22 citations · 38 across the 14 of their papers we have counts for
5 papers · 1 filter
Logarithmic Regret from Sublinear Hints
Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar +1
We consider the online linear optimization problem, where at every step the algorithm plays a point in the unit ball, and suffers loss for some cost…
Upper Confidence Bounds for Combining Stochastic Bandits
Ashok Cutkosky, Abhimanyu Das, Manish Purohit
We provide a simple method to combine stochastic bandit algorithms. Our approach is based on a "meta-UCB" procedure that treats each of individual bandit algorithms as arms in…
Online Linear Optimization with Many Hints
Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar +1
We study an online linear optimization (OLO) problem in which the learner is provided access to "hint" vectors in each round prior to making a decision. In this setting, we dev…
Online Learning with Imperfect Hints
Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar +1
We consider a variant of the classical online linear optimization problem in which at every step, the online player receives a "hint" vector before choosing the action for that rou…
On Correcting Inputs: Inverse Optimization for Online Structured Prediction
Hal Daumé, Samir Khuller, Manish Purohit +1
Algorithm designers typically assume that the input data is correct, and then proceed to find "optimal" or "sub-optimal" solutions using this input data. However this assumption of…