Stochastic Gradient Descent Methods with Biased Estimators
Offered By: VinAI via YouTube
Course Description
Overview
Explore a comprehensive seminar on stochastic gradient descent methods using biased estimators, presented by Quoc Tran-Dinh from the University of North Carolina at Chapel Hill. Delve into recent advancements in gradient descent algorithms, their variants, and practical applications in machine learning. Gain insights into the speaker's research on stochastic gradient-based methods for large-scale optimization and minimax problems, with potential applications in deep learning, statistical learning, generative adversarial nets, and federated learning. Learn about the collaborative work with researchers from UNC and IBM, and understand the theoretical and practical aspects of these cutting-edge optimization techniques.
Syllabus
[Seminar Series] Stochastic Gradient Descent Methods with Biased Estimators
Taught by
VinAI
Related Courses
On Gradient-Based Optimization - Accelerated, Distributed, Asynchronous and StochasticSimons Institute via YouTube Optimisation - An Introduction: Professor Coralia Cartis, University of Oxford
Alan Turing Institute via YouTube Optimization in Signal Processing and Machine Learning
IEEE Signal Processing Society via YouTube Methods for L_p-L_q Minimization in Image Restoration and Regression - SIAM-IS Seminar
Society for Industrial and Applied Mathematics via YouTube Certificates of Nonnegativity and Their Applications in Theoretical Computer Science
Society for Industrial and Applied Mathematics via YouTube