On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “Fair-SMAB”

Achieving Fairness in Stochastic Multi-armed Bandit Problemcs.LG

New algorithm tackles fairness in multi-armed bandit problem.

problem Fairness in stochastic multi-armed bandit problem.

method Characterized a class of Fair-SMAB algorithms with two parameters.

result Achieves O(log(T)) r-Regret with UCB1 learning algorithm.

Fair-SMAB stochastic multi-armed bandit fairness UCB1 regret

2019-05-27abs ↗pdf ↗

Achieving Fairness in the Stochastic Multi-armed Bandit Problemcs.LG

New algorithm tackles fairness in multi-armed bandit problem.

problem Fairness constraints in multi-armed bandit.

method Characterized Fair-SMAB algorithms with fairness tolerance and learning algorithm parameters.

result Achieves

O(\ln T)

r

-Regret with UCB1 learning algorithm.

Fair-SMAB multi-armed bandit fairness constraints UCB1 regret

2019-07-23abs ↗pdf ↗