Energy Discrepancies: A Score-Independent Loss for Energy-Based Models

Oct-9-2025, 01:05:42 GMT–Neural Information Processing Systems

We propose a novel loss function called Energy Discrepancy (ED) which does not rely on the computation of scores or expensive Markov chain Monte Carlo.

artificial intelligence, energy discrepancy, machine learning, (14 more...)

Neural Information Processing Systems

Oct-9-2025, 01:05:42 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Jordan (0.04)
- Europe > Germany
  - Rhineland-Palatinate > Kaiserslautern (0.04)
- North America > United States
  - California > San Diego County
    - San Diego (0.04)
  - Virginia > Arlington County
    - Arlington (0.04)

Industry:
- Education (0.46)
- Health & Medicine (0.46)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning
      - Learning Graphical Models > Undirected Networks
        Markov Models (0.34)
      - Neural Networks > Deep Learning (0.67)
      - Statistical Learning (1.00)
    - Representation & Reasoning > Uncertainty (1.00)
    - Vision (0.93)
  - Sensing and Signal Processing > Image Processing (0.93)

Duplicate Docs Excel Report

Title
Energy Discrepancies: A Score-Independent Loss for Energy-Based Models

Similar Docs Excel Report more

Title	Similarity	Source
None found