J Sun, Q Qu, J Wright - IEEE Transactions on Information …, 2016 - ieeexplore.ieee.org
We consider the problem of recovering a complete (ie, square and invertible) matrix A 0, from Y∈ R n× p with Y= A 0 X 0, provided X 0 is sufficiently sparse. This recovery problem is …
Single-index models are a class of functions given by an unknown univariate``link''function applied to an unknown one-dimensional projection of the input. These models are …
When training deep neural networks for classification tasks, an intriguing empirical phenomenon has been widely observed in the last-layer classifiers and features, where (i) …
We provide the first global optimization landscape analysis of Neural Collapse--an intriguing empirical phenomenon that arises in the last-layer classifiers and features of neural …
We lower bound the complexity of finding ϵ-stationary points (with gradient norm at most ϵ) using stochastic first-order methods. In a well-studied model where algorithms access …
This paper shows that a perturbed form of gradient descent converges to a second-order stationary point in a number iterations which depends only poly-logarithmically on …
Over past several years, machine learning, or more generally artificial intelligence, has generated overwhelming research interest and attracted unprecedented public attention. As …
M Nouiehed, M Sanjabi, T Huang… - Advances in …, 2019 - proceedings.neurips.cc
Recent applications that arise in machine learning have surged significant interest in solving min-max saddle point games. This problem has been extensively studied in the convex …
Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond. By …