Explore a 34-minute lecture by Victoria Kostina from the California Institute of Technology, presented at the Simons Institute, focusing on Differentially Quantized Gradient Methods. Delve into information-theoretic approaches for developing trustworthy machine learning systems, gaining insights into advanced techniques for optimizing gradient-based algorithms through quantization methods.
Overview
Syllabus
Differentially Quantized Gradient Methods
Taught by
Simons Institute
Related Courses
-
Variational Formulations and Distributed Convex Optimization Methods for...
-
Practical Predictive Analytics: Models and Methods
2.0 -
Deep Reinforcement Learning in Python
-
Decision Making with Information-Theoretic Constraints
-
Distributed Optimization and Machine Learning
-
Global Guarantees for Policy Gradient Methods
