About Lukang Sun Lukang Sun Ph.D. Student, Computer Science Lukang Sun is a Ph.D. student majoring in Computer Science under the supervision of Prof. Peter Richtarik since 2021. At KAUST, Lukang Sun’s research focuses on interacting particle systems and their applications to machine learning, engineering, etc. Events Presented Events May 26 - Jun 1, 2024 Stein Variational Gradient Descent and Consensus-Based Optimization: Towards a Convergence Analysis and Generalization Lukang Sun, Ph.D. Student, Computer Science May 30, 11:00 - 14:00 B3 L5 R5220 The first part of the dissertation presents a study on the convergence properties of Stein Variational Gradient Descent (SVGD), a sampling algorithm with applications in machine learning. The research delves into the theoretical analysis of SVGD in the population limit, focusing on its behavior under various conditions, including the Talagrand’s inequality T1 and the (L0, L1)−smoothness condition. The study also introduces an improved version of SVGD with importance weights, demonstrating its potential to accelerate convergence and enhance stability.
Stein Variational Gradient Descent and Consensus-Based Optimization: Towards a Convergence Analysis and Generalization Lukang Sun, Ph.D. Student, Computer Science May 30, 11:00 - 14:00 B3 L5 R5220 The first part of the dissertation presents a study on the convergence properties of Stein Variational Gradient Descent (SVGD), a sampling algorithm with applications in machine learning. The research delves into the theoretical analysis of SVGD in the population limit, focusing on its behavior under various conditions, including the Talagrand’s inequality T1 and the (L0, L1)−smoothness condition. The study also introduces an improved version of SVGD with importance weights, demonstrating its potential to accelerate convergence and enhance stability.
