Artificial Intelligence

    

Temporal Information Curvature: A Robust Diagnostic for Instability in Machine Learning Training Dynamics

Authors: Dhruvil Chodavadiya Rajeshbhai

Training loss metrics in machine learning are often reactive, failing to anticipate instability until divergence occurs. I propose Temporal Information Curvature (TIC), a novel time-aware diagnostic that measures curvature, nonlinear feedback, and memory effects in training dynamics. Through simulations across clean, unstable, and noisy loss curves, I show that TIC detects instability early, remaining robust to noise and outperforming derivative-only metrics. TIC also enables plug-and-play decision logic for training optimization, with applications extending to finance and signal processing. This work establishes TIC as a versatile and reliable tool for temporal analysis in machine learning and beyond.

Comments: 7 Pages. © 2025 Dhruvil Chodavadiya Rajeshbhai

Download: PDF

Submission history

[v1] 2025-06-14 02:37:38

Unique-IP document downloads: 212 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus