Data Generation as Sequential Decision Making

Abstract

We connect a broad class of generative models through their shared reliance on sequential decision making. Motivated by this view, we develop extensions to an existing model, and then explore the idea further in the context of data imputation -- perhaps the simplest setting in which to investigate the relation between unconditional and conditional generative modelling. We formulate data imputation as an MDP and develop models capable of representing effective policies for it. We construct the models using neural networks and train them using a form of guided policy search. Our models generate predictions through an iterative process of feedback and refinement. We show that this approach can learn effective policies for imputation problems of varying difficulty and across multiple datasets.

Accepted for publication at Advances in Neural Information Processing Systems (NIPS) 2015

References in corpus (2)

• Semi-Supervised Learning with Deep Generative Models
• Variational Inference with Normalizing Flows

Cited by in corpus (16)

• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
• Long Text Generation via Adversarial Training with Leaked Information
• Generating Images from Captions with Attention
• Variational Autoencoder with Arbitrary Conditioning
• Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
• Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
• A Generative Parser with a Discriminative Recognition Algorithm
• Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce
• Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation
• Product Title Refinement via Multi-Modal Generative Adversarial Learning
• Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data
• Testing Visual Attention in Dynamic Environments
• Improving Adversarial Text Generation by Modeling the Distant Future
• Generative Model for Material Experiments Based on Prior Knowledge and Attention Mechanism
• Seq2Seq Mimic Games: A Signaling Perspective