Workshop — Day 2 (Provisional)

Venue: H.C. Ørsted Institute (HCØ), Auditorium 1 (Aud. 01), Universitetsparken 5, 2100 Copenhagen Ø.

Accepted contributions are now available: view the full list.

Sat, Jun 27

08:30–09:00	Morning coffee break
09:00–09:45	Maryam Kamgarpour Title: Learning equilibria in multiagent games: from monotone to stochastic games
09:45–10:30	Mehryar Mohri Title: Distributional Alignment Games for Answer-Level Fine-Tuning
10:30–10:50	Coffee break
10:50–11:30	Contributed talks 7–8 (2×20 min incl. Q&A) Language Generation with Replay: A Learning-Theoretic View of Model Collapse Giorgio Racca r-Adjacency Differential Privacy: Convex Learning, Gaussian Release, and Reconstruction Robustness Joseph Margaryan
11:30–12:15	Marco Mondelli Title: Learning from Surrogate Data: Weak-to-Strong Generalization through the Lens of High-Dimensional Regression
12:15–13:30	Lunch
13:30–14:15	Alex Slivkins Title: Bandit Social Learning: Exploration (Failures) under Exploitation
14:15–15:15	Contributed talks 9–11 (3×20 min incl. Q&A) (Semi-)Adversarial Causal Bandits with Known Causal Mechanism and Causal Self-Bounding Hubert Marek Drazkowski On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents Oliver Mortensen A Single Stepsize for Robust and Fast Unprojected TD(0) Wei-Cheng Lee
15:15–15:30	Coffee break
15:30–16:15	Francesco Orabona Title: State-of-the-Art Confidence Intervals and Confidence Sequences through Testing-by-Betting Algorithms
16:15–17:00	Julian Zimmert Title: Bandits in the wild: What are the tradeoffs of robustness?
17:00–17:10	Closing remarks for the workshop

Venue Map

Workshop

H.C. Ørsted Institute (HCØ)

Universitetsparken 5, 2100 Copenhagen Ø

Auditorium 1 (Aud. 01)

Map data: OpenStreetMap contributors.