Daniel Russo
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 2 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Adaptivity and Confounding in Multi-armed Bandit Experiments | Quantifying Uncertainty: Stochastic, Adversarial, and Beyond | 2022-09-12 |
Proposes deconfounded Thompson sampling, a simple tweak that samples arms by their posterior chance of being best across the whole population (not just the… | ||
| On the Global Convergence and Approximation Benefits of Policy Gradient Methods | Mathematics of Online Decision Making 2020 | 2020-10-23 |
Shows that gradient descent on parameterized policies avoids suboptimal stationary points when two concrete conditions hold: the policy class is closed under… | ||
| nothing matches | ||