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..
Uniform Wrappers: Bridging Concave to Quadratizable Functions in Online Optimization
Authors: Mohammad Pedramfar, Christopher John Quinn, Vaneet Aggarwal
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper presents novel contributions to the field of online optimization, particularly focusing on the adaptation of algorithms from concave optimization to more challenging classes of functions. Key contributions include the introduction of uniform wrappers, a class of meta-algorithms that could be used for algorithmic conversions such as converting algorithms for convex optimization into those for quadratizable optimization. Moreover, we propose a guideline that, given a base algorithm A for concave optimization and a uniform wrapper W, describes how to convert a proof of the regret bound of A in the concave setting into a proof of the regret bound of W(A) for quadratizable setting. Through this framework, the paper demonstrates improved regret guarantees for various classes of DR-submodular functions under zeroth-order feedback. Furthermore, the paper extends zeroth-order online algorithms to bandit feedback and offline counterparts, achieving notable improvements in regret/sample complexity compared to existing approaches. |
| Researcher Affiliation | Academia | Mohammad Pedramfar Mila Quebec AI Institute/Mc Gill University EMAIL Christopher J. Quinn Iowa State University EMAIL Vaneet Aggarwal Purdue University EMAIL |
| Pseudocode | Yes | Meta-algorithm 1: Application of a uniform wrapper to the base algorithm W(A) Input : horizon T, algorithm A, uniform wrapper W for t = 1, 2, . . . , T do Play Waction(xt) where xt is the action chosen by Aaction The adversary selects ft and a query oracle Qt for ft for i starting from 1, while Aquery is not terminated for this time-step do Let yt,i be the query chosen by Aquery Return ot,i = Wquery(Qt)(yt,i) as the output of the query oracle to Aquery |
| Open Source Code | No | The paper does not include any explicit statement or link regarding the public availability of source code for the methodology described. |
| Open Datasets | No | The paper does not describe any experiments that use specific datasets, nor does it provide any information about the public availability of datasets. |
| Dataset Splits | No | The paper does not perform experiments and thus does not provide information on dataset splits. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental setup or the specific hardware used for running experiments. |
| Software Dependencies | No | The paper is theoretical and does not mention specific software dependencies or version numbers required for reproducing experiments. |
| Experiment Setup | No | The paper is theoretical and does not provide details on experimental setup such as hyperparameters or system-level training settings. |