2 papers
cs.LG2024
Comparing analytic and data-driven approaches to parameter identifiability: A power systems case study
Nikolaos Evangelou, Alexander M. Stankovic, Ioannis G. Kevrekidis +1
Parameter identifiability refers to the capability of accurately inferring the parameter values of a model from its observations (data). Traditional analysis methods exploit analyt…
math.OC2023
A New Perspective of Accelerated Gradient Methods: The Controlled Invariant Manifold Approach
Revati Gunjal, Sushama Wagh, Syed Shadab Nayyer +2
Gradient Descent (GD) is a ubiquitous algorithm for finding the optimal solution to an optimization problem. For reduced computational complexity, the optimal solution $\mathrm{x^*…