Jonathan Ullman
where else to find them
what they talk about
where they keep going back
no series more than once — all 4 in the filters
on a stage with
- Deepak Gargonce
- Jiawen Liuonce
- Marco Gaboardionce
all 4 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Virtual talk by Jonathan Ullman (Northeastern) | Trust in Decentralized Systems 2026 | 2026-03-16 |
Shows that for a noisy Gaussian mean setting membership inference can be information-theoretically possible yet demand an auxiliary sample size Omega(d) that… | ||
| Program Analysis for Adaptive Data Analysis | PLDI 2024 | 2024-06-24 |
Static analysis estimates the adaptivity of while-like adaptive data analyses by building a weighted dependency graph whose node weights are reachability upper… | ||
| Differential Privacy And The Complexity Of Simple Queries | Rigorous Evidence for Information-Computation Trade-offs | 2021-09-13 |
Shows an explicit information–computation gap: answering k arbitrary bounded mean queries privately needs about √k samples with any polynomial-time algorithm… | ||
| Algorithmic Stability for Interactive Data Analysis | Optimization, Statistics and Uncertainty | 2017-11-28 |
Interactive reuse of data causes severe overfitting: naive empirical answers let an adaptive procedure reach correlation about √D/√N (even perfect when D > N)… | ||
| nothing matches | ||