paper-with-me

Papers

Stabilising priors for robust Bayesian deep learning

2019-10-23 · Felix McGregor, Arnu Pretorius, Johan du Preez, Steve Kroon

Bayesian neural networks (BNNs) have developed into useful tools for probabilistic modelling due to recent advances in variational inference enabling large scale BNNs. However, BNNs remain brittle and hard to train, especially: (1) when using deep architectures consisting of many hidden layers and (2) in situations with large weight variances. We use signal propagation theory to quantify these challenges and propose self-stabilising priors. This is achieved by a reformulation of the ELBO to allow the prior to influence network signal propagation. Then, we develop a stabilising prior, where the distributional parameters of the prior are adjusted before each forward pass to ensure stability of the propagating signal. This stabilised signal propagation leads to improved convergence and robustness making it possible to train deeper networks and in more noisy settings.

📄 PDF Abstract BibTeX arXiv:1910.10386

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningVariational Inference

Similar Papers 제목 키워드 기반

Tipping Cycles

2021-03-22 · Michael Thorne

Ecological systems are studied using many different approaches and mathematical tools. One approach, based on the Jacobian of Lotka-Volterra type models, has been a staple of mathematical ecology for years, leading to ma…

Priors in Bayesian Deep Learning: A Review

2021-05-14 · Vincent Fortuin

While the choice of prior is one of the most critical parts of the Bayesian inference workflow, recent Bayesian deep learning models have often fallen back on vague priors, such as standard Gaussians. In this review, we …

Bayesian InferenceDeep LearningGaussian Processes

Exact marginal prior distributions of finite Bayesian neural networks

2021-04-23 · NeurIPS 2021 12 · Jacob A. Zavatone-Veth, Cengiz Pehlevan

Bayesian neural networks are theoretically well-understood only in the infinite-width limit, where Gaussian priors over network weights yield Gaussian priors over network outputs. Recent work has suggested that finite Ba…

BNNpriors: A library for Bayesian neural network inference with different prior distributions

2021-05-14 · Vincent Fortuin, Adrià Garriga-Alonso, Mark van der Wilk, Laurence Aitchison

Bayesian neural networks have shown great promise in many applications where calibrated uncertainty estimates are crucial and can often also lead to a higher predictive performance. However, it remains challenging to cho…

Osmolyte-Induced Protein Stability Changes Explained by Graph Theory

2023-05-08 · Mattia Miotto, Nina Warner, Giancarlo Ruocco, Gian Gaetano Tartaglia 외

Enhanced stabilisation of protein structures via the presence of inert excipients is a key mechanism adopted both by physiological systems and in biotechnological applications. While the intrinsic stability of proteins i…