# Analog Physical Systems Can Exhibit Double Descent

arXiv: https://arxiv.org/abs/2511.17825 · HTML: https://mlsanity.com/paper/2511.17825/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Builds on (most cited first, 17 of 17)

- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation](https://mlsanity.com/paper/1602.05179/) (2016)
- [Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems](https://mlsanity.com/paper/2104.13386/) (2021)
- [A jamming transition from under- to over-parametrization affects loss landscape and generalization](https://mlsanity.com/paper/1810.09665/) (2018)
- [Training of Physical Neural Networks](https://mlsanity.com/paper/2406.03372/) (2024)
- [Backpropagation-free Training of Deep Physical Neural Networks](https://mlsanity.com/paper/2304.11042/) (2023)
- [Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle](https://mlsanity.com/paper/2303.14151/) (2023)
- [Training an Ising Machine with Equilibrium Propagation](https://mlsanity.com/paper/2305.18321/) (2023)
- [Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized models](https://mlsanity.com/paper/2010.13933/) (2020)
- [Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial](https://mlsanity.com/paper/2311.00537/) (2023)
- [Algorithm for Training Neural Networks on Resistive Device Arrays](https://mlsanity.com/paper/1909.07908/) (2019)
- [Frequency propagation: Multi-mechanism learning in nonlinear physical networks](https://mlsanity.com/paper/2208.08862/) (2022)
- [Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models](https://mlsanity.com/paper/2409.19315/) (2024)
- [Arbitrary control over multimode wave propagation for machine learning](https://mlsanity.com/paper/2402.17750/) (2024)
- [Multiplexed gradient descent: Fast online training of modern datasets on hardware neural networks without backpropagation](https://mlsanity.com/paper/2303.03986/) (2023)
- [Desynchronous Learning in a Physics-Driven Learning Network](https://mlsanity.com/paper/2201.04626/) (2022)
- [Training all-mechanical neural networks for task learning through in situ backpropagation](https://mlsanity.com/paper/2404.15471/) (2024)

## Abstract (arXiv)

An important component of the success of large AI models is double descent, in which networks avoid overfitting as they grow relative to the amount of training data, instead improving their performance on unseen data. Here we demonstrate double descent in a decentralized analog network of self-adjusting resistive elements. This system trains itself and performs tasks without a digital processor, offering potential gains in energy efficiency and speed -- but must endure component non-idealities. We find that standard training fails to yield double descent, but a modified protocol that accommodates this inherent imperfection succeeds. Our findings show that analog physical systems, if appropriately trained, can exhibit behaviors underlying the success of digital AI. Further, they suggest that biological systems might similarly benefit from over-parameterization.