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 Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization
Authors: Massil HIHAT, Stéphane Gaïffas, Guillaume Garrigos, Simon Bussy
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, in Section 6 we present numerical experiments on both synthetic and real-world data that validate empirically the versatility and performances of Max COSD. |
| Researcher Affiliation | Collaboration | 1LOPF, Califrais Machine Learning Lab, Paris, France 2Université Paris Cité and Sorbonne Université, CNRS, Laboratoire de Probabilités, Statistique et Modélisation, Paris, France |
| Pseudocode | Yes | Algorithm 2: Max COSD |
| Open Source Code | Yes | The code is available at https://github.com/Califrais/newsvendor_tester. |
| Open Datasets | Yes | Demands are taken from the real-world dataset of the M5 competition [17]. |
| Dataset Splits | No | The paper mentions using the M5 competition dataset for T = 1969 periods but does not provide specific details on training, validation, or test splits. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU or CPU models, or memory specifications used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python version, library versions like PyTorch or scikit-learn). |
| Experiment Setup | Yes | All the algorithms have been initialized with y1 = 0. Settings 1, 2 and 3 have been run 10 times, with different demand realizations generated through independent samples. Figure 1 shows, for every setting, the regret obtained after T periods as a function of the learning rate parameter γ [10−5, 101]. We picked T = 1969 for all the settings... |