]
  We propose a novel amortized variational inference scheme for an empirical Bayes meta-learning model. We learn the prior distribution over model parameters conditioned on limited training data using a variational autoencoder approach.
  arXiv  Detail & Related papers  (2020-08-27T10:28:13Z)
• Accounting for Unobserved Confounding in Domain Generalization [107.0464488046289]
  This paper investigates the problem of learning robust, generalizable prediction models from a combination of datasets. Part of the challenge of learning robust models lies in the influence of unobserved confounders. We demonstrate the empirical performance of our approach on healthcare data from different modalities.
  arXiv  Detail & Related papers  (2020-07-21T08:18:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.