Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Efficient PAC Learning for Realizable-Statistic Models via Convex Surrogates
Authors: Shivani Agarwal
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We show that for a broad range of RSM learning problems, where the statistic of interest can be accurately estimated via a convex strongly proper composite surrogate loss, minimizing this convex surrogate loss yields a computationally efficient learning algorithm with finite sample complexity bounds. We then apply this result to show that various commonly used (and in some cases, not so commonly used) convex surrogate risk minimization algorithms yield computationally efficient learning algorithms with finite sample complexity bounds for a variety of RSM learning problems including binary classification, multiclass classification, multi-label prediction, and subset ranking. |
| Researcher Affiliation | Academia | Shivani Agarwal University of Pennsylvania EMAIL |
| Pseudocode | No | The paper describes algorithms in textual form within the theorems (e.g., "a surrogate risk minimization algorithm A which, given a training sample S of size m, finds an (16B/ m)approximate minimizer..."), but does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not include experiments requiring code. The paper poses no such risks (there are no data or models to be released). |
| Open Datasets | No | The paper does not include experiments that would use specific named datasets. The work is theoretical and discusses 'classes of data distributions' without concrete access information for any open datasets. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical experiments, therefore, it does not provide specific dataset split information. |
| Hardware Specification | No | The paper is theoretical and does not involve empirical experiments, therefore, no hardware specifications are provided. |
| Software Dependencies | No | The paper is theoretical and does not involve empirical experiments, therefore, no software dependencies with specific version numbers are mentioned. |
| Experiment Setup | No | The paper is theoretical and does not involve empirical experiments, therefore, no specific experimental setup details such as hyperparameters or training configurations are provided. |