23 citations · 38 across the 6 of their papers we have counts for
6 papers
Tighter Confidence Bounds for Sequential Kernel Regression
Hamish Flynn, David Reeb
Confidence bounds are an essential tool for rigorously quantifying the uncertainty of predictions. They are a core component in many sequential learning and decision-making algorit…
Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
Hamish Flynn, David Reeb, Melih Kandemir +1
We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem. The widely used "optimism in the face of uncertainty" principle reduces a…
PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison
Hamish Flynn, David Reeb, Melih Kandemir +1
PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learning algorithms with tight performance guarantees. However, applications of PAC-Ba…
PAC-Bayesian Lifelong Learning For Multi-Armed Bandits
Hamish Flynn, David Reeb, Melih Kandemir +1
We present a PAC-Bayesian analysis of lifelong learning. In the lifelong learning problem, a sequence of learning tasks is observed one-at-a-time, and the goal is to transfer infor…
Persistence and the Random Bond Ising Model in Two Dimensions
S. Jain, H. Flynn
We study the zero-temperature persistence phenomenon in the random bond Ising model on a square lattice via extensive numerical simulations. We find strong evidence for ` b…
Scaling and Persistence in the Two-Dimensional Ising Model
S. Jain, H. Flynn
The spatial distribution of persistent spins at zero-temperature in the pure two-dimensional Ising model is investigated numerically. A persistence correlation length, $ξ(t)\sim t^…