ITCVLGMay 17, 2023

The Principle of Uncertain Maximum Entropy

arXiv:2305.09868v6
Originality Incremental advance
AI Analysis

This addresses a limitation in statistical estimation for researchers and practitioners, but it appears incremental as it builds directly on a classic principle.

The paper tackles the problem that the Principle of Maximum Entropy requires error-free information by relaxing this requirement using a memoryless communication channel framework, resulting in a new principle that provides an upper bound on entropy and shows experimental performance relative to existing methods.

The Principle of Maximum Entropy is a rigorous technique for estimating an unknown distribution given partial information while simultaneously minimizing bias. However, an important requirement for applying the principle is that the available information be provided error-free (Jaynes, 1982). We relax this requirement using a memoryless communication channel as a framework to derive a new, more general principle. We show our new principle provides an upper bound on the entropy of the unknown distribution and the amount of information lost due to the use of a given communications channel is unknown unless the unknown distribution's entropy is also known. Using our new principle we provide a new interpretation of the classic principle and experimentally show its performance relative to the classic principle and some other generally applicable solutions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes