Sham Kakade
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 5 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| What is the Statistical Complexity of Reinforcement Learning? | Multi-Agent Reinforcement Learning and Bandit Learning | 2022-04-29 |
Shows that simple linear Q realizability and linear policy classes still require exponential samples in horizon or dimension, so they fail for high‑dimensional… | ||
| What Are the Statistical Limits of Offline Reinforcement Learning With Function Approximation? | Mathematics of Online Decision Making 2020 | 2020-10-23 |
Assumes linear Q realizability and spectral coverage and then proves an information-theoretic lower bound: any offline algorithm can require about D^{H/2}… | ||
| Tradeoffs in Large Scale Learning: Statistical Accuracy vs. Numerical Precision | Information Theory, Learning and Big Data (Simons Institute, 2015) | 2015-03-16 |
Claims an algorithm based on variance-reduced gradient ideas drives the excess risk to the empirical-risk-minimizer rate sigma^2/n while using one-pass… | ||
| Tensor Decompositions for Estimating Latent Variable Models | Tensors in Computer Science and Geometry 2014 | 2014-11-10 |
Claims that tensors yield closed‑form, polynomial‑time estimators for several latent models under mild nondegeneracy: use the method of moments, whiten the… | ||
| Spectral Algorithms for Learning Latent Variable Models | Spectral Algorithms: From Theory to Practice 2014 | 2014-10-27 |
Spectral methods use explicit moment equations and tensor algebra to recover latent mixtures: three-word documents suffice for identifiable topic vectors… | ||
| nothing matches | ||