47 citations · 189 across the 27 of their papers we have counts for
34 papers
A Unified Model for High-Resolution ODEs: New Insights on Accelerated Methods
Hoomaan Maskan, Konstantinos C. Zygalakis, Armin Eftekhari +1
Recent work on high-resolution ordinary differential equations (HR-ODEs) captures fine nuances among different momentum-based optimization methods, leading to accurate theoretical…
Computing second-order points under equality constraints: revisiting Fletcher's augmented Lagrangian
Florentin Goyens, Armin Eftekhari, Nicolas Boumal
We address the problem of minimizing a smooth function under smooth equality constraints. Under regularity assumptions on these constraints, we propose a notion of approximate firs…
The Forward-Backward Envelope for Sampling with the Overdamped Langevin Algorithm
Armin Eftekhari, Luis Vargas, Konstantinos Zygalakis
In this paper, we analyse a proximal method based on the idea of forward-backward splitting for sampling from distributions with densities that are not necessarily smooth. In parti…
Over-Parametrized Matrix Factorization in the Presence of Spurious Stationary Points
Armin Eftekhari
Motivated by the emerging role of interpolating machines in signal processing and machine learning, this work considers the computational aspects of over-parametrized matrix factor…
Subquadratic Overparameterization for Shallow Neural Networks
Chaehwan Song, Ali Ramezani-Kebrya, Thomas Pethick +2
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 train…
Nonlinear matrix recovery using optimization on the Grassmann manifold
Florentin Goyens, Coralia Cartis, Armin Eftekhari
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 groupe…