Research
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.

169,181 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Jan 201919922001200920182026
1 result for “regime-free”
Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneouslycs.LG

Optimal semi-bandit algorithm for both stochastic and adversarial environments.

problem Optimal semi-bandit algorithm for both stochastic and adversarial environments.
method Developed a general semi-bandit algorithm that achieves O(log⁡T)\mathcal{O}(\log T) regret for stochastic and O(T)\mathcal{O}(\sqrt{T}) regret for adversarial environments without regime or TT knowledge.
result First algorithm to achieve optimal O(log⁡T)\mathcal{O}(\log T) and O(T)\mathcal{O}(\sqrt{T}) regret simultaneously for stochastic and adversarial environments.
semi-banditregret minimizationstochasticadversarialregime-free
2019-01-25abs ↗pdf ↗