ENEM 747 Optimization Methods in Signal Processing and Machine Learning

Credit 3
Optimization methods that are suitable for large-scale problems arising in data science and machine learning applications. Optimization algorithms are explored for solving convex/nonconvex, and smooth/nonsmooth problems appearing in signal processing and machine learning. The efficacy of these methods, which include (sub)gradient methods, proximal methods, Nesterov’s accelerated methods, ADMM, quasi-Newton, trust-region, cubic regularization methods, and (some of) their stochastic variants are studied. Constraint optimization over Riemannian manifold is also included.

Academic Affairs

Quick Office Links

Student Services

Research

ENEM 747 Optimization Methods in Signal Processing and Machine Learning

Academic Affairs﻿

ENEM 747 Optimization Methods in Signal Processing and Machine Learning

Academic Affairs