Partial Matrix Completion

Authors: Elad Hazan, Adam Tauman Kalai, Varun Kanade, Clara Mohri, Y. Jennifer Sun

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Preliminary empirical evaluations are included. [...] 6 Experiments and Implementation
Researcher Affiliation Collaboration Elad Hazan Princeton University Google DeepMind Adam Tauman Kalai Microsoft Research Varun Kanade University of Oxford Clara Mohri Harvard University Y. Jennifer Sun Princeton University Google DeepMind
Pseudocode Yes Algorithm 1 [...] Algorithm 2 (Efficient) Offline Algorithm for Partial Matrix Completion [...] Algorithm 3
Open Source Code No The paper mentions using a standard matrix completion tool, fancyimpute, but does not state that the authors are releasing their own code for the described methodology.
Open Datasets Yes The Movie Lens dataset ([Harper and Konstan, 2015]) consists of, among other data, a set of users with their rankings of a set of movies.
Dataset Splits No The paper mentions using "training data" and a "validation set" but does not specify the exact split percentages, absolute sample counts, or a detailed splitting methodology required for reproducibility.
Hardware Specification No The paper does not specify any hardware details (e.g., CPU, GPU models, memory, or cloud resources) used for running the experiments.
Software Dependencies No The paper mentions using "fancyimpute ([Rubinsteyn and Feldman, 2016])" but does not provide any specific version numbers for this or any other software dependencies.
Experiment Setup No The paper describes the experimental procedure (e.g., using Movie Lens, running ODD algorithm, using fancyimpute, validating with true ratings) but does not provide specific details on hyperparameters, model initialization, or system-level training settings.