J. Mayo

activity

20192026

most citedFull Counting Statistics of Topological Defects After Crossing a Phase Transition

67 citations · 98 across the 4 of their papers we have counts for

collaborators

Showing cs.LGShow all

3 papers · 1 filter

cs.LG2026

Minimax-Optimal Small-Loss Bounds for Online Linear Optimisation on $ℓ_{p}$ Balls

Jack J. Mayo

We study full-information online linear optimisation on the unit $ℓ_{p}$ ball in $R^{d}$ , for fixed $2 \leq p < \infty$ and losses of dual norm at most one. Let $Δ_{T}$ denote th…

cs.LG2023

First- and Second-Order Bounds for Adversarial Linear Contextual Bandits

Julia Olkhovskaya, Jack Mayo, Tim van Erven +2

We consider the adversarial linear contextual bandit setting, which allows for the loss functions associated with each of $K$ arms to change over time without restriction. Assuming…

cs.LG2022★ 1 cited

Scale-free Unconstrained Online Learning for Curved Losses

Jack J. Mayo, Hédi Hadiji, Tim van Erven

A sequence of works in unconstrained online convex optimisation have investigated the possibility of adapting simultaneously to the norm $U$ of the comparator and the maximum norm…

Minimax-Optimal Small-Loss Bounds for Online Linear Optimisation on ℓp​ Balls

First- and Second-Order Bounds for Adversarial Linear Contextual Bandits

Scale-free Unconstrained Online Learning for Curved Losses

Minimax-Optimal Small-Loss Bounds for Online Linear Optimisation on $ℓ_{p}$ Balls