Global convergence of COVID-19 basic reproduction number and estimation from early-time SIR dynamics [PDF]
PLoS One, 2020 The SIR ('susceptible-infectious-recovered') formulation is used to uncover the generic spread mechanisms observed by COVID-19 dynamics globally, especially in the early phases of infectious spread.
Katul GG +4 more
europepmc +3 more sources
On the Global Convergence of Particle Swarm Optimization Methods [PDF]
Applied Mathematics and Optimization, 2022 In this paper we provide a rigorous convergence analysis for the renowned particle swarm optimization method by using tools from stochastic calculus and the analysis of partial differential equations.
Hui Huang, Jinniao Qiu, Konstantin Riedl
semanticscholar +1 more source
Global Convergence of Policy Gradient Primal–Dual Methods for Risk-Constrained LQRs [PDF]
IEEE Transactions on Automatic Control, 2021 While the techniques in optimal control theory are often model-based, the policy optimization (PO) approach directly optimizes the performance metric of interest. Even though it has been an essential approach for reinforcement learning problems, there is
Feiran Zhao, Keyou You, T. Başar
semanticscholar +1 more source
Gradient Descent with Random Initialization: Fast Global Convergence for Nonconvex Phase Retrieval. [PDF]
Math Program, 2019 This paper considers the problem of solving systems of quadratic equations, namely, recovering an object of interest x♮∈Rn\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage ...
Chen Y, Chi Y, Fan J, Ma C.
europepmc +3 more sources
Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization [PDF]
Operational Research, 2020 Preconditioning and Regularization Enable Faster Reinforcement Learning Natural policy gradient (NPG) methods, in conjunction with entropy regularization to encourage exploration, are among the most popular policy optimization algorithms in contemporary ...
Shicong Cen +4 more
semanticscholar +1 more source
A Two-Level ADMM Algorithm for AC OPF With Global Convergence Guarantees [PDF]
IEEE Transactions on Power Systems, 2020 This paper proposes a two-level distributed algorithmic framework for solving the AC optimal power flow (OPF) problem with convergence guarantees. The presence of highly nonconvex constraints in OPF poses significant challenges to distributed algorithms ...
Kaizhao Sun, X. Sun
semanticscholar +1 more source
Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies [PDF]
SIAM Journal of Control and Optimization, 2019 Policy gradient (PG) methods are a widely used reinforcement learning methodology in many applications such as video games, autonomous driving, and robotics.
K. Zhang +3 more
semanticscholar +1 more source
Toward Moderate Overparameterization: Global Convergence Guarantees for Training Shallow Neural Networks [PDF]
IEEE Journal on Selected Areas in Information Theory, 2019 Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset.
Samet Oymak, M. Soltanolkotabi
semanticscholar +1 more source
Policy Optimization for H2 Linear Control with H∞ Robustness Guarantee: Implicit Regularization and Global Convergence [PDF]
SIAM Journal of Control and Optimization, 2019 Policy optimization (PO) is a key ingredient for reinforcement learning (RL). For control design, certain constraints are usually enforced on the policies to optimize, accounting for either the stability, robustness, or safety concerns on the system ...
K. Zhang, Bin Hu, T. Başar
semanticscholar +1 more source
ADMM for Efficient Deep Learning with Global Convergence [PDF]
Knowledge Discovery and Data Mining, 2019 Alternating Direction Method of Multipliers (ADMM) has been used successfully in many conventional machine learning applications and is considered to be a useful alternative to Stochastic Gradient Descent (SGD) as a deep learning optimizer.
Junxiang Wang +3 more
semanticscholar +1 more source