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

2 results for “NormalHedge”

A second order regret bound for NormalHedgecs.LG

Improved prediction algorithm for 'easy' sequences with reduced regret.

problem Prediction with expert advice for 'easy' sequences.

method Variant of NormalHedge algorithm using second-order

ε

-quantile regret bound.

result Second-order

ε

-quantile regret bound of

O\big(\sqrt{V_T \log(V_T/ε)}\big)

for

V_T > \log N

regret bound prediction with expert advice second order NormalHedge Stochastic Differential Equations

2026-02-08abs ↗pdf ↗

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 regret semi-adversarial FTRL root-logarithmic regularizers minimax optimality

2021-10-27abs ↗pdf ↗