Lectures related to Plurisubharmonic function

Covers faster gradient descent methods and projected gradient descent for constrained optimization in machine learning.

Discusses advanced optimization techniques, focusing on faster and projected gradient descent methods in machine learning.

Explores the convergence proof of Stochastic Gradient Descent with strongly-convex functions and the impact of step-size on convergence properties.

Explores the analytic continuation of the zeta function and its relation to holomorphic functions and natural numbers.

Explores Laplace approximation for integral estimation using smooth convex functions and Gaussian distribution.

Discusses interpreting convergence plots in optimization, identifying bugs based on convergence rates, and understanding optimization algorithms.