3 papers
cs.LG2025
Sample-Adaptivity Tradeoff in On-Demand Sampling
Nika Haghtalab, Omar Montasser, Mingda Qiao
We study the tradeoff between sample complexity and round complexity in on-demand sampling, where the learning algorithm adaptively samples from distributions over a limited nu…
stat.ML2025
Beyond Worst-Case Online Classification: VC-Based Regret Bounds for Relaxed Benchmarks
Omar Montasser, Abhishek Shetty, Nikita Zhivotovskiy
We revisit online binary classification by shifting the focus from competing with the best-in-class binary loss to competing against relaxed benchmarks that capture smoothed notion…
cs.LG2024
Derandomizing Multi-Distribution Learning
Kasper Green Larsen, Omar Montasser, Nikita Zhivotovskiy
Multi-distribution or collaborative learning involves learning a single predictor that works well across multiple data distributions, using samples from each during training. Recen…