סמינר: Machine Learning Seminar
PAC-Bayes Bounds for Forgetting in Continual Learning
Date:
January,29,2025
Start Time:
11:30 - 12:30
Location:
1061, Meyer Building
Add to:
Lecturer:
Lior Friedman
Research Areas:
| In continual learning, knowledge must be preserved and re-used between tasks, maintaining good transfer to future tasks and minimizing forgetting of previously learned ones. While several practical algorithms have been devised for this setting, there have been few theoretical works aiming to quantify and bound the degree of forgetting in general settings.
In this talk, I will present some of our work on general upper bounds for forgetting, as well as asymptotic oracle bounds for Gibbs posteriors. |
| Lior is a PhD student supervised by Prof. Ron Meir. His research focuses on Continual and Meta-Learning and providing insights on the benefits of learning with multiple related tasks.
|