paper-with-me

Papers

A PAC-Bayesian Tutorial with A Dropout Bound

2013-07-08 · David McAllester

This tutorial gives a concise overview of existing PAC-Bayesian theory focusing on three generalization bounds. The first is an Occam bound which handles rules with finite precision parameters and which states that generalization loss is near training loss when the number of bits needed to write the rule is small compared to the sample size. The second is a PAC-Bayesian bound providing a generalization guarantee for posterior distributions rather than for individual rules. The PAC-Bayesian bound naturally handles infinite precision rule parameters, $L_2$ regularization, {\em provides a bound for dropout training}, and defines a natural notion of a single distinguished PAC-Bayesian posterior distribution. The third bound is a training-variance bound --- a kind of bias-variance analysis but with bias replaced by expected training loss. The training-variance bound dominates the other bounds but is more difficult to interpret. It seems to suggest variance reduction methods such as bagging and may ultimately provide a more meaningful analysis of dropouts.

📄 PDF Abstract BibTeX arXiv:1307.2118

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization Bounds

Similar Papers 제목 키워드 기반

Variational Dropout via Empirical Bayes

2018-11-01 · Valery Kharitonov, Dmitry Molchanov, Dmitry Vetrov

We study the Automatic Relevance Determination procedure applied to deep neural networks. We show that ARD applied to Bayesian DNNs with Gaussian approximate posterior distributions leads to a variational bound similar t…

PAC-Bayes Mini-tutorial: A Continuous Union Bound

2014-05-07 · Tim van Erven

When I first encountered PAC-Bayesian concentration inequalities they seemed to me to be rather disconnected from good old-fashioned results like Hoeffding's and Bernstein's inequalities. But, at least for one flavour of…

BIG-bench Machine LearningRelation

Tutorial: Deriving the Standard Variational Autoencoder (VAE) Loss Function

2019-07-21 · Stephen Odaibo

In Bayesian machine learning, the posterior distribution is typically computationally intractable, hence variational inference is often required. In this approach, an evidence lower bound on the log likelihood of data is…

Variational Inference

Variational Dropout Sparsifies Deep Neural Networks

2017-01-19 · ICML 2017 8 · Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov

We explore a recently proposed Variational Dropout technique that provided an elegant Bayesian interpretation to Gaussian Dropout. We extend Variational Dropout to the case when dropout rates are unbounded, propose a way…

Sparse Learning

High Dimensional Bayesian Optimization Using Dropout

2018-02-15 · Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen 외

Scaling Bayesian optimization to high dimensions is challenging task as the global optimization of high-dimensional acquisition function can be expensive and often infeasible. Existing methods depend either on limited ac…

Bayesian Optimizationglobal-optimizationVocal Bursts Intensity Prediction