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 Non-convex Learning in Dynamic Environments
Authors: Zhipan Xu, Lijun Zhang
NeurIPS 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we discuss the application to online constrained meta-learning and conduct experiments to verify the effectiveness of our methods. |
| Researcher Affiliation | Academia | National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China School of Artificial Intelligence, Nanjing University, Nanjing, China |
| Pseudocode | Yes | Algorithm 1 Follow the Perturbed Leader (FTPL) |
| Open Source Code | Yes | The code and data are included in supplemental material. |
| Open Datasets | Yes | We use the demonstration data given by Huang et al. [2019] and set the total number of tasks T = 200. |
| Dataset Splits | Yes | For each group, we randomly allocate 50% of the classes for training data, 25% for validation data, and 25% for test data. |
| Hardware Specification | Yes | All experiments are executed on a computer with a 2.50 GHz Intel Xeon Platinum 8255C CPU and an RTX 2080Ti GPU. |
| Software Dependencies | No | The paper mentions using the Adam optimizer and a neural network framework, but does not provide specific version numbers for software dependencies like Python, PyTorch, or TensorFlow. |
| Experiment Setup | Yes | We use the Adam optimizer [Kingma and Ba, 2014] with a learning rate of 0.001 for the optimization. |