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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “doubly-optimistic”

Safe Linear Bandits over Unknown Polytopescs.LG

Safe linear bandits over unknown polytopes avoid safety violations and suboptimal actions.

problem Online approach to linear programming with unknown constraints and risks.

method Doubly-optimistic strategy (DOSS) for safe linear bandits over polytopes.

result DOSS achieves tight bounds on efficacy regret and safety violations.

safe linear bandits unknown polytopes doubly-optimistic strategy regret bounds safety violations

2022-09-27abs ↗pdf ↗

Online Decision Making with Generative Action Setscs.LG

New algorithm optimizes online decision-making with dynamically generated actions.

problem Balancing action generation costs with optimal decision-making in online learning.

method Doubly-optimistic algorithm using LCB for action selection and UCB for action generation.

result Achieves optimal regret bound of

O(T^{\frac{d}{d+2}}d^{\frac{d}{d+2}} + d\sqrt{T\log T})

online learning generative AI doubly-optimistic action generation regret bound

2025-09-30abs ↗pdf ↗

Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Riskcs.LG

Logarithmic regret strategies for safe multi-armed bandits with safety risk constraints.

problem Maximizing reward while avoiding unsafe arms under safety risk constraints.

method Doubly optimistic strategies with pseudo-regret formulation.

result Logarithmic regret bounds for safe multi-armed bandits.

multi-armed bandits logarithmic regret safety constraints pseudo-regret risk management

2022-04-01abs ↗pdf ↗