Search Results for author:
Found 6 papers, 0 papers with code
Mitigating Disparity while Maximizing Reward: Tight Anytime Guarantee for Improving Bandits
We study the tension that arises between two seemingly conflicting objectives in the horizon-unaware setting: a) maximizing the cumulative reward at any time based on current rewards of the arms, and b) ensuring that arms with better long-term rewards get sufficient opportunities even if they initially have low rewards.
Fairness and Welfare Quantification for Regret in Multi-Armed Bandits
Since NSW is known to satisfy fairness axioms, our approach complements the utilitarian considerations of average (cumulative) regret, wherein the algorithm is evaluated via the arithmetic mean of its expected rewards.
Approximation Algorithms for ROUND-UFP and ROUND-SAP
In ROUND-UFP, the goal is to find a packing of all tasks into a minimum number of copies (rounds) of the given path such that for each copy, the total demand of tasks on any edge does not exceed the capacity of the respective edge.
Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization
In this setting, the arms arrive in a stream, and the number of arms that can be stored in the memory at any time, is bounded.
Approximation Algorithms for Generalized Multidimensional Knapsack
The input is a set of rectangular items, each with an associated profit and $d$ nonnegative weights ($d$-dimensional vector), and a square knapsack.
Data Structures and Algorithms Computational Geometry
Streaming Algorithms for Stochastic Multi-armed Bandits
In this setting, the arms arrive in a stream, and the number of arms that can be stored in the memory at any time, is bounded.
