Efficient and Modular Implicit Differentiation - Machine Learning Research Paper Explained
Offered By: Yannic Kilcher via YouTube
Course Description
Overview
Explore a comprehensive video explanation of a machine learning research paper on efficient and modular implicit differentiation. Delve into advanced topics like automatic differentiation of inner optimizations, meta-learning, optimization unrolling, and the implicit function theorem. Learn about a unified framework for implicit differentiation of optimization problems that combines autodiff benefits with efficiency and modularity. Discover how this approach can be applied to bi-level optimization problems and sensitivity analysis in molecular dynamics. Follow along with the detailed outline covering key concepts, mathematical foundations, and experimental results presented by the speaker.
Syllabus
- Intro & Overview
- Automatic Differentiation of Inner Optimizations
- Example: Meta-Learning
- Unrolling Optimization
- Unified Framework Overview & Pseudocode
- Implicit Function Theorem
- More Technicalities
- Experiments
Taught by
Yannic Kilcher
Related Courses
Introduction to Neural Networks and PyTorchIBM via Coursera Regression with Automatic Differentiation in TensorFlow
Coursera Project Network via Coursera Neural Network from Scratch in TensorFlow
Coursera Project Network via Coursera Customising your models with TensorFlow 2
Imperial College London via Coursera PyTorch Fundamentals
Microsoft via Microsoft Learn