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 [1].

Dueling Convex Optimization with General Preferences

Authors: Aadirupa Saha, Tomer Koren, Yishay Mansour

ICML 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main contribution is an efficient algorithm with convergence rate of O(ϵ 4p) for smooth convex functions, and an optimal rate of e O(ϵ 2p) when the objective is both smooth and strongly convex, where p is the minimal degree (with a non-zero coefficient) in the transfer s series expansion about the origin.
Researcher Affiliation Collaboration 1Department of Computer Science, University of Illinois, Chicago, US 2Blavatnik School of Computer Science, Tel Aviv University, Israel 3Google Research, Tel Aviv, Israel. Correspondence to: Aadirupa Saha <EMAIL>.
Pseudocode Yes Algorithm 1 Projected Dueling Descent (PDD) ... Algorithm 2 Epoch-PDD
Open Source Code No The paper does not provide any statements or links regarding the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical, focusing on algorithm design and convergence analysis for convex optimization. It does not conduct empirical studies that would involve datasets.
Dataset Splits No The paper is theoretical and does not involve the use of datasets or experiments, therefore, there are no dataset splits mentioned.
Hardware Specification No The paper is theoretical and focuses on algorithm design and convergence proofs. It does not describe any experiments that would require specific hardware, thus no hardware specifications are provided.
Software Dependencies No The paper is theoretical and does not describe any experimental implementation. Therefore, no specific software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and presents algorithms with convergence proofs. It does not describe any empirical experiments, and therefore, no experimental setup details, such as hyperparameters or system-level training settings, are provided.