Linear Label Ranking with Bounded Noise

Authors: Dimitris Fotakis, Alkis Kalavasis, Vasilis Kontonis, Christos Tzamos

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The main contributions of this paper are the first efficient algorithms for learning LSFs with bounded noise with respect to Kendall s Tau distance and top-𝑟disagreement loss. This paper is theoretical and does not have any negative social impact. [N/A] Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A] Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A] Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? [N/A] Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)?
Researcher Affiliation Academia Dimitris Fotakis NTUA fotakis@cs.ntua.gr Alkis Kalavasis NTUA kalavasisalkis@mail.ntua.gr Vasilis Kontonis UW Madison kontonis@wisc.edu Christos Tzamos UW Madison tzamos@wisc.edu
Pseudocode Yes Algorithm 1 Non-proper Learning Algorithm Improper LSF and Algorithm 2 Proper Learning Algorithm Proper LSF
Open Source Code No The paper states it is theoretical and marks 'N/A' for questions related to code and experimental reproduction, indicating no open-source code for the described methodology is provided.
Open Datasets No The paper is theoretical and assumes `x` is sampled from a 'd-dimensional standard normal' distribution, but it does not mention the use of any real-world public datasets or provide access information for any dataset used in experiments. All experimental questions are marked N/A.
Dataset Splits No The paper is theoretical and does not describe any training, validation, or test dataset splits; all experimental questions are marked N/A.
Hardware Specification No The paper is theoretical and does not report on experiments or provide details on hardware specifications. All experimental questions are marked N/A.
Software Dependencies No The paper is theoretical and does not report on experiments, therefore, it does not specify software dependencies with version numbers. All experimental questions are marked N/A.
Experiment Setup No The paper is theoretical and focuses on algorithm design and theoretical guarantees rather than experimental setups or hyperparameters. All experimental questions are marked N/A.