paper-with-me

홈 › Papers

One Simple Trick to Fix Your Bayesian Neural Network

2022-07-26 · Piotr Tempczyk, Ksawery Smoczyński, Philip Smolenski-Jensen, Marek Cygan

One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activation function induce posteriors, that are hard to fit with MFVI. We provide a theoretical justification for this phenomenon, study it empirically, and report the results of a series of experiments to investigate the effect of activation function on the calibration of BNNs. We find that using Leaky ReLU activations leads to more Gaussian-like weight posteriors and achieves a lower expected calibration error (ECE) than its ReLU-based counterpart.

📄 PDF Abstract BibTeX arXiv:2207.13167

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…

Similar Papers 제목 키워드 기반

ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep Reinforcement Learning

2021-02-15 · Naichen Shi, Ruichen Li, Sun Youran

People have made remarkable progress in game AIs, especially in domain of perfect information game. However, trick-taking poker game, as a popular form of imperfect information game, has been regarded as a challenge for …

Bayesian InferenceDeep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian Optimization

2026-08-18 · Travis Zhang, Christian Belardi, Justin Lovelace, Jin Peng Zhou 외 arxiv

Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparati…

Text-to-Image Generation

Bayesian statistical learning using density operators

2022-12-28 · Yann Berquin

This short study reformulates the statistical Bayesian learning problem using a quantum mechanics framework. Density operators representing ensembles of pure states of sample wave functions are used in place probability …

A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation

2023-04-11 · Florian Bordes, Samuel Lavoie, Randall Balestriero, Nicolas Ballas 외

Self-Supervised Learning (SSL) models rely on a pretext task to learn representations. Because this pretext task differs from the downstream tasks used to evaluate the performance of these models, there is an inherent mi…

Self-Supervised Learning

All your loss are belong to Bayes

2020-06-08 · NeurIPS 2020 12 · Christian Walder, Richard Nock

Loss functions are a cornerstone of machine learning and the starting point of most algorithms. Statistics and Bayesian decision theory have contributed, via properness, to elicit over the past decades a wide set of admi…

AllGaussian Processes