23 citations · 47 across the 10 of their papers we have counts for
11 papers
Local linear convergence of gradient methods for overparameterized Gaussian mixtures
Jingxing Wang, Vasileios Charisopoulos, Maryam Fazel
We study the problem of learning Gaussian mixture models under overparameterization. Prior work has shown that while overparameterization is essential for avoiding spurious local o…
Robust and differentially private stochastic linear bandits
Vasileios Charisopoulos, Hossein Esfandiari, Vahab Mirrokni
In this paper, we study the stochastic linear bandit problem under the additional requirements of differential privacy, robustness and batched observations. In particular, we assum…
Communication-efficient distributed eigenspace estimation with arbitrary node failures
Vasileios Charisopoulos, Anil Damle
We develop an eigenspace estimation algorithm for distributed environments with arbitrary node failures, where a subset of computing nodes can return structurally valid but otherwi…
A superlinearly convergent subgradient method for sharp semismooth problems
Vasileios Charisopoulos, Damek Davis
Subgradient methods comprise a fundamental class of nonsmooth optimization algorithms. Classical results show that certain subgradient methods converge sublinearly for general Lips…
Communication-efficient distributed eigenspace estimation
Vasileios Charisopoulos, Austin R. Benson, Anil Damle
Distributed computing is a standard way to scale up machine learning and data science algorithms to process large amounts of data. In such settings, avoiding communication amongst…
Entrywise convergence of iterative methods for eigenproblems
Vasileios Charisopoulos, Austin R. Benson, Anil Damle
Several problems in machine learning, statistics, and other fields rely on computing eigenvectors. For large scale problems, the computation of these eigenvectors is typically perf…
Incrementally Updated Spectral Embeddings
Vasileios Charisopoulos, Austin R. Benson, Anil Damle
Several fundamental tasks in data science rely on computing an extremal eigenspace of size , where is the underlying problem dimension. For example, spectral clusterin…
Stochastic algorithms with geometric step decay converge linearly on sharp functions
Damek Davis, Dmitriy Drusvyatskiy, Vasileios Charisopoulos
Stochastic (sub)gradient methods require step size schedule tuning to perform well in practice. Classical tuning strategies decay the step size polynomially and lead to optimal sub…
Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
Vasileios Charisopoulos, Yudong Chen, Damek Davis +3
The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem often exhibit an undes…
Composite optimization for robust blind deconvolution
Vasileios Charisopoulos, Damek Davis, Mateo Díaz +1
The blind deconvolution problem seeks to recover a pair of vectors from a set of rank one bilinear measurements. We consider a natural nonsmooth formulation of the problem and show…
A Tropical Approach to Neural Networks with Piecewise Linear Activations
Vasileios Charisopoulos, Petros Maragos
We present a new, unifying approach following some recent developments on the complexity of neural networks with piecewise linear activations. We treat neural network layers with p…