# The Copycat Perceptron: Smashing Barriers Through Collective Learning

arXiv: https://arxiv.org/abs/2308.03743 · HTML: https://mlsanity.com/paper/2308.03743/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 6 of its 30 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 6 of 6)

- [Statistical physics of inference: Thresholds and algorithms](https://mlsanity.com/paper/1511.02476/) (2015)
- [Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes](https://mlsanity.com/paper/1605.06444/) (2016)
- [Local entropy as a measure for sampling solutions in Constraint Satisfaction Problems](https://mlsanity.com/paper/1511.05634/) (2015)
- [Learning curves for the multi-class teacher-student perceptron](https://mlsanity.com/paper/2203.12094/) (2022)
- [Entropy landscape of solutions in the binary perceptron problem](https://mlsanity.com/paper/1304.2850/) (2013)
- [Efficiency of quantum versus classical annealing in non-convex learning problems](https://mlsanity.com/paper/1706.08470/) (2017)

## Built on by (most cited first, 1 of 1)

- [Improving Generalization by Permutation Routing Across Model Copies](https://mlsanity.com/paper/2605.09256/) (2026)

## Abstract (arXiv)

We characterize the equilibrium properties of a model of y coupled binary perceptrons in the teacher-student scenario, subject to a suitable cost function, with an explicit ferromagnetic coupling proportional to the Hamming distance between the students' weights. In contrast to recent works, we analyze a more general setting in which thermal noise is present that affects each student's generalization performance. In the nonzero temperature regime, we find that the coupling of replicas leads to a bend of the phase diagram towards smaller values of α: This suggests that the free entropy landscape gets smoother around the solution with perfect generalization (i.e., the teacher) at a fixed fraction of examples, allowing standard thermal updating algorithms such as Simulated Annealing to easily reach the teacher solution and avoid getting trapped in metastable states as it happens in the unreplicated case, even in the computationally textiteasy regime of the inference phase diagram. These results provide additional analytic and numerical evidence for the recently conjectured Bayes-optimal property of Replicated Simulated Annealing (RSA) for a sufficient number of replicas. From a learning perspective, these results also suggest that multiple students working together (in this case reviewing the same data) are able to learn the same rule both significantly faster and with fewer examples, a property that could be exploited in the context of cooperative and federated learning.