John Duchi
where else to find them
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 5 in the filters
on a stage with
- Aleksandra Slavkoviconce
- Anand Sarwateonce
- Bin Yuonce
all 5 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Robust Optimization and Generalization | Modern Paradigms in Generalization Boot Camp 2024 | 2024-08-27 |
A production LP with tiny input shifts (about 0.5%–2%) shows losses of 15%–20% when reusing the same plan; a robust LP that enforces rowwise perturbations… | ||
| Optimality in Locally Private Estimation and Learning | Privacy and the Science of Data Analysis 2019 | 2019-04-08 |
Proves lower bounds for locally private estimation by reducing estimation to testing via Assouad’s method and a communication-complexity / strong data… | ||
| PANEL: Statistical Theory, Privacy and Data Analysis | Privacy and the Science of Data Analysis 2019 | 2019-04-08 |
Panel argues that differential privacy acts as both a constraint and an enabler: it enforces data hygiene, gives formal generalization guarantees, and opens… | ||
| The Importance of Better Models in Stochastic Optimization... | Robust and High-Dimensional Statistics (Simons Institute workshop, 2018) | 2018-10-29 |
Experiments compare stochastic gradient to stochastic proximal point and simple truncated models and claim proximal/truncated updates remain stable across… | ||
| Distributional Robustness, Learning, and Empirical Likelihood | Optimization, Statistics and Uncertainty | 2017-11-28 |
Claims that modest distributional robustness recovers a variance penalty and gives usable certificates, implemented two concrete tools: a convex reweighting… | ||
| Strong Data Processing Inequalities and Estimation with Constraints | Information Theory, Learning and Big Data (Simons Institute, 2015) | 2015-03-16 |
Claim: a likelihood ratio bound anywhere in a Markov chain forces a strong data processing inequality that contracts mutual information by roughly (e^α−1)^2… | ||
| nothing matches | ||