paper-with-me

Papers

Overpruning in Variational Bayesian Neural Networks

2018-01-18 · Brian Trippe, Richard Turner

The motivations for using variational inference (VI) in neural networks differ significantly from those in latent variable models. This has a counter-intuitive consequence; more expressive variational approximations can provide significantly worse predictions as compared to those with less expressive families. In this work we make two contributions. First, we identify a cause of this performance gap, variational over-pruning. Second, we introduce a theoretically grounded explanation for this phenomenon. Our perspective sheds light on several related published results and provides intuition into the design of effective variational approximations of neural networks.

📄 PDF Abstract BibTeX arXiv:1801.06230

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Similar Papers 제목 키워드 기반

Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo

2017-08-01 · ICML 2017 8 · Matthew D. Hoffman

Deep latent Gaussian models are powerful and popular probabilistic models of high-dimensional data. These models are almost always fit using variational expectation-maximization, an approximation to true maximum-mar…

Sparsity in Variational Autoencoders

2018-12-18 · Andrea Asperti

Working in high-dimensional latent spaces, the internal encoding of data in Variational Autoencoders becomes naturally sparse. We discuss this known but controversial phenomenon sometimes refereed to as overpruning, to e…

Generalized Variational Continual Learning

2020-11-24 · ICLR 2021 1 · Noel Loo, Siddharth Swaroop, Richard E. Turner

Continual learning deals with training models on new tasks and datasets in an online fashion. One strand of research has used probabilistic regularization for continual learning, with two of the main approaches in this v…

Continual LearningVariational Inference

BayesPy: Variational Bayesian Inference in Python

2014-10-03 · Jaakko Luttinen

BayesPy is an open-source Python software package for performing variational Bayesian inference. It is based on the variational message passing framework and supports conjugate exponential family models. By removing the …

Bayesian InferenceVariational Inference

Variational Bayesian Last Layers

2024-04-17 · James Harrison, John Willes, Jasper Snoek

We introduce a deterministic variational formulation for training Bayesian last layer neural networks. This yields a sampling-free, single-pass model and loss that effectively improves uncertainty estimation. Our variati…

Out-of-Distribution DetectionVariational Inference