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.

168,695 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · May 201919922001200920172026
3 results for “norm-agnostic”
Empirical Bound Information-Directed Sampling for Norm-Agnostic Banditsstat.ML

New IDS algorithm refines parameter norm bounds for better bandit performance.

problem Frequentist IDS requires tight norm bounds, which are often unavailable in practice.
method Iteratively refines a high-probability upper bound on true parameter norm using data.
result Regret bounds independent of assumed parameter norm, outperforming state-of-the-art algorithms.
banditsIDSnorm-agnosticregretparameter bounds
2025-03-07abs ↗pdf ↗
Norm-Agnostic Linear Banditsstat.ML

New algorithms for linear bandits avoid norm knowledge, reducing regret.

problem Linear bandits require knowledge of norm bound SS on parameter θ∗θ^*, leading to high regret.
method Proposes two novel algorithms for changing and fixed arm sets, analyzing their regret bounds.
result Regret bounds show no significant price for not knowing SS, with no price for fixed arm sets.
linear banditsregret boundsnorm-agnosticalgorithm designrecommendation systems
2022-05-03abs ↗pdf ↗
On Norm-Agnostic Robustness of Adversarial Trainingcs.LG

Adversarial examples are carefully perturbed in-puts for fooling machine learning models. A well-acknowledged defense method against such examples is adversarial training, where adversarial examples are injected into training data to increase robustness. In this paper, we propose a new attack to unveil an undesired pro…

2019-05-15abs ↗pdf ↗