6 papers · 1 filter
Does LinUCB Need Valid Confidence Sets?
Ahmed Ben Yahmed, Marc Abeille, David Janz +1
We show that replacing LinUCB's usual confidence width by any fixed preserves sublinear regret when the action set is -smooth and -strongly convex. Our high-probabi…
Generalizing Markowitz Portfolio Optimization by a Quadratic Risk Measure
Ignas Gasparavičius, Andrius Grigutis
We show that the key optimization results of the classical Markowitz portfolio selection theory, originally formulated for variance as the risk measure, remain available in explici…
Self-normalised Bennett inequalities for Hilbert-valued martingales
David Janz
We prove time-uniform self-normalised Bennett inequalities for a martingale in a separable Hilbert space, with and increments bounded in norm by one. Writi…
Variance-sensitive Thompson sampling for generalised linear bandits, revisited
Tom Perneczky, Marc Abeille, David Janz
We prove a variance-sensitive regret bound for Thompson sampling in stochastic generalised linear bandits. The argument assumes a warm-up, after which the regret is controlled thro…
Sharp analysis of linear ensemble sampling
David Janz, Arya Akhavan, Csaba Szepesvári
We analyse linear ensemble sampling (ES) with standard Gaussian perturbations in stochastic linear bandits. We show that for ensemble size , ES attains $\tilde O(d^{3…
Eluder dimension: localise it!
Alireza Bakhtiari, Alex Ayoub, Samuel Robertson +2
We establish a lower bound on the eluder dimension of generalised linear model classes, showing that standard eluder dimension-based analysis cannot lead to first-order regret boun…