6 citations · 8 across the 4 of their papers we have counts for
5 papers
Instance-Adaptive Online Multiclass Multicalibration
Zhiming Huang, Jamie Morgenstern, Aaron Roth +1
We study online multiclass multicalibration over rounds, and give an algorithm with beyond-worst-case guarantees. With possible outcomes, forecasts lie in a simplex of dime…
Instance-Adaptive Online Multicalibration
Zhiming Huang, Jamie Morgenstern, Aaron Roth +1
We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-case sequences by adaptively r…
Algorithmic Collusion Without Threats
Eshwar Ram Arunachaleswaran, Natalie Collina, Sampath Kannan +2
There has been substantial recent concern that pricing algorithms might learn to ``collude.'' Supra-competitive prices can emerge as a Nash equilibrium of repeated pricing games, i…
Oracle Efficient Algorithms for Groupwise Regret
Krishna Acharya, Eshwar Ram Arunachaleswaran, Sampath Kannan +2
We study the problem of online prediction, in which at each time step , an individual arrives, whose label we must predict. Each individual is associated with various grou…
A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem
Sampath Kannan, Jamie Morgenstern, Aaron Roth +2
Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of…