Many success stories in the data sciences share an intriguing computational phenomenon.
While the core algorithmic problems might seem intractable at first, simple heuristics or …

We study the problem of minimizing a convex function given by a zeroth order oracle that is
possibly corrupted by {\em outlier noise}. Specifically, we assume the function values at …

Binary search is one of the most fundamental search routines, exploiting the hidden
structure of the search space. In particular, it cuts down exponentially on the complexity of …

We consider optimization problems whose parameters are known only approximately,
based on a noisy sample. Of particular interest is the high-dimensional regime, where the …

Generalization properties are a central aspect of the design and analysis of learning
algorithms. One notion that has been considered in many previous works as leading to good …

This authoritative book draws on the latest research to explore the interplay of high-
dimensional statistics with optimization. Through an accessible analysis of fundamental …

Noisy optimization is the optimization of objective functions corrupted by noise. A portfolio of
algorithms is a set of algorithms equipped with an algorithm selection tool for distributing the …

In recent years, a rapidly increasing number of applications in practice requires solving non-
convex objectives, like training neural networks, learning graphical models, maximum …

Given a point set P={p_1,\dots,p_n\} in the d-dimensional unit hypercube, we give upper
bounds on the maximal expected number of extreme points when each point pi is perturbed …

In this paper we investigate multiplicative noise models in the context of continuous
optimization. We illustrate how some intrinsic properties of the noise model imply the failure …