Gradient Surgery for Multi-Task Learning
Offered By: Yannic Kilcher via YouTube
Course Description
Overview
Explore a comprehensive analysis of gradient surgery for multi-task learning in this informative video. Delve into the challenges of multi-task learning, particularly when gradients of different tasks have significantly different magnitudes or conflicting directions. Learn about PCGrad, a method that projects conflicting gradients while maintaining optimality guarantees. Examine the three conditions in the multi-task optimization landscape that cause detrimental gradient interference and discover a general approach to avoid such interference. Investigate how this gradient surgery technique projects a task's gradient onto the normal plane of conflicting task gradients, leading to substantial improvements in efficiency and performance across challenging multi-task supervised and reinforcement learning problems. Understand the model-agnostic nature of this approach and its potential to enhance previously-proposed multi-task architectures.
Syllabus
Introduction
What is multitask learning
Example
Loss Function
Theorems
Conditions
Evil Try Effect
MultiTask Learning
Taught by
Yannic Kilcher
Related Courses
Structuring Machine Learning ProjectsDeepLearning.AI via Coursera Структурирование проектов по машинному обучению
DeepLearning.AI via Coursera 머신 러닝 프로젝트 구조화
DeepLearning.AI via Coursera Stanford CS330: Deep Multi-Task and Meta Learning
Stanford University via YouTube Stanford Seminar - The Next Generation of Robot Learning
Stanford University via YouTube