1 code implementation • 22 Oct 2022 • Michael Dinitz, Sungjin Im, Thomas Lavastida, Benjamin Moseley, Sergei Vassilvitskii
For each of these problems we introduce new algorithms that take advantage of multiple predictors, and prove bounds on the resulting performance.
no code implementations • NeurIPS 2018 • Raman Arora, Michael Dinitz, Teodor V. Marinov, Mehryar Mohri
We revisit the notion of policy regret and first show that there are online learning settings in which policy regret and external regret are incompatible: any sequence of play that achieves a favorable regret with respect to one definition must do poorly with respect to the other.
no code implementations • 9 Jun 2021 • Michael Dinitz, Aravind Srinivasan, Leonidas Tsepenekas, Anil Vullikanti
Graph cut problems are fundamental in Combinatorial Optimization, and are a central object of study in both theory and practice.
no code implementations • NeurIPS 2021 • Michael Dinitz, Sungjin Im, Thomas Lavastida, Benjamin Moseley, Sergei Vassilvitskii
Second, once the duals are feasible, they may not be optimal, so we show that they can be used to quickly find an optimal solution.
no code implementations • 16 Feb 2022 • Amy Babay, Michael Dinitz, Aravind Srinivasan, Leonidas Tsepenekas, Anil Vullikanti
The second is a Sample Average Approximation (SAA) based algorithm, which we analyze for the Chung-Lu random graph model.