filmov
tv
An Introduction to PAC-Bayes
Показать описание
Speakers: Andrew Foong, David Burt, Javier Antoran
Abstract:
PAC -Bayes is a frequentist framework for obtaining generalisation error bounds. It has been used to derive learning algorithms, provide explanations for generalisation in deep learning, and form connections between Bayesian and frequentist inference. This reading group will cover a broad introduction to PAC bounds, the proof ideas in PAC -Bayes, and a discussion of some recent applications.
Suggested reading:
Abstract:
PAC -Bayes is a frequentist framework for obtaining generalisation error bounds. It has been used to derive learning algorithms, provide explanations for generalisation in deep learning, and form connections between Bayesian and frequentist inference. This reading group will cover a broad introduction to PAC bounds, the proof ideas in PAC -Bayes, and a discussion of some recent applications.
Suggested reading:
1:38:00
An Introduction to PAC-Bayes
2:58:34
MLSS 2021 Taipei- An intro to Statistical Learning Theory and PAC-Bayes Analysis (John Shawe-Taylor)
0:10:12
The PAC-Bayes Guarantee
0:20:09
Part 1: generalization and PAC bayesian learning
0:37:28
AI Excellence Lecture Series 9 - John Shawe Taylor: An Introduction to PAC-Bayesian Analysis
0:31:06
Introduction of PAC-Bayes and its Application for Contrastive Unsupervised Representation Learning
0:31:34
PAC-Bayesian approaches to understanding generalization in deep learning - Gintare Dziugaite
0:55:39
PAC bayes
0:35:02
meta-learning with pac-bayes theory and related background knowledge
0:56:24
François Laviolette - A Tutorial on PAC-Bayesian Theory (Talk)
0:58:06
21 Jan 2021: Benjamin Guedj (UCL) - A primer on PAC-Bayesian learning, and some applications
0:57:14
A primer on PAC-Bayesian learning, and application to deep neural networks
1:33:55
CS 159 (Spring 2021) -- PAC-Bayesian Theory
0:12:09
AISTATS 2023: PAC-Bayesian Learning of Optimization Algorithms
0:44:40
Studying Generalization in Deep Learning via PAC-Bayes
0:03:04
NIPS 2016 spotlight - PAC Bayesian Theory Meets Bayesian Inference
0:58:06
A (condensed) primer on PAC-Bayesian Learning followed by News from the PAC-Bayes frontline
0:20:35
Part 2: PAC bayesian learning for deep learning
0:07:59
PAC-Bayesian Contrastive Unsupervised Representation Learning
1:08:01
A (condensed) primer on PAC-Bayesian learning, followed by News from the PAC-Bayes frontline
0:05:15
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
0:00:54
PAC-Bayes control for grasping
0:01:45
PAC-Bayes control for obstacle avoidance
0:20:25
Towards self-certified learning: Probabilistic neural networks trained by PAC-Bayes with Backprop
Комментарии