Search Results for author:
Found 10 papers, 4 papers with code
Double-Loop Unadjusted Langevin Algorithm
A well-known first-order method for sampling from log-concave probability distributions is the Unadjusted Langevin Algorithm (ULA).
Subquadratic Overparameterization for Shallow Neural Networks
Overparameterization refers to the important phenomenon where the width of a neural network is chosen such that learning algorithms can provably attain zero loss in nonconvex training.
Nonlinear matrix recovery using optimization on the Grassmann manifold
We investigate the problem of recovering a partially observed high-rank matrix whose columns obey a nonlinear structure such as a union of subspaces, an algebraic variety or grouped in clusters.
Principal Component Hierarchy for Sparse Quadratic Programs
We propose a novel approximation hierarchy for cardinality-constrained, convex quadratic programs that exploits the rank-dominating eigenvectors of the quadratic matrix.
The Nonconvex Geometry of Linear Inverse Problems
The gauge function, closely related to the atomic norm, measures the complexity of a statistical model, and has found broad applications in machine learning and statistical signal processing.
Limitations of Implicit Bias in Matrix Sensing: Initialization Rank Matters
In matrix sensing, we first numerically identify the sensitivity to the initialization rank as a new limitation of the implicit bias of gradient flow.
Information Theory Information Theory Optimization and Control
Nearly Minimal Over-Parametrization of Shallow Neural Networks
A recent line of work has shown that an overparametrized neural network can perfectly fit the training data, an otherwise often intractable nonconvex optimization problem.
Fast and Provable ADMM for Learning with Generative Priors
We focus on the special case where such constraint arises from the specification that a variable should lie in the range of a neural network.
Scalable Learning-Based Sampling Optimization for Compressive Dynamic MRI
Compressed sensing applied to magnetic resonance imaging (MRI) allows to reduce the scanning time by enabling images to be reconstructed from highly undersampled data.
MOSES: A Streaming Algorithm for Linear Dimensionality Reduction
This paper introduces Memory-limited Online Subspace Estimation Scheme (MOSES) for both estimating the principal components of data and reducing its dimension.
Information Theory Information Theory
