Functional Gradient Descent Methods for Optimization and Sampling
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore advanced machine learning concepts in this seminar on Functional Gradient Descent methods for optimization and sampling. Delve into the research of Dr. Qiang Liu, Assistant Professor of Computer Science at the University of Texas at Austin, as he discusses innovative applications of gradient descent beyond traditional Euclidean spaces. Learn about Stein variational gradient descent and its use in drawing samples from complex distributions. Discover how splitting steepest neural architecture descent can be applied to jointly estimate neural network weights and structures. Examine extensions of these techniques for handling constrained, bilevel, and multi-objective optimization problems. Gain insights into cutting-edge approaches that push the boundaries of statistical learning methods for high-dimensional and complex data.