Search Results for author: Orlando Romero

Found 7 papers, 0 papers with code

Finite-Time Convergence in Continuous-Time Optimization

no code implementations ICML 2020 Orlando Romero, Mouhacine Benosman

In this paper, we investigate a Lyapunov-like differential inequality that allows us to establish finite-time stability of a continuous-time state-space dynamical system represented via a multivariate ordinary differential equation or differential inclusion.

First-Order Optimization Algorithms via Discretization of Finite-Time Convergent Flows

no code implementations1 Jan 2021 Mouhacine Benosman, Orlando Romero, Anoop Cherian

In this paper, we investigate in the context of deep neural networks, the performance of several discretization algorithms for two first-order finite-time optimization flows.

First-Order Optimization Inspired from Finite-Time Convergent Flows

no code implementations6 Oct 2020 Siqi Zhang, Mouhacine Benosman, Orlando Romero, Anoop Cherian

In this paper, we investigate the performance of two first-order optimization algorithms, obtained from forward Euler discretization of finite-time optimization flows.

A Dynamical Systems Approach for Convergence of the Bayesian EM Algorithm

no code implementations23 Jun 2020 Orlando Romero, Subhro Das, Pin-Yu Chen, Sérgio Pequito

Out of the recent advances in systems and control (S\&C)-based analysis of optimization algorithms, not enough work has been specifically dedicated to machine learning (ML) algorithms and its applications.

Finite-Time Convergence of Continuous-Time Optimization Algorithms via Differential Inclusions

no code implementations18 Dec 2019 Orlando Romero, Mouhacine Benosman

In this paper, we propose two discontinuous dynamical systems in continuous time with guaranteed prescribed finite-time local convergence to strict local minima of a given cost function.

Analysis of a Generalized Expectation-Maximization Algorithm for Gaussian Mixture Models: A Control Systems Perspective

no code implementations3 Mar 2019 Sarthak Chatterjee, Orlando Romero, Sérgio Pequito

The Expectation-Maximization (EM) algorithm is one of the most popular methods used to solve the problem of parametric distribution-based clustering in unsupervised learning.

Cannot find the paper you are looking for? You can Submit a new open access paper.