Search papers, labs, and topics across Lattice.
5
0
4
6
Randomness is not just a convenience in Adaptive Data Analysis; it’s a necessity, especially when analysts are unbounded, limiting deterministic mechanisms to just \( \tilde{O}(n) \) queries.
Delayed feedback in linear bandits can fundamentally alter regret dynamics, revealing that loss-dependent delays are significantly more challenging than in multi-armed bandits.
Forget KL divergence – this work shows you *can* reliably evaluate generative models with finite samples, but only if you use the right metric (IPMs with bounded test classes).
Forget adversarial attacks – learning can be efficient even with counterexamples, as long as they're chosen symmetrically based on the difference between your model and the truth.
Learning to predict averages within neighborhoods, rather than individual labels, offers a new PAC learning framework with applications in explainability, fairness, and recommendation systems.
