Roundtrip: A Deep Generative Neural Density Estimator

Abstract

Density estimation is a fundamental problem in both statistics and machine learning. In this study, we proposed Roundtrip as a general-purpose neural density estimator based on deep generative models. Roundtrip retains the generative power of generative adversarial networks (GANs) but also provides estimates of density values. Unlike previous neural density estimators that put stringent conditions on the transformation from the latent space to the data space, Roundtrip enables the use of much more general mappings. In a series of experiments, Roundtrip achieves state-of-the-art performance in a diverse range of density estimation tasks.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• TensorFlow: A system for large-scale machine learning
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Variational Inference with Normalizing Flows
• Density estimation using Real NVP
• MADE: Masked Autoencoder for Distribution Estimation
• Density Modeling of Images using a Generalized Normalization Transformation
• Adversarial Autoencoders
• Parameterized Machine Learning for High-Energy Physics
• Masked Autoregressive Flow for Density Estimation
• Sylvester Normalizing Flows for Variational Inference
• Roundtrip: A Deep Generative Neural Density Estimator
• Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models

Cited by in corpus (10)

• Roundtrip: A Deep Generative Neural Density Estimator
• Flow-matching -- efficient coarse-graining of molecular dynamics without forces
• Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning
• Cryo-shift: Reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization
• Causal, Bayesian, & Non-parametric Modeling of the SARS-CoV-2 Viral Load Distribution vs. Patient's Age
• Fast and Flexible Analysis of Direct Dark Matter Search Data with Machine Learning
• Generative learning for the problem of critical slowing down in lattice Gross Neveu model
• Neural Network Predicts Ion Concentration Profiles under Nanoconfinement
• Efficient Multimodal Sampling via Tempered Distribution Flow
• Density Estimation via Binless Multidimensional Integration