Uniform Convergence with Square-Root Lipschitz Loss
Authors: Lijia Zhou, Zhen Dai, Frederic Koehler, Nati Srebro
NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We establish generic uniform convergence guarantees for Gaussian data in terms of the Rademacher complexity of the hypothesis class and the Lipschitz constant of the square root of the scalar loss function. We show how these guarantees substantially generalize previous results based on smoothness (Lipschitz constant of the derivative), and allow us to handle the broader class of square-root-Lipschitz losses, which includes also non-smooth loss functions appropriate for studying phase retrieval and Re LU regression, as well as rederive and better understand optimistic rate and interpolation learning guarantees. |
| Researcher Affiliation | Academia | Lijia Zhou University of Chicago zlj@uchicago.edu Zhen Dai University of Chicago zhen9@uchicago.edu Frederic Koehler Stanford University fkoehler@stanford.edu Nathan Srebro Toyota Technological Institute at Chicago nati@ttic.edu Collaboration on the Theoretical Foundations of Deep Learning (deepfoundations.ai) |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete access to source code for the methodology described. |
| Open Datasets | No | The paper is theoretical and does not conduct experiments on datasets, thus it does not provide access information for a publicly available dataset. |
| Dataset Splits | No | The paper is theoretical and does not conduct experiments that would require train/validation/test splits. |
| Hardware Specification | No | The paper is theoretical and does not report on experiments requiring hardware specifications. |
| Software Dependencies | No | The paper is theoretical and does not report on experiments that would require software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup with hyperparameters or system-level training settings. |