Self-Adversarially Learned Bayesian Sampling

  title={Self-Adversarially Learned Bayesian Sampling},
  author={Yang Zhao and Jianyi Zhang and Changyou Chen},
Scalable Bayesian sampling is playing an important role in modern machine learning, especially in the fast-developed unsupervised-(deep)-learning models. While tremendous progresses have been achieved via scalable Bayesian sampling such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD), the generated samples are typically highly correlated. Moreover, their sample-generation processes are often criticized to be inefficient. In this paper, we propose a novel self… 

Figures and Tables from this paper

Structure-Aware Human-Action Generation

This work proposes a variant of GCNs to leverage the powerful self-attention mechanism to adaptively sparsify a complete action graph in the temporal space, and demonstrates the superiority of this method on two standard human action datasets compared with existing methods.

Temporal Prediction Model of the Evolution of Confirmed Cases of the New Coronavirus (SARS-CoV-2) in Brazil

A model of temporal prediction of the evolution of the number of confirmed cases of the new coronavirus (SARS-CoV-2) in Brazil is presented, based on the analysis of the data source of the The authors' World in Data platform, and showed a good accuracy for short-term forecasts.

3d Human Motion Generation from the Text via Gesture Action Classification and the Autoregressive Model

The proposed deep learning-based model for 3D human motion generation from the text focuses on generating special gestures that express human thinking, such as waving and nodding and successfully generates perceptually natural and realistic 3Dhuman motion from theText.



A-NICE-MC: Adversarial Training for MCMC

A-NICE-MC provides the first framework to automatically design efficient domain-specific Markov Chain Monte Carlo proposals, and is able to significantly outperform competing methods such as Hamiltonian Monte Carlo.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a

Continuous-Time Flows for Deep Generative Models

This paper discretizes the CTF to make training feasible, and develops theory on the approximation error, which is then adopted to distill knowledge from a C TF to an efficient inference network.

Learning to Draw Samples with Amortized Stein Variational Gradient Descent

A simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient direction that maximally decreases the KL divergence with the target distribution.

Continuous-Time Flows for Efficient Inference and Density Estimation

This paper proposes the concept of continuous-time flows (CTFs), a family of diffusion-based methods that are able to asymptotically approach a target distribution and demonstrates promising performance of the proposed CTF framework, compared to related techniques.

A Unified Particle-Optimization Framework for Scalable Bayesian Sampling

This paper proposes a principle particle-optimization framework based on Wasserstein gradient flows to unify SG-MCMC and SVGD, and to allow new algorithms to be developed, demonstrating the effectiveness and efficiency of this framework for scalable Bayesian sampling.

Reinforcement Learning with Deep Energy-Based Policies

A method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before, is proposed and a new algorithm, called soft Q-learning, that expresses the optimal policy via a Boltzmann distribution is applied.

Stein Variational Gradient Descent Without Gradient

A gradient-free variant of SVGD (GF-SVGD), which replaces the true gradient with a surrogate gradient, and corrects the induced bias by re-weighting the gradients in a proper form, and shed insights on the empirical choice of the surrogate gradient.

Bayesian Learning via Stochastic Gradient Langevin Dynamics

In this paper we propose a new framework for learning from large scale datasets based on iterative learning from small mini-batches. By adding the right amount of noise to a standard stochastic

Learning Structural Weight Uncertainty for Sequential Decision-Making

This work proposes efficient posterior learning of structural weight uncertainty, within an SVGD framework, by employing matrix variate Gaussian priors on NN parameters, and investigates the learned structural uncertainty in sequential decision-making problems, including contextual bandits and reinforcement learning.