Advances in Computer-Assisted Design and Analysis of First-Order Optimization Methods and Related Problems
First-order methods are optimization algorithms that can be described and analyzed using the values and gradients of the functions to be minimized. These methods have become the main workhorses for modern large-scale optimization and machine learning due to their low iteration costs, minimal memory...
Main Author: | Das Gupta, Shuvomoy |
---|---|
Other Authors: | Freund, Robert M. |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2024
|
Online Access: | https://hdl.handle.net/1721.1/155495 https://orcid.org/0000-0001-9650-8746 |
Similar Items
-
Branch-and-bound performance estimation programming: a unified methodology for constructing optimal optimization methods
by: Das Gupta, Shuvomoy, et al.
Published: (2024) -
Relatively Smooth Convex Optimization by First-Order Methods, and Applications
by: Nesterov, Yurii, et al.
Published: (2019) -
New computational guarantees for solving convex optimization problems with first order methods, via a function growth condition measure
by: Freund, Robert Michael, et al.
Published: (2018) -
An accelerated first-order method for solving SOS relaxations of unconstrained polynomial optimization problems
by: Bertsimas, Dimitris J., et al.
Published: (2014) -
Discontinuous Galerkin methods for first-order hyperbolic problems
by: Brezzi, F, et al.
Published: (2004)