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..

Smoothed Agnostic Learning of Halfspaces over the Hypercube

Authors: Yiwen Kou, Raghu Meka

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This is the first result that establishes efficient smoothed agnostic learning of halfspaces over the Boolean hypercube. Our approach combines tools from smoothing analysis, conditional polynomial approximation, and critical index decomposition to construct low-degree polynomial approximators in a discrete setting where standard analytic techniques are not applicable.
Researcher Affiliation Academia Yiwen Kou Department of Computer Science, UCLA Los Angeles, CA, US EMAIL. Raghu Meka Department of Computer Science, UCLA Los Angeles, CA, US EMAIL.
Pseudocode Yes Algorithm 1 L1 Polynomial Regression Algorithm
Open Source Code No [NA] Justification: No datasets or code are used or required, as the paper does not include experiments.
Open Datasets No [NA] Justification: No datasets or code are used or required, as the paper does not include experiments.
Dataset Splits No [NA] Justification: The paper is entirely theoretical and does not include empirical experiments.
Hardware Specification No [NA] Justification: No experiments were conducted; no compute resources were used.
Software Dependencies No [NA] Justification: No experimental setting is involved; the paper is theoretical.
Experiment Setup No [NA] Justification: No experimental setting is involved; the paper is theoretical.