Tight Stability Convergence And Robustness Bounds For Predictive Coding Networks
ASecurity**arXiv ID:** 2410.04708 **Authors:** Ankur Mali, Tommaso Salvatori, Alexander Ororbia **Published:** 2024-10-07T02:57:26Z **Abstract:** Energy-based learning algorithms, such as predictive coding (PC), have garnered significant attention in the machine learning community due to their theoretical properties, such as local operations and biologically plausible mechanisms for error correction. In this work, we rigorously analyze the stability, robustness, and convergence of PC through the lens ...
- 3 stars
- 0 votes
- 0 copies
- 3 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill tight-stability-convergence-and-robustness-bounds-for-predictive-coding-networks --agent claude-codeAre you the author of Tight Stability Convergence And Robustness Bounds For Predictive Coding Networks?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-tight-stability-convergence-and-robustness-bounds)# Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks
**arXiv ID:** 2410.04708
**Authors:** Ankur Mali, Tommaso Salvatori, Alexander Ororbia
**Published:** 2024-10-07T02:57:26Z
**Abstract:**
Energy-based learning algorithms, such as predictive coding (PC), have garnered significant attention in the machine learning community due to their theoretical properties, such as local operations and biologically plausible mechanisms for error correction. In this work, we rigorously analyze the stability, robustness, and convergence of PC through the lens of dynamical systems theory. We show that, first, PC is Lyapunov stable under mild assumptions on its loss and residual energy functions, which implies intrinsic robustness to small random perturbations due to its well-defined energy-minimizing dynamics. Second, we formally establish that the PC updates approximate quasi-Newton methods by incorporating higher-order curvature information, which makes them more stable and able to converge with fewer iterations compared to models trained via backpropagation (BP). Furthermore, using this dynamical framework, we provide new theoretical bounds on the similarity between PC and other algorithms, i.e., BP and target propagation (TP), by precisely characterizing the role of higher-order derivatives. These bounds, derived through detailed analysis of the Hessian structures, show that PC is significantly closer to quasi-Newton updates than TP, providing a deeper understanding of the stability and efficiency of PC compared to conventional learning methods.
## Skill Description
This skill is generated from the arXiv paper: Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks (2410.04708).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2410.04708](http://arxiv.org/abs/2410.04708v1)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.