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.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Jan 202019922001200920172026
5 results for “semi-adversarial”
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizersstat.ML

Optimizes quantile and semi-adversarial regret with novel root-logarithmic regularizers.

problem Minimizes regret in adversarial and semi-adversarial online learning.
method FTRL with root-logarithmic regularizers for quantile and semi-adversarial settings.
result Achieves minimax optimal regret bounds in both paradigms.
quantile regretsemi-adversarialFTRLroot-logarithmic regularizersminimax optimality
2021-10-27abs ↗pdf ↗
Relaxing the I.I.D. Assumption: Adaptively Minimax Optimal Regret via Root-Entropic Regularizationstat.ML

Adapting Hedge algorithm for semi-adversarial data with root-entropy regularization.

problem Minimizing regret in prediction with expert advice under varying distributions.
method Follow-the-Regularized-Leader (FTRL) with root-entropy regularization.
result Adaptive minimax optimal regret across all levels of constraint sets.
Hedge algorithmsemi-adversarialroot-entropyFTRLminimax
2020-07-13abs ↗pdf ↗
No-Regret Learning with Unbounded Losses: The Case of Logarithmic Poolingcs.LG

Algorithm learns expert weights to minimize regret in adversarial setting.

problem Learning to aggregate expert forecasts with no-regret guarantee in adversarial conditions.
method Online mirror descent algorithm for logarithmic pooling of expert forecasts.
result Achieves O(Tlog⁡T)O(\sqrt{T} \log T) expected regret compared to best weights.
regret minimizationlogarithmic poolingonline learningadversarial settingmirror descent
2022-02-22abs ↗pdf ↗