paper-with-me

홈 › Papers

Extended critical regimes of deep neural networks

2022-03-24 · Cheng Kevin Qu, Asem Wardak, Pulin Gong

Deep neural networks (DNNs) have been successfully applied to many real-world problems, but a complete understanding of their dynamical and computational principles is still lacking. Conventional theoretical frameworks for analysing DNNs often assume random networks with coupling weights obeying Gaussian statistics. However, non-Gaussian, heavy-tailed coupling is a ubiquitous phenomenon in DNNs. Here, by weaving together theories of heavy-tailed random matrices and non-equilibrium statistical physics, we develop a new type of mean field theory for DNNs which predicts that heavy-tailed weights enable the emergence of an extended critical regime without fine-tuning parameters. In this extended critical regime, DNNs exhibit rich and complex propagation dynamics across layers. We further elucidate that the extended criticality endows DNNs with profound computational advantages: balancing the contraction as well as expansion of internal neural representations and speeding up training processes, hence providing a theoretical guide for the design of efficient neural architectures.

📄 PDF Abstract BibTeX arXiv:2203.12967

Code (1)

CKQu1/extended-criticality-dnn 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Emergence of Hopf bifurcation in an extended SIR dynamic

2021-07-22 · Arash Roostaei, Hadi Barzegar, Fakhteh Ghanbarnejad

In this paper, the SIR dynamics is extended by considering another compartmental which represents hospitalization of the critical cases. So a system of differential equations with four blocks is considered when there is …

Online learning of Koopman operator using streaming data from different dynamical regimes

2024-07-18 · Kartik Loya, Phanindra Tallapragada

The paper presents a framework for online learning of the Koopman operator using streaming data. Many complex systems for which data-driven modeling and control are sought provide streaming sensor data, the abundance of …

A Stochastic Dynamical Theory of LLM Self-Adversariality: Modeling Severity Drift as a Critical Process

2025-01-28 · Jack David Carson

This paper introduces a continuous-time stochastic dynamical framework for understanding how large language models (LLMs) may self-amplify latent biases or toxicity through their own chain-of-thought reasoning. The model…

Temporal Complexity and Self-Organization in an Exponential Dense Associative Memory Model

2026-01-16 · Marco Cafiso, Paolo Paradisi arxiv

Dense Associative Memory (DAM) models generalize the classical Hopfield model by incorporating n-body or exponential interactions that greatly enhance storage capacity. While the criticality of DAM models has been largel…

Multi-Phase Spacecraft Trajectory Optimization via Transformer-Based Reinforcement Learning

2025-11-14 · Amit Jain, Victor Rodriguez-Fernandez, Richard Linares arxiv

Autonomous spacecraft control for mission phases such as launch, ascent, stage separation, and orbit insertion remains a critical challenge due to the need for adaptive policies that generalize across dynamically distinc…

Reinforcement Learning