Bayesian optimization (BO) has been widely applied to several modern science and
engineering applications such as machine learning, neural networks, robotics, aerospace …

Many applications in machine learning require optimizing unknown functions defined over a
high-dimensional space from noisy samples that are expensive to obtain. We address this …

We study active learning methods for single index models of the form $ F ({\bm x})= f (⟨{\bm
w},{\bm x}⟩) $, where $ f:\mathbb {R}\to\mathbb {R} $ and ${\bx,\bm w}\in\mathbb {R}^ d $. In …

In this paper, we present and analyze a new set of low-rank recovery algorithms for linear
inverse problems within the class of hard thresholding methods. We provide strategies on …

We consider the problem of active learning for single neuron models, also sometimes called
“ridge functions”, in the agnostic setting (under adversarial label noise). Such models have …

The Quark-Gluon Plasma (QGP) is a unique phase of nuclear matter, theorized to have filled
the Universe shortly after the Big Bang. A critical challenge in studying the QGP is that, to …

We study the properties of ridge functions f (x)= g (a ⋅ x) f (x)= g (a· x) in high dimensions dd
from the viewpoint of approximation theory. The function classes considered consist of ridge …

Bayesian optimization and kernelized bandit algorithms are widely used techniques for
sequential black box function optimization with applications in parameter tuning, control …

A function f:\mathbbR^ d→\mathbbR is referred to as a Sparse Additive Model (SPAM), if it is
of the form f (x)=\sum_l∈ S\phi_l (x_l), where S⊂[d],| S|≪ d. Assuming\phi_l's and S to be …

The multi-index model is a simple yet powerful high-dimensional regression model which
circumvents the curse of dimensionality assuming EY|X=g(A^⊤X) for some unknown index …