Last-Iterate Convergence of Optimistic Multiplicative Weights Update Francesco Orabona, Associate Professor, Computer Science Oct 5, 12:00 - 13:00 B9 R2325 gradient descent operation optimistic gradient descent ascent convex optimization saddle-point problems This talk will show how OMWU converges asymptotically for smooth convex-concave saddle-point problems, with a small enough constant learning rate.
Private and Robust Learning for Decision Making Yulian Wu, Ph.D. Student, Computer Science Apr 14, 15:00 - 17:00 B4 R5220; Zoom Meeting 98132861421 decision making Trustworthy AI privacy-preserving AI Data Privacy machine learning artificial intelligence AI This thesis develops the theoretical foundations of decision-making under privacy, heavy-tailed feedback, and data contamination, establishing fundamental limits and designing near-optimal algorithms across bandits, reinforcement learning, and RLHF.
