# Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks

arXiv: https://arxiv.org/abs/1910.01619 · HTML: https://mlsanity.com/paper/1910.01619/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2019.

## Built on by (most cited first, 30 of 79)

- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Neural Networks can Learn Representations with Gradient Descent](https://mlsanity.com/paper/2206.15144/) (2022)
- [High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation](https://mlsanity.com/paper/2205.01445/) (2022)
- [Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning](https://mlsanity.com/paper/2105.15134/) (2021)
- [Learning Single-Index Models with Shallow Neural Networks](https://mlsanity.com/paper/2210.15651/) (2022)
- [Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models](https://mlsanity.com/paper/2210.14199/) (2022)
- [Towards Understanding Mixture of Experts in Deep Learning](https://mlsanity.com/paper/2208.02813/) (2022)
- [Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization](https://mlsanity.com/paper/2108.11371/) (2021)
- [A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features](https://mlsanity.com/paper/2206.01717/) (2022)
- [Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit](https://mlsanity.com/paper/2406.01581/) (2024)
- [Second-order regression models exhibit progressive sharpening to the edge of stability](https://mlsanity.com/paper/2210.04860/) (2022)
- [What can a Single Attention Layer Learn? A Study Through the Random Features Lens](https://mlsanity.com/paper/2307.11353/) (2023)
- [SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem](https://mlsanity.com/paper/2309.15111/) (2023)
- [Random Feature Amplification: Feature Learning and Generalization in Neural Networks](https://mlsanity.com/paper/2202.07626/) (2022)
- [Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks](https://mlsanity.com/paper/2306.04073/) (2023)
- [The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization](https://mlsanity.com/paper/2106.04013/) (2021)
- [Pretrained transformer efficiently learns low-dimensional target functions in-context](https://mlsanity.com/paper/2411.02544/) (2024)
- [Spectral Evolution and Invariance in Linear-width Neural Networks](https://mlsanity.com/paper/2211.06506/) (2022)
- [Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel](https://mlsanity.com/paper/2107.12723/) (2021)
- [Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features](https://mlsanity.com/paper/2212.13881/) (2022)
- [Multi-scale Feature Learning Dynamics: Insights for Double Descent](https://mlsanity.com/paper/2112.03215/) (2021)
- [Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos](https://mlsanity.com/paper/2311.02076/) (2023)
- [The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective](https://mlsanity.com/paper/2106.06529/) (2021)
- [Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks](https://mlsanity.com/paper/2209.09298/) (2022)
- [Generalization and Stability of Interpolating Neural Networks with Minimal Width](https://mlsanity.com/paper/2302.09235/) (2023)
- [Understanding Deflation Process in Over-parametrized Tensor Decomposition](https://mlsanity.com/paper/2106.06573/) (2021)
- [On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game](https://mlsanity.com/paper/2110.09771/) (2021)
- [Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm](https://mlsanity.com/paper/2206.00833/) (2022)
- [Six Lectures on Linearized Neural Networks](https://mlsanity.com/paper/2308.13431/) (2023)
- [A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models](https://mlsanity.com/paper/2401.07187/) (2024)

## Abstract (arXiv)

Recent theoretical work has established connections between over-parametrized neural networks and linearized models governed by he Neural Tangent Kernels (NTKs). NTK theory leads to concrete convergence and generalization results, yet the empirical performance of neural networks are observed to exceed their linearized models, suggesting insufficiency of this theory. Towards closing this gap, we investigate the training of over-parametrized neural networks that are beyond the NTK regime yet still governed by the Taylor expansion of the network. We bring forward the idea of randomizing the neural networks, which allows them to escape their NTK and couple with quadratic models. We show that the optimization landscape of randomized two-layer networks are nice and amenable to escaping-saddle algorithms. We prove concrete generalization and expressivity results on these randomized networks, which lead to sample complexity bounds (of learning certain simple functions) that match the NTK and can in addition be better by a dimension factor when mild distributional assumptions are present. We demonstrate that our randomization technique can be generalized systematically beyond the quadratic case, by using it to find networks that are coupled with higher-order terms in their Taylor series.