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.

168,982 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.0% · Jul 199219922001200920172026
1 result for “THV-UCB”
Top-kk Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selectioncs.LG

A new algorithm THV-UCB reduces regret in multi-objective bandit problems.

problem Maintaining a small set of actions that jointly approximate the Pareto frontier in multi-objective slate selection.
method THV-UCB, an optimistic algorithm that selects arms based on optimistic estimates of their marginal hypervolume contributions.
result The algorithm achieves a gap-free regret bound of ildeO(dnkT) ilde{O}(d\sqrt{nkT}) and a gap-dependent bound of ildeO(nk2.5/Δmin⁡) ilde{O}(nk^{2.5}/Δ_{\min}).
multi-objective banditsPareto fronthypervolume regretTHV-UCBslate selection
2026-07-28abs ↗pdf ↗