paper-with-me

Papers

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 framework. The proposed framework takes as input "teacher" and student model architectures and a general posterior expectation of interest. The distillation method performs an online compression of the selected posterior expectation using iteratively generated Monte Carlo samples. We focus on the posterior predictive distribution and expected entropy as distillation targets. We investigate several aspects of this framework including the impact of uncertainty and the choice of student model architecture. We study methods for student model architecture search from a speed-storage-accuracy perspective and evaluate down-stream tasks leveraging entropy distillation including uncertainty ranking and out-of-distribution detection.

📄 PDF Abstract BibTeX arXiv:2005.08110

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Similar Papers 제목 키워드 기반

Latent Bayesian melding for integrating individual and population models

2015-10-30 · NeurIPS 2015 12 · Mingjun Zhong, Nigel Goddard, Charles Sutton

In many statistical problems, a more coarse-grained model may be suitable for population-level behaviour, whereas a more detailed model is appropriate for accurate modelling of individual behaviour. This raises the quest…

blind source separation

Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server

2015-12-31 · Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer 외

This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular v…

Variational Inference

Frequentist Consistency of Variational Bayes

2017-05-09 · Yixin Wang, David M. Blei

A key challenge for modern Bayesian statistics is how to perform scalable inference of posterior distributions. To address this challenge, variational Bayes (VB) methods have emerged as a popular alternative to the class…

Loss-calibrated expectation propagation for approximate Bayesian decision-making

2022-01-10 · Michael J. Morais, Jonathan W. Pillow

Approximate Bayesian inference methods provide a powerful suite of tools for finding approximations to intractable posterior distributions. However, machine learning applications typically involve selecting actions, whic…

Bayesian InferenceDecision Making

Posterior concentration and fast convergence rates for generalized Bayesian learning

2021-11-19 · Lam Si Tung Ho, Binh T. Nguyen, Vu Dinh, Duy Nguyen

In this paper, we study the learning rate of generalized Bayes estimators in a general setting where the hypothesis class can be uncountable and have an irregular shape, the loss function can have heavy tails, and the op…

regression