Statistical curriculum learning: An elimination algorithm achieving the weak oracle risk
Cancelled
Event details
| Date | 04.03.2024 |
| Hour | 16:15 › 17:00 |
| Speaker | Prof. Nir Weinberger The Viterbi Faculty of Electrical and Computer Engineering Technion - Israel Institute of Technology |
| Location | |
| Category | Conferences - Seminars |
| Event Language | English |
Curriculum Learning (CL) is a widely used machine learning strategy that improves the learner's performance by allowing it to order the training samples during learning, similarly to the way humans learn.
In this work, we address statistical aspects of CL, and consider a parametric learning problem with a target task and multiple source tasks. While only the target parameter is of interest, sampling from a source task might be beneficial if they are less noisy than the target task, while their corresponding parameters are very close. The learner is restricted by the total number of samples, and can adaptively choose how to allocate samples to each of the models.
We define a strong-oracle learner as an ideal learner, which allocates all its samples to the most effective model (either the target or one of the sources). We show that achieving its performance is too ambitious for a learning algorithm, and advocate a weak-oracle learner, as a more realistic benchmark for CL algorithms.
We first develop an elimination-based learning algorithm, and determine conditions that allow it to match the weak-oracle learner. We then consider lower bounds via minimax lower bounds. We reveal a few challenges associated with defining informative classes of problem-instances, propose two bounds, and determine the conditions under which the performance weak-oracle learner is provably optimal.
Joint work with Omer Cohen and Ron Meir.
Practical information
- Informed public
- Free
Organizer
- IPG Seminar Prof. Weinberger is hosted by Prof. Michael Gastpar (LINX)