Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.22347 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918429615718400 |
|---|---|
| author | Han, Jipeng |
| author_facet | Han, Jipeng |
| contents | Classical frameworks like Fisher Information approximate the cost of neural adaptation only in low-density regimes, failing to explain the explosive computational overhead incurred during deep structural reconfiguration. To address this, we introduce \textbf{Intelligence Inertia}, a property derived from the fundamental non-commutativity between rules and states ($[\hat{S}, \hat{R}] = i\mathcal{D}$). Rather than claiming a new fundamental physical law, we establish a \textbf{heuristic mathematical isomorphism} between deep learning dynamics and Minkowski spacetime. Acting as an \textit{effective theory} for high-dimensional tensor evolution, we derive a non-linear cost formula mirroring the Lorentz factor, predicting a relativistic $J$-shaped inflation curve -- a computational wall where classical approximations fail. We validate this framework via three experiments: (1) adjudicating the $J$-curve divergence under high-entropy noise, (2) mapping the optimal geodesic for architecture evolution, and (3) deploying an \textbf{inertia-aware scheduler wrapper} that prevents catastrophic forgetting. Adopting this isomorphism yields an exact quantitative metric for structural resistance, advancing the stability and efficiency of intelligent agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22347 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Intelligence Inertia: Physical Isomorphism and Applications Han, Jipeng Artificial Intelligence Statistical Mechanics Machine Learning 68T05, 82C05, 94A17, 53B50 I.2.6; F.2.2; I.2.0 Classical frameworks like Fisher Information approximate the cost of neural adaptation only in low-density regimes, failing to explain the explosive computational overhead incurred during deep structural reconfiguration. To address this, we introduce \textbf{Intelligence Inertia}, a property derived from the fundamental non-commutativity between rules and states ($[\hat{S}, \hat{R}] = i\mathcal{D}$). Rather than claiming a new fundamental physical law, we establish a \textbf{heuristic mathematical isomorphism} between deep learning dynamics and Minkowski spacetime. Acting as an \textit{effective theory} for high-dimensional tensor evolution, we derive a non-linear cost formula mirroring the Lorentz factor, predicting a relativistic $J$-shaped inflation curve -- a computational wall where classical approximations fail. We validate this framework via three experiments: (1) adjudicating the $J$-curve divergence under high-entropy noise, (2) mapping the optimal geodesic for architecture evolution, and (3) deploying an \textbf{inertia-aware scheduler wrapper} that prevents catastrophic forgetting. Adopting this isomorphism yields an exact quantitative metric for structural resistance, advancing the stability and efficiency of intelligent agents. |
| title | Intelligence Inertia: Physical Isomorphism and Applications |
| topic | Artificial Intelligence Statistical Mechanics Machine Learning 68T05, 82C05, 94A17, 53B50 I.2.6; F.2.2; I.2.0 |
| url | https://arxiv.org/abs/2603.22347 |