Recently, over-parameterized deep networks, with increasingly more network parameters
than training samples, have dominated the performances of modern machine learning …

This century saw an unprecedented increase of public and private investments in Artificial
Intelligence (AI) and especially in (Deep) Machine Learning (ML). This led to breakthroughs …

In this work, we study the performance of sub-gradient method (SubGM) on a natural
nonconvex and nonsmooth formulation of low-rank matrix recovery with ℓ1-loss, where the …

This paper presents a framework for smooth optimization of objectives with ℓq and ℓp, q
regularization for (structured) sparsity. Finding solutions to these non-smooth and possibly …

We consider using gradient descent to minimize the nonconvex function f (X)= ϕ (XX T) over
an n× r factor matrix X, in which ϕ is an underlying smooth convex cost function defined over …

This work analyzes the solution trajectory of gradient-based algorithms via a novel basis
function decomposition. We show that, although solution trajectories of gradient-based …

Label noise poses an important challenge in machine learning, especially in deep learning,
in which large models with high expressive power dominate the field. Models of that kind are …

Overparameterized models have proven to be powerful tools for solving various machine
learning tasks. However, overparameterization often leads to a substantial increase in …

In low-rank matrix recovery, the goal is to recover a low-rank matrix, given a limited number
of linear and possibly noisy measurements. Low-rank matrix recovery is typically solved via …

We establish a new theoretical framework for learning under multi-class, instance-
dependent label noise. This framework casts learning with label noise as a form of domain …