# The Landscape of Empirical Risk for Non-convex Losses

arXiv: https://arxiv.org/abs/1607.06534 · HTML: https://mlsanity.com/paper/1607.06534/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2016.

## Built on by (most cited first, 30 of 86)

- [Learning Single-Index Models with Shallow Neural Networks](https://mlsanity.com/paper/2210.15651/) (2022)
- [Learning with User-Level Privacy](https://mlsanity.com/paper/2102.11845/) (2021)
- [Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models](https://mlsanity.com/paper/2305.10633/) (2023)
- [Learning time-scales in two-layers neural networks](https://mlsanity.com/paper/2303.00055/) (2023)
- [On Learning Gaussian Multi-index Models with Gradient Flow](https://mlsanity.com/paper/2310.19793/) (2023)
- [Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels](https://mlsanity.com/paper/2103.01210/) (2021)
- [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)
- [Stochastic Gradient Descent under Markovian Sampling Schemes](https://mlsanity.com/paper/2302.14428/) (2023)
- [Adaptive and Robust Multi-Task Learning](https://mlsanity.com/paper/2202.05250/) (2022)
- [Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments](https://mlsanity.com/paper/2204.08281/) (2022)
- [Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems](https://mlsanity.com/paper/2206.07082/) (2022)
- [Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms](https://mlsanity.com/paper/2106.04881/) (2021)
- [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)
- [Mean-field Variational Inference via Wasserstein Gradient Flow](https://mlsanity.com/paper/2207.08074/) (2022)
- [Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks](https://mlsanity.com/paper/2305.06986/) (2023)
- [Learning a Single Neuron with Bias Using Gradient Descent](https://mlsanity.com/paper/2106.01101/) (2021)
- [Local convexity of the TAP free energy and AMP convergence for Z2-synchronization](https://mlsanity.com/paper/2106.11428/) (2021)
- [Survey on Algorithms for multi-index models](https://mlsanity.com/paper/2504.05426/) (2025)
- [Generalization Guarantees for Neural Architecture Search with Train-Validation Split](https://mlsanity.com/paper/2104.14132/) (2021)
- [Learning a Single Neuron for Non-monotonic Activation Functions](https://mlsanity.com/paper/2202.08064/) (2022)
- [Sign-RIP: A Robust Restricted Isometry Property for Low-rank Matrix Recovery](https://mlsanity.com/paper/2102.02969/) (2021)
- [Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods](https://mlsanity.com/paper/2205.14818/) (2022)
- [How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization](https://mlsanity.com/paper/2402.11173/) (2024)
- [Why Do Local Methods Solve Nonconvex Problems?](https://mlsanity.com/paper/2103.13462/) (2021)
- [Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data](https://mlsanity.com/paper/2207.03615/) (2022)
- [SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates](https://mlsanity.com/paper/2211.08597/) (2022)
- [Learning to Generalize Provably in Learning to Optimize](https://mlsanity.com/paper/2302.11085/) (2023)
- [Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron](https://mlsanity.com/paper/2303.02255/) (2023)
- [Should Under-parameterized Student Networks Copy or Average Teacher Weights?](https://mlsanity.com/paper/2311.01644/) (2023)

## Abstract (arXiv)

Most high-dimensional estimation and prediction methods propose to minimize a cost function (empirical risk) that is written as a sum of losses associated to each data point. In this paper we focus on the case of non-convex losses, which is practically important but still poorly understood. Classical empirical process theory implies uniform convergence of the empirical risk to the population risk. While uniform convergence implies consistency of the resulting M-estimator, it does not ensure that the latter can be computed efficiently. In order to capture the complexity of computing M-estimators, we propose to study the landscape of the empirical risk, namely its stationary points and their properties. We establish uniform convergence of the gradient and Hessian of the empirical risk to their population counterparts, as soon as the number of samples becomes larger than the number of unknown parameters (modulo logarithmic factors). Consequently, good properties of the population risk can be carried to the empirical risk, and we can establish one-to-one correspondence of their stationary points. We demonstrate that in several problems such as non-convex binary classification, robust regression, and Gaussian mixture model, this result implies a complete characterization of the landscape of the empirical risk, and of the convergence properties of descent algorithms. We extend our analysis to the very high-dimensional setting in which the number of parameters exceeds the number of samples, and provide a characterization of the empirical risk landscape under a nearly information-theoretically minimal condition. Namely, if the number of samples exceeds the sparsity of the unknown parameters vector (modulo logarithmic factors), then a suitable uniform convergence result takes place. We apply this result to non-convex binary classification and robust regression in very high-dimension.