1 / 5
02 / Subgroups
What we work on.
We organize around problems, not techniques. Each thread carries the same commitment to provable guarantees and practical deployment.
Bandits & Online Learning
Sequential decision-making under partial information — multi-armed bandits, contextual bandits, and adversarial online learning with provable regret guarantees.
UCBThompson SamplingMirror DescentAdversarialRegret bounds
Õ(√T)
tight regret
running average across our 2024–2026 contributions
03 / Latest publications
Out of the lab.
New preprints, conference papers, and code releases — most recent first. Each one comes with a one-click citation.
- Oral 2026/05/02
Optimistic Online Newton with Sublinear Regret on Strongly Curved Losses
- Paper 2026/04/28
Learned Cardinality with Distribution-Free Confidence
- Preprint 2026/04/14
Adaptive Mirror Descent for Heavy-Tailed Bandits
- Journal 2026/04/02
On the Price of Adaptivity in Online Convex Optimization
04 / Join us
Let's work together.
We do science for both academia and industry, and we read every application. Whether you're a prospective student, a collaborator, or a company with a hard problem, we'd love to hear from you.