Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures
Authors: Yuan Cao, Quanquan Gu, Mikhail Belkin
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we study this benign overfitting phenomenon of the maximum margin classifier for linear classification problems. Specifically, we consider data generated from sub-Gaussian mixtures, and provide a tight risk bound for the maximum margin linear classifier in the over-parameterized setting. Our results precisely characterize the condition under which benign overfitting can occur in linear classification problems, and improve on previous work. They also have direct implications for over-parameterized logistic regression. |
| Researcher Affiliation | Academia | Yuan Cao Department of Statistics & Actuarial Science Department of Mathematics The University of Hong Kong yuancao@hku.hk Quanquan Gu Department of Computer Science University of California, Los Angeles Los Angeles, CA 90095, USA qgu@cs.ucla.edu Mikhail Belkin Halicio glu Data Science Institute University of California San Diego La Jolla, CA 92093, USA mbelkin@ucsd.edu |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide a direct link or explicit statement in the main text about the availability of its source code. |
| Open Datasets | No | We consider a model where the feature vectors are generated from a mixture of two sub-Gaussian distributions with means µ and µ and the same covariance matrix Σ. We consider n training data points (xi, yi) generated independently from the above procedure |
| Dataset Splits | No | The paper defines training data generation but does not specify any dataset splits (e.g., train/validation/test percentages or counts). |
| Hardware Specification | No | The paper states 'All experiments can be run very efficiently on a standard PC.' but does not provide specific hardware details (e.g., CPU/GPU model, memory). |
| Software Dependencies | No | The paper does not list any specific software dependencies with version numbers. |
| Experiment Setup | No | As a theoretical paper, it defines a model and assumptions but does not describe an experimental setup with hyperparameters or training configurations for empirical evaluation. |