Han Shao
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 3 in the filters
on a stage with
all 11 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Lightning Talks! | The Role of TCS in Modern Machine Learning | 2026-05-26 |
A rapid-fire set of concrete results: an online load‑balancing scheme learns from a 1% sample and achieves a 1+ε load guarantee (using fractional relaxations… | ||
| A Theoretical Framework for Statistical Evaluability of Generative Models | Agency in Collaborative Learning 2026 | 2026-04-13 |
Statistical evaluability is formalized: some metrics are impossible to test from finite i.i.d. samples while others are. Concrete findings: KL and Rényi are… | ||
| Tutorial: Incentives for Collaborative Learning and Data Sharing, Part I | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
Presents a formal model where K agents choose contribution levels (Mi) and utilities equal local model quality minus linear data cost, proves Nash equilibria… | ||
| Tutorial: Incentives for Collaborative Learning and Data Sharing, Part Ib | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
Shows that naive collaboration can be K times inefficient: a double-star network has an optimal effort of 2 but any stable outcome costs Theta(K). Uses… | ||
| Tutorial: Incentives for Collaborative Learning and Data Sharing, Part II | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
Covers practical definitions and limits of data valuation: leave-one-out needs N+1 retrainings and fails on redundancy; Shapley value solves redundancy but… | ||
| nothing matches | ||