Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling

Nov-19-2025, 17:48:24 GMT–Neural Information Processing Systems

To solve this optimization, we propose a simulation-free training objective with a model parameterization that imposes the desired boundary conditions by design.

artificial intelligence, machine learning, transition path, (18 more...)

Neural Information Processing Systems

Nov-19-2025, 17:48:24 GMT

Conferences PDF

Country:
- Europe
  - France (0.04)
  - Romania > Black Sea (0.04)
  - United Kingdom
    - England > Cambridgeshire
      - Cambridge (0.04)
    - North Sea > Southern North Sea (0.04)
- North America
  - Canada
    - Ontario > Toronto (0.14)
    - Quebec > Montreal (0.04)
  - United States > Massachusetts
    - Middlesex County > Reading (0.04)

Genre:
- Research Report > Experimental Study (0.93)

Industry:
- Energy (0.93)
- Government > Regional Government (0.46)
- Health & Medicine (0.67)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks (1.00)
    - Representation & Reasoning (1.00)
  - Data Science (0.68)

Duplicate Docs Excel Report

Title
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling

Similar Docs Excel Report more

Title	Similarity	Source
None found