# Diverse Neural Network Learns True Target Functions

arXiv: https://arxiv.org/abs/1611.03131 · HTML: https://mlsanity.com/paper/1611.03131/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2016.

## Built on by (most cited first, 30 of 33)

- [Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models](https://mlsanity.com/paper/2208.06677/) (2022)
- [Overview frequency principle/spectral bias in deep learning](https://mlsanity.com/paper/2201.07395/) (2022)
- [Learning with Hyperspherical Uniformity](https://mlsanity.com/paper/2103.01649/) (2021)
- [The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy](https://mlsanity.com/paper/2203.06345/) (2022)
- [Fast Sketching of Polynomial Kernels of Polynomial Degree](https://mlsanity.com/paper/2108.09420/) (2021)
- [Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime](https://mlsanity.com/paper/2112.08297/) (2021)
- [Distribution-sensitive Information Retention for Accurate Binary Neural Network](https://mlsanity.com/paper/2109.12338/) (2021)
- [Characterizing the Spectrum of the NTK via a Power Series Expansion](https://mlsanity.com/paper/2211.07844/) (2022)
- [Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent](https://mlsanity.com/paper/2106.13792/) (2021)
- [On the Trade-Off between Actionable Explanations and the Right to be Forgotten](https://mlsanity.com/paper/2208.14137/) (2022)
- [Understanding Unimodal Bias in Multimodal Deep Linear Networks](https://mlsanity.com/paper/2312.00935/) (2023)
- [Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off](https://mlsanity.com/paper/2211.16667/) (2022)
- [Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension](https://mlsanity.com/paper/2405.14630/) (2024)
- [When Are Solutions Connected in Deep Networks?](https://mlsanity.com/paper/2102.09671/) (2021)
- [Reparameterized LLM Training via Orthogonal Equivalence Transformation](https://mlsanity.com/paper/2506.08001/) (2025)
- [When Expressivity Meets Trainability: Fewer than n Neurons Can Work](https://mlsanity.com/paper/2210.12001/) (2022)
- [A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning](https://mlsanity.com/paper/2106.14749/) (2021)
- [A spectral-based analysis of the separation between two-layer neural networks and linear methods](https://mlsanity.com/paper/2108.04964/) (2021)
- [Comparing Text Representations: A Theory-Driven Approach](https://mlsanity.com/paper/2109.07458/) (2021)
- [Memory capacity of two layer neural networks with smooth activations](https://mlsanity.com/paper/2308.02001/) (2023)
- [Learning distinct features helps, provably](https://mlsanity.com/paper/2106.06012/) (2021)
- [WLD-Reg: A Data-dependent Within-layer Diversity Regularizer](https://mlsanity.com/paper/2301.01352/) (2023)
- [Learning Diversified Feature Representations for Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2210.09381/) (2022)
- [Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks](https://mlsanity.com/paper/2201.12052/) (2022)
- [Benefit of Interpolation in Nearest Neighbor Algorithms](https://mlsanity.com/paper/2202.11817/) (2022)
- [Improved Convergence Guarantees for Shallow Neural Networks](https://mlsanity.com/paper/2212.02323/) (2022)
- [Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability](https://mlsanity.com/paper/2010.00521/) (2020)
- [Deep Learning in Random Neural Fields: Numerical Experiments via Neural Tangent Kernel](https://mlsanity.com/paper/2202.05254/) (2022)
- [Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions](https://mlsanity.com/paper/2206.03254/) (2022)
- [On Feature Diversity in Energy-based Models](https://mlsanity.com/paper/2306.01489/) (2023)

## Abstract (arXiv)

Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that provide theoretical guarantees on why they are so effective. Lying in the center of the problem is the difficulty of analyzing the non-convex loss function with potentially numerous local minima and saddle points. Can neural networks corresponding to the stationary points of the loss function learn the true target function? If yes, what are the key factors contributing to such nice optimization properties? In this paper, we answer these questions by analyzing one-hidden-layer neural networks with ReLU activation, and show that despite the non-convexity, neural networks with diverse units have no spurious local minima. We bypass the non-convexity issue by directly analyzing the first order optimality condition, and show that the loss can be made arbitrarily small if the minimum singular value of the "extended feature matrix" is large enough. We make novel use of techniques from kernel methods and geometric discrepancy, and identify a new relation linking the smallest singular value to the spectrum of a kernel function associated with the activation function and to the diversity of the units. Our results also suggest a novel regularization function to promote unit diversity for potentially better generalization.