Sasha Rakhlin
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 4 in the filters
on a stage with
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Generalization I | Deep Learning Boot Camp 2019 | 2019-05-28 |
Proves a concrete generalization claim: the perceptron update makes at most 1/γ^2 mistake bound on any sequence with margin γ, and a one‑pass run yields… | ||
| Generalization II | Deep Learning Boot Camp 2019 | 2019-05-28 |
Shows that uniform deviation between population and empirical losses is essentially captured by Rademacher averages using symmetrization with a ghost sample… | ||
| Generalization III | Deep Learning Boot Camp 2019 | 2019-05-28 |
Uses Rademacher symmetrization to reduce uniform deviations to analyzable averages and gives classification bounds like sup deviation = O(sqrt(d log n / n))… | ||
| Generalization IV | Deep Learning Boot Camp 2019 | 2019-05-28 |
Compares K‑nearest neighbors and kernel smoothing with explicit bias–variance decompositions, deriving the minimax rate N^{-2/(2+d)} under Lipschitz… | ||
| A Few Connections Between Optimization and Probability | Optimization, Statistics and Uncertainty | 2017-11-28 |
Claims an iff equivalence: a martingale inequality holds for all martingale difference sequences exactly when there exists a function U satisfying domination… | ||
| Robustness, Stochastics, Uncertainty 1 | Bridging Continuous and Discrete Optimization Boot Camp 2017 | 2017-08-21 |
Shows that finite-sample learning guarantees come from concrete optimization tools: Blackwell approachability gives a randomized strategy that matches the… | ||
| Robustness, Stochastics, Uncertainty 2 | Bridging Continuous and Discrete Optimization Boot Camp 2017 | 2017-08-21 |
Shows that projected SGD and online linear optimization give a deterministic 1/√N regret for bounded gradients and that an adaptive stepsize (Adagrad-style)… | ||
| Robustness, Stochastics, Uncertainty 3 | Bridging Continuous and Discrete Optimization Boot Camp 2017 | 2017-08-21 |
Gives a practical tour: shows that tiny implementation noise (example cited: 0.001% error breaks feasibility) ruins some linear-program designs, converts… | ||
| How to Predict When Estimation is Hard: Algorithms for Learning on Graphs | Optimization and Decision-Making Under Uncertainty (Simons Institute, September 2016) | 2016-09-19 |
Claim: sequential predictors achieve the same error as the NP‑hard best graph labeling while avoiding model estimation by using improper prediction and… | ||
| nothing matches | ||