3 papers
cs.LG2026
Adaptive Weighted Averaging
Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar +1
We study the problem of selecting the largest among unknown values given only a single unbiased estimate for each . We design strategies that are sim…
cs.LG2022
Leveraging Initial Hints for Free in Stochastic Linear Bandits
Ashok Cutkosky, Chris Dann, Abhimanyu Das +2
We study the setting of optimizing with bandit feedback with additional prior knowledge provided to the learner in the form of an initial hint of the optimal action. We present a n…
cs.LG2021
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…