activity
20172023
most citedRobust Submodular Maximization: A Non-Uniform Partitioning Approach

32 citations · 57 across the 12 of their papers we have counts for

collaborators
Showing stat.MLShow all

11 papers · 1 filter

stat.ML2022

A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits

Ilija Bogunovic, Zihan Li, Andreas Krause +1

We consider the sequential optimization of an unknown, continuous, and expensive to evaluate reward function, from noisy and adversarially corrupted observed rewards. When the corr…

stat.ML20217 cited

Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors

Zhaoqiang Liu, Subhroshekhar Ghosh, Jonathan Scarlett

Compressive phase retrieval is a popular variant of the standard compressive sensing problem in which the measurements only contain magnitude information. In this paper, motivated…

stat.ML2021

Lenient Regret and Good-Action Identification in Gaussian Process Bandits

Xu Cai, Selwyn Gomes, Jonathan Scarlett

In this paper, we study the problem of Gaussian process (GP) bandits under relaxed optimization criteria stating that any function value above a certain threshold is "good enough".…

stat.ML2020

Stochastic Linear Bandits Robust to Adversarial Attacks

Ilija Bogunovic, Arpan Losalka, Andreas Krause +1

We consider a stochastic linear bandit problem in which the rewards are not only subject to random noise, but also adversarial attacks subject to a suitable budget (i.e., an up…

stat.ML2020

The Generalized Lasso with Nonlinear Observations and Generative Priors

Zhaoqiang Liu, Jonathan Scarlett

In this paper, we study the problem of signal estimation from noisy non-linear measurements when the unknown -dimensional signal is in the range of an -Lipschitz continuous g…

stat.ML20208 cited

Corruption-Tolerant Gaussian Process Bandit Optimization

Ilija Bogunovic, Andreas Krause, Jonathan Scarlett

We consider the problem of optimizing an unknown (typically non-convex) function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS), based on noisy bandit feedback…