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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “min-regret”

Risk management in multi-objective portfolio optimization under uncertaintyq-fin.PM

Enhances portfolio optimization under uncertainty using robust multi-objective methods.

problem Uncertainties in real-world portfolio optimization scenarios.

method Robust multi-objective optimization with benchmark comparisons.

result More reliable and adaptable portfolio strategies for market uncertainties.

portfolio optimization uncertainty robustness multi-objective min-regret

2024-07-29abs ↗pdf ↗

Learning Stochastic Shortest Path with Linear Function Approximationcs.LG

New algorithm learns optimal path in reinforcement learning with linear approximations.

problem Optimal path learning in reinforcement learning with linear approximations.

method Proposes novel algorithm with Hoeffding-type and Bernstein-type confidence sets.

result Achieves near-optimal regret guarantee for linear mixture SSP.

reinforcement learning stochastic shortest path linear function approximation regret minimization confidence sets

2021-10-25abs ↗pdf ↗

Integrating multiple sources of ordinal information in portfolio optimizationq-fin.PM

Two approaches integrate qualitative views into portfolio optimization, showing aggregation methods outperform robust optimization.

problem Incorporating qualitative views into portfolio optimization models.

method Robust optimization and order aggregation methods.

result Aggregation methods outperform robust optimization in portfolio performance analysis.

portfolio optimization qualitative views social choice theory robust optimization mean-variance model

2022-11-01abs ↗pdf ↗

When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Lossescs.LG

New algorithms avoid a dominant lower-order term in heavy-tailed loss settings.

problem Prediction with heavy-tailed losses without prior knowledge.

method Adaptive algorithms that avoid the maximum of losses as a lower-order term in regret.

result Improved regret bounds of

\mathcal{O}(\sqrt{θT\log(K)})

and

\mathcal{O}(θ\log(KT)/Δ_{\min})

heavy-tailed losses adaptive algorithms regret bounds lower-order term squared loss

2025-06-02abs ↗pdf ↗