Backpropagation as Physical Relaxation: Exact Gradients in Finite Time

arXiv:2602.02281v11 citationsh-index: 20
Originality Highly original
AI Analysis

This provides a rigorous foundation for exact gradient computation in analog and neuromorphic substrates, addressing a problem for hardware designers and theorists, though it is incremental in linking physical dynamics to existing algorithms.

The paper tackles the problem of understanding backpropagation as a physical process, showing it emerges exactly as the finite-time relaxation of a dynamical system, and proves that unit-step Euler discretization recovers standard backpropagation exactly in 2L steps for an L-layer network.

Backpropagation, the foundational algorithm for training neural networks, is typically understood as a symbolic computation that recursively applies the chain rule. We show it emerges exactly as the finite-time relaxation of a physical dynamical system. By formulating feedforward inference as a continuous-time process and applying Lagrangian theory of non-conservative systems to handle asymmetric interactions, we derive a global energy functional on a doubled state space encoding both activations and sensitivities. The saddle-point dynamics of this energy perform inference and credit assignment simultaneously through local interactions. We term this framework ''Dyadic Backpropagation''. Crucially, we prove that unit-step Euler discretization, the natural timescale of layer transitions, recovers standard backpropagation exactly in precisely 2L steps for an L-layer network, with no approximations. Unlike prior energy-based methods requiring symmetric weights, asymptotic convergence, or vanishing perturbations, our framework guarantees exact gradients in finite time. This establishes backpropagation as the digitally optimized shadow of a continuous physical relaxation, providing a rigorous foundation for exact gradient computation in analog and neuromorphic substrates where continuous dynamics are native.

Foundations

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

Your Notes