activity
20172021
most citedAdaptive Sensor Placement for Continuous Spaces

8 citations · 21 across the 6 of their papers we have counts for

collaborators

13 papers

stat.ML20211 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…

cs.LG2021

Uniform Generalization Bounds for Overparameterized Neural Networks

Sattar Vakili, Michael Bromberg, Jezabel Garcia +2

An interesting observation in artificial neural networks is their favorable generalization error despite typically being extremely overparameterized. It is well known that the clas…

stat.ML20215 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 . The problem can be cast as a Gaussian Process (GP) band…

stat.ML2020

A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance

Sudeep Salgia, Sattar Vakili, Qing Zhao

We consider sequential optimization of an unknown function in a reproducing kernel Hilbert space. We propose a Gaussian process-based algorithm and establish its order-optimal regr…

stat.ML2020

On Information Gain and Regret Bounds in Gaussian Process Bandits

Sattar Vakili, Kia Khezeli, Victor Picheny

Consider the sequential optimization of an expensive to evaluate and possibly non-convex objective function from noisy feedback, that can be considered as a continuum-armed ban…

stat.ML2020

Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization

Sudeep Salgia, Qing Zhao, Sattar Vakili

A framework based on iterative coordinate minimization (CM) is developed for stochastic convex optimization. Given that exact coordinate minimization is impossible due to the unkno…