Nov 28, 2022
Speaker · 0 followers
Speaker · 0 followers
Most PAC-Bayesian bounds hold in the batch learning setting where data is collected at once, prior to inference or prediction. This somewhat departs from many contemporary learning problems where data streams are collected and the algorithms must dynamically adjust. We prove new PAC-Bayesian bounds in this online learning framework, leveraging an updated definition of regret, and we revisit classical PAC-Bayesian results with a batch-to-online conversion, extending their remit to the case of dependent data. Our results hold for bounded losses, potentially non-convex, paving the way to promising developments in online learning.Most PAC-Bayesian bounds hold in the batch learning setting where data is collected at once, prior to inference or prediction. This somewhat departs from many contemporary learning problems where data streams are collected and the algorithms must dynamically adjust. We prove new PAC-Bayesian bounds in this online learning framework, leveraging an updated definition of regret, and we revisit classical PAC-Bayesian results with a batch-to-online conversion, extending their remit to the case of dep…
Account · 952 followers
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Haoxuan Qu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Pedro Ortiz, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Yanchen Deng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Seanie Lee, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%