# Width-Robust Learnability in Mean-Field Bayesian Neural Networks

arXiv: https://arxiv.org/abs/2607.05735 · HTML: https://mlsanity.com/paper/2607.05735/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 7 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Deep Neural Networks as Gaussian Processes](https://mlsanity.com/paper/1711.00165/) (2017)
- [A Mean Field View of the Landscape of Two-Layers Neural Networks](https://mlsanity.com/paper/1804.06561/) (2018)
- [On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport](https://mlsanity.com/paper/1805.09545/) (2018)
- [Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit](https://mlsanity.com/paper/2207.08799/) (2022)
- [Mean Field Analysis of Neural Networks: A Central Limit Theorem](https://mlsanity.com/paper/1808.09372/) (2018)
- [Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach](https://mlsanity.com/paper/1805.00915/) (2018)
- [Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks](https://mlsanity.com/paper/2205.09653/) (2022)
- [Learning Parities with Neural Networks](https://mlsanity.com/paper/2002.07400/) (2020)
- [A Rigorous Framework for the Mean Field Limit of Multilayer Neural Networks](https://mlsanity.com/paper/2001.11443/) (2020)
- [Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs](https://mlsanity.com/paper/2112.15383/) (2021)
- [A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs](https://mlsanity.com/paper/2106.04110/) (2021)
- [How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers](https://mlsanity.com/paper/2402.06323/) (2024)
- [Generalization Bounds for Neural Networks via Approximate Description Length](https://mlsanity.com/paper/1910.05697/) (2019)
- [Adaptive kernel predictors from feature-learning infinite limits of neural networks](https://mlsanity.com/paper/2502.07998/) (2025)
- [From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning](https://mlsanity.com/paper/2502.03210/) (2025)
- [On the Sample Complexity of Two-Layer Networks: Lipschitz vs. Element-Wise Lipschitz Activation](https://mlsanity.com/paper/2211.09634/) (2022)
- [Summary statistics of learning link changing neural representations to behavior](https://mlsanity.com/paper/2504.16920/) (2025)
- [Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity](https://mlsanity.com/paper/2512.04165/) (2025)
- [Algorithmic Task Capture, Computational Complexity, and Inductive Bias of Infinite Transformers](https://mlsanity.com/paper/2603.11161/) (2026)

## Abstract (arXiv)

Infinite-width limits are a standard way to reason about neural networks, but it is not automatic that the limiting learner has the same complexity-theoretic inductive bias as large finite networks. We study this question for Bayesian neural networks at the mean-field, or critical feature-learning, scaling. The central quantity is the reduced entropy [ s_∞(y,varepsilon)=limsupN -frac1Nlog πN0(L≤ varepsilon), ] the intensive prior cost of representing a target function y to population mean-squared error varepsilon. Our main result is a width-robust learnability theorem. At fixed depth, a family of Boolean-cube targets is learnable from polynomially many samples at infinite width if and only if it is learnable at polynomial width, if and only if its reduced entropy is polynomially bounded. Equivalently, up to polynomial slack in accuracy, the Bayesian mean-field learner generalizes exactly on the targets that can be represented by polynomial-size networks. The forward direction is proved by a form of subsampling: from the infinitely many hidden neurons in the mean-field solution, one can select polynomially many representatives and still preserve the learned function on every input simultaneously. At the critical scaling this subsampling has both an ``active'' component, which keeps the data-dependent low-dimensional statistics, and a ``lazy'' component, which resamples the entropy-dominated directions from the prior. Thus the infinite-width mean-field limit gives a clean analytic description of learning without introducing spurious width-dependent generalization power.