A Allibhoy, J Cortés - IEEE Transactions on Automatic Control, 2023 - ieeexplore.ieee.org
This article considers the problem of designing a continuous-time dynamical system that solves a constrained nonlinear optimization problem and makes the feasible set forward …
H Maskan, K Zygalakis… - Advances in Neural …, 2024 - proceedings.neurips.cc
We consider unconstrained minimization of smooth convex functions. We propose a novel variational perspective using forced Euler-Lagrange equation that allows for studying high …
We consider the problem of minimizing a non-convex function over a smooth manifold M. We propose a novel algorithm, the Orthogonal Directions Constrained Gradient Method …
In this chapter, we identify fundamental geometric structures that underlie the problems of sampling, optimization, inference, and adaptive decision-making. Based on this …
X Shi, G Wen, J Cao, X Yu - IEEE Transactions on Automatic …, 2022 - ieeexplore.ieee.org
In distributed optimization (DO), the designed algorithms are expected to have a fast convergence rate but less computation cost. Moreover, the boundedness of the control …
A Lonardi, C De Bacco - Physical Review Letters, 2023 - APS
Global infrastructure robustness and local transport efficiency are critical requirements for transportation networks. However, since passengers often travel greedily to maximize their …
L Leconte, S Schechtman… - … Conference on Artificial …, 2023 - proceedings.mlr.press
In this paper, we develop a new algorithm, Annealed Skewed SGD-AskewSGD-for training deep neural networks (DNNs) with quantized weights. First, we formulate the training of …
P Kolev, G Martius… - Advances in Neural …, 2024 - proceedings.neurips.cc
In many applications, learning systems are required to process continuous non-stationary data streams. We study this problem in an online learning framework and propose an …
P Mestres, J Cortés - 2023 62nd IEEE Conference on Decision …, 2023 - ieeexplore.ieee.org
This paper considers the problem of designing a dynamical system to solve constrained optimization problems in a distributed way and in an anytime fashion (ie, such that the …