Substantial progress has been made recently on developing provably accurate and efficient
algorithms for low-rank matrix factorization via nonconvex optimization. While conventional …

Factored feature volumes offer a simple way to build more compact, efficient, and
intepretable neural fields, but also introduce biases that are not necessarily beneficial for …

Abstract We propose $\textsf {ScaledGD ($\lambda $)} $, a preconditioned gradient descent
method to tackle the low-rank matrix sensing problem when the true rank is unknown, and …

We study a completion problem of broad practical interest: the reconstruction of a low-rank
symmetric tensor from highly incomplete and randomly corrupted observations of its entries …

As science and engineering have become increasingly data-driven, the role of optimization
has expanded to touch almost every stage of the data analysis pipeline, from signal and …

This paper considers the fundamental problem of learning a complete (orthogonal)
dictionary from samples of sparsely generated signals. Most existing methods solve the …

This paper concerns dictionary learning, ie, sparse coding, a fundamental representation
learning problem. We show that a subgradient descent algorithm, with random initialization …

We study the multi-channel sparse blind deconvolution (MCS-BD) problem, whose task is to
simultaneously recover a kernel $\mathbf a $ and multiple sparse inputs $\{\mathbf x_i\} _ {i …

Short-and-sparse deconvolution (SaSD) is the problem of extracting localized, recurring
motifs in signals with spatial or temporal structure. Variants of this problem arise in …

Learning overcomplete representations finds many applications in machine learning and
data analytics. In the past decade, despite the empirical success of heuristic methods …