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..
Online Learning with Local Permutations and Delayed Feedback
Authors: Ohad Shamir, Liran Szlak
ICML 2017 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we provide some experiments validating the performance of our algorithm. |
| Researcher Affiliation | Academia | 1Weizmann Institute of Science, Rehovot, Israel. Correspondence to: Liran Szlak <EMAIL>. |
| Pseudocode | Yes | Algorithm 1 Delayed Permuted Mirror Descent |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper uses a custom-generated adversarial setting based on linear loss functions, described in Section 4, rather than a publicly available dataset with specified access information. |
| Dataset Splits | No | The paper describes a simulated adversarial setting for experiments, which does not involve standard training, validation, and test dataset splits common in empirical studies with fixed datasets. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependency names with version numbers that would be necessary for replication. |
| Experiment Setup | Yes | In all experiments we use T = 105 rounds, a delay parameter of τ = 200, set our step sizes according to the theoretical analysis, and report the mean regret value over 1000 repetitions of the experiments. |