
Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery
We study the robust recovery of a lowrank matrix from sparsely and gros...
read it

Only Train Once: A OneShot Neural Network Training And Pruning Framework
Structured pruning is a commonly used technique in deploying deep neural...
read it

A Geometric Analysis of Neural Collapse with Unconstrained Features
We provide the first global optimization landscape analysis of Neural Co...
read it

CDFI: CompressionDriven Network Design for Frame Interpolation
DNNbased frame interpolation–that generates the intermediate frames giv...
read it

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
Normalization techniques have become a basic component in modern convolu...
read it

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Overparameterization
Recent advances have shown that implicit bias of gradient descent on ove...
read it

Recovery and Generalization in OverRealized Dictionary Learning
In over two decades of research, the field of dictionary learning has ga...
read it

Orthant Based Proximal Stochastic Gradient Method for ℓ_1Regularized Optimization
Sparsityinducing regularization problems are ubiquitous in machine lear...
read it

Finding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications
The problem of finding the sparsest vector (direction) in a low dimensio...
read it

Analysis of the Optimization Landscapes for Overcomplete Representation Learning
We study nonconvex optimization landscapes for learning overcomplete rep...
read it

ViewpointAware Loss with Angular Regularization for Person ReIdentification
Although great progress in supervised person reidentification (ReID) h...
read it

Nonsmooth Optimization over Stiefel Manifold: Riemannian Subgradient Methods
Nonsmooth Riemannian optimization is a still under explored subfield of ...
read it

A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution
We study the multichannel sparse blind deconvolution (MCSBD) problem, ...
read it

Incremental Methods for Weakly Convex Optimization
We consider incremental algorithms for solving weakly convex optimizatio...
read it

Provable Bregmandivergence based Methods for Nonconvex and NonLipschitz Problems
The (global) Lipschitz smoothness condition is crucial in establishing t...
read it

Dual Principal Component Pursuit: Probability Analysis and Efficient Algorithms
Recent methods for learning a linear subspace from data corrupted by out...
read it

Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization
Symmetric nonnegative matrix factorization (NMF), a special but importan...
read it

Global Optimality in Distributed Lowrank Matrix Factorization
We study the convergence of a variant of distributed gradient descent (D...
read it

Nonconvex Robust Lowrank Matrix Recovery
In this paper we study the problem of recovering a lowrank matrix from ...
read it

The Global Optimization Geometry of Shallow Linear Neural Networks
We examine the squared error loss landscape of shallow linear neural net...
read it

Convergence Analysis of Alternating Nonconvex Projections
We consider the convergence properties for alternating projection algori...
read it

ROAST: Rapid Orthogonal Approximate Slepian Transform
In this paper, we provide a Rapid Orthogonal Approximate Slepian Transfo...
read it

Geometry of Factored Nuclear Norm Regularization
This work investigates the geometry of a nonconvex reformulation of mini...
read it
Zhihui Zhu
is this you? claim profile