Distilling the Posterior in Bayesian Neural Networks

2018-07-01 · ICML 2018 7 · Kuan-Chieh Wang, Paul Vicol, James Lucas, Li Gu, Roger Grosse, Richard Zemel

Bayesian neural networks (BNNs) allow us to reason about uncertainty in a principled way. Stochastic Gradient Langevin Dynamics (SGLD) enables efficient BNN learning by drawing samples from the BNN posterior using mini-batches. However, SGLD and its extensions require storage of many copies of the model parameters, a potentially prohibitive cost, especially for large neural networks. We propose a framework, Adversarial Posterior Distillation, to distill the SGLD samples using a Generative Adversarial Network (GAN). At test-time, samples are generated by the GAN. We show that this distillation framework incurs no loss in performance on recent BNN applications including anomaly detection, active learning, and defense against adversarial attacks. By construction, our framework distills not only the Bayesian predictive distribution, but the posterior itself. This allows one to compute quantities such as the approximate model variance, which is useful in downstream tasks. To our knowledge, these are the first results applying MCMC-based BNNs to the aforementioned applications.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning Anomaly DetectionGenerative Adversarial Network

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networks

2020-05-16 · Meet P. Vadera, Brian Jalaian, Benjamin M. Marlin

In this paper, we present a general framework for distilling expectations with respect to the Bayesian posterior distribution of a deep neural network classifier, extending prior work on the Bayesian Dark Knowledge frame…

Out-of-Distribution Detection

Model-based Lifelong Reinforcement Learning with Bayesian Exploration

2022-10-20 · Haotian Fu, Shangqun Yu, Michael Littman, George Konidaris

We propose a model-based lifelong reinforcement-learning approach that estimates a hierarchical Bayesian posterior distilling the common structure shared across different tasks. The learned posterior combined with a samp…

model reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Distilling Bayesian Belief States into Language Models for Auditable Negotiation

2026-05-06 · Zongqi Cui, Baihan Lin arxiv

Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end large language models (LLMs) can imitate negotiation dialogue, but t…

Decision Making

Bayesian Dark Knowledge

2015-06-14 · NeurIPS 2015 12 · Anoop Korattikara, Vivek Rathod, Kevin Murphy, Max Welling

We consider the problem of Bayesian parameter estimation for deep neural networks, which is important in problem settings where we may have little data, and/ or where we need accurate posterior predictive densities, e.g.…

Active Learning parameter estimation

If there is no underfitting, there is no Cold Posterior Effect

2023-10-02 · Yijie Zhang, Yi-Shan Wu, Luis A. Ortega, Andrés R. Masegosa

The cold posterior effect (CPE) (Wenzel et al., 2020) in Bayesian deep learning shows that, for posteriors with a temperature $T<1$, the resulting posterior predictive could have better performances than the Bayesian pos…