Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions
–Neural Information Processing Systems
The profile of a sample is the multiset of its symbol frequencies. We show that for samples of discrete distributions, profile entropy is a fundamental measure unifying the concepts of estimation, inference, and compression.
Neural Information Processing Systems
Oct-2-2025, 21:23:50 GMT
- Country:
- North America > United States (0.45)
- Genre:
- Research Report (0.46)
- Technology:
- Information Technology
- Information Management (0.68)
- Data Science (0.67)
- Artificial Intelligence
- Natural Language (1.00)
- Machine Learning (1.00)
- Representation & Reasoning > Uncertainty (0.93)
- Information Technology