MediaTek (China)

most citedOptimal Order Simple Regret for Gaussian Process Bandits

5 citations

researchers with a paper here

Sattar Vakili2 · h 16
A. Bernacchia1 · h 17
Chia-Ping Chen1 · h 6
Da-shan Shiu1
John Scarlett1
Kevin Jou1
N. Bouziani1
Ning-Hsu Wang1
Ren Wang1
Sepehr Jalali1
T. Javidi1 · h 34
Yu-Hao Huang1

collaborating institutions

National Tsing Hua UniversityTW1 paper
National University of SingaporeSG1 paper
University College LondonGB1 paper
University of California San DiegoUS1 paper
University of CambridgeGB1 paper

Showing stat.MLShow all

2 papers · 1 filter

stat.ML2021★ 1 cited

Open Problem: Tight Online Confidence Intervals for RKHS Elements

Sattar Vakili, Jonathan Scarlett, Tara Javidi

Confidence intervals are a crucial building block in the analysis of various online learning problems. The analysis of kernel based bandit and reinforcement learning problems utili…

stat.ML2021★ 5 cited

Optimal Order Simple Regret for Gaussian Process Bandits

Sattar Vakili, Nacime Bouziani, Sepehr Jalali +2

Consider the sequential optimization of a continuous, possibly non-convex, and expensive to evaluate objective function $f$ . The problem can be cast as a Gaussian Process (GP) band…