Stephan Mandt - Compressing Variational Bayes: From neural data compression to video prediction
Presentation given by Stephan Mandt on 7/6/22 in the one world seminar on the mathematics of machine learning on the topic "Compressing Variational Bayes: From neural data compression to video prediction".
Abstract: Recent research has shown surprising connections between variational inference (VI) and data compression. This talk will review several theoretical and applied contributions in this domain. I will first show VI enables estimating the information rate-distortion function of a real-world data set, a quantity that could previously not be estimated beyond a few dimensions. I will then show how semi-amortized variational inference can improve neural image compression, how posterior uncertainties enable compression at variable bitrates, and how sequential variational autoencoders can be converted into practical video codecs. Finally, I show how neural video codecs can inspire design choices for extending diffusion models to video data.
Видео Stephan Mandt - Compressing Variational Bayes: From neural data compression to video prediction канала One world theoretical machine learning
Abstract: Recent research has shown surprising connections between variational inference (VI) and data compression. This talk will review several theoretical and applied contributions in this domain. I will first show VI enables estimating the information rate-distortion function of a real-world data set, a quantity that could previously not be estimated beyond a few dimensions. I will then show how semi-amortized variational inference can improve neural image compression, how posterior uncertainties enable compression at variable bitrates, and how sequential variational autoencoders can be converted into practical video codecs. Finally, I show how neural video codecs can inspire design choices for extending diffusion models to video data.
Видео Stephan Mandt - Compressing Variational Bayes: From neural data compression to video prediction канала One world theoretical machine learning
Показать
Комментарии отсутствуют
Информация о видео
6 июля 2022 г. 23:21:17
00:57:48
Другие видео канала
Lukasz Szpruch - Mean-Field Neural ODEs, Relaxed Control and Generalization Errors
Matthew Colbrook - Smale’s 18th Problem and the Barriers of Deep Learning
Yu Bai - How Important is the Train-Validation Split in Meta-Learning?
Anna Korba - Kernel Stein Discrepancy Descent
Anirbit Mukherjee - Provable Training of Neural Nets With One Layer of Activation
Kevin Miller - Ensuring Exploration and Exploitation in Graph-Based Active Learning
Theo Bourdais - Computational Hypergraph Discovery, a Gaussian Process framework
Yaoqing Yang - Predicting & improving generalization by measuring loss landscapes & weight matrices
Konstantinos Spiliopoulos - Mean field limits of neural networks: typical behavior and fluctuations
Nadia Drenska - A PDE Interpretation of Prediction with Expert Advice
Matthias Ehrhardt - Bilevel Learning for Inverse Problems
Peter Richtarik - The Resolution of a Question Related to Local Training in Federated Learning
Marcus Hutter - Testing Independence of Exchangeable Random Variables
Yury Korolev - Approximation properties of two-layer neural networks with values in a Banach space
Sophie Langer - Circumventing the curse of dimensionality with deep neural networks
Derek Driggs - Barriers to Deploying Deep Learning Models During the COVID-19 Pandemic
Gal Vardi - Implications of the implicit bias in neural networks
Ziwei Ji - The dual of the margin: improved analyses and rates for gradient descent’s implicit bias
Qi Lei - Predicting What You Already Know Helps: Provable Self-Supervised Learning
Alessandro Scagliotti - Deep Learning Approximation of Diffeomorphisms via Linear-Control Systems