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..

Robust Regression of General ReLUs with Queries

Authors: Ilias Diakonikolas, Daniel Kane, Mingchen Ma

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The paper is theoretical in nature and does not include experiments.
Researcher Affiliation Academia Ilias Diakonikolas University of Wisconsin-Madison EMAIL Daniel M. Kane University of California, San Diego EMAIL Mingchen Ma University of Wisconsin-Madison EMAIL
Pseudocode Yes Algorithm 1 QUERYLEARNING(Learn optimal Re LU with a warm start) ... Algorithm 2 HYPOTHESISSELECTION(Select a good hypothesis from a list of hypothesis) ... Algorithm 3 SPHERICALLEARNING(Learn w over the unit sphere) ... Algorithm 4 QUERYLEARNING(Learn optimal Re LU with a warm start)
Open Source Code No The paper is theoretical in nature and does not include code, data or experiments.
Open Datasets No The paper is theoretical in nature and does not include code, data or experiments.
Dataset Splits No The paper is theoretical in nature and does not include experiments.
Hardware Specification No The paper is theoretical in nature and does not include experiments.
Software Dependencies No The paper is theoretical in nature and does not include experiments.
Experiment Setup No The paper is theoretical in nature and does not include experiments.