A Computational Framework for Solving Wasserstein Lagrangian Flows
Offered By: Valence Labs via YouTube
Course Description
Overview
Explore a comprehensive lecture on a computational framework for solving Wasserstein Lagrangian flows. Delve into the dynamical formulation of optimal transport, examining various choices of underlying geometry and density path regularization. Learn how these combinations yield different variational problems, encompassing variations of optimal transport such as the Schrödinger bridge and unbalanced optimal transport. Discover a novel deep learning-based framework that approaches these problems from a unified perspective, without requiring simulation or backpropagation through learned dynamics trajectories. Examine the framework's versatility through its application to single-cell trajectory inference, demonstrating the importance of incorporating prior knowledge into dynamics for accurate predictions. Follow along as the speaker covers Lagrangian mechanics, Wasserstein Lagrangian mechanics, optimal transport, Schrödinger bridge, the computational framework, applications, results, and concludes with a Q&A session.
Syllabus
- Intro + Motivation
- Lagrangian Mechanics
- Wasserstein Lagrangian Mechanics
- Optimal Transport
- Schrödinger Bridge
- Computational Framework
Applications + Results
- Q&A
Taught by
Valence Labs
Related Courses
Drug DiscoveryUniversity of California, San Diego via Coursera 新药发现和药物靶点 | Drug Discovery and its Target
Peking University via edX Principles and Applications of NMR Spectroscopy
Indian Institute of Science Bangalore via Swayam Cell Culture Technologies
Indian Institute of Technology Kanpur via Swayam Medicinal Chemistry
Indian Institute of Technology Madras via Swayam