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..
Robustly Learning Monotone Single-Index Models
Authors: Puqian Wang, Nikos Zarifis, Ilias Diakonikolas, Jelena Diakonikolas
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our main contribution is the first computationally efficient algorithm for this learning task, achieving a constant factor approximation... This work resolves a recognized open problem in the algorithmic theory of learning SIMs, by developing the first polynomial-time, constant-factor robust SIM learner for monotone activations under Gaussian inputs. At the technical level, our alignment-based spectral framework bypasses the limitations of gradient-based methods and leads to a constant-factor approximation ratio independent of dimension, radius of optimization, or noise level. |
| Researcher Affiliation | Academia | Puqian Wang * UW Madison EMAIL Nikos Zarifis * UW Madison EMAIL Ilias Diakonikolas UW Madison EMAIL Jelena Diakonikolas UW Madison EMAIL |
| Pseudocode | Yes | Algorithm 1 Main algorithm Algorithm 2 Initialization Algorithm 3 Spectral Optimization Algorithm 4 Spectral Optimization Algorithm 5 Testing |
| Open Source Code | No | Question: Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material? Answer: [NA] Justification: The paper does not include experiments requiring code. |
| Open Datasets | No | Question: Does the paper explicitly state that the dataset used in the experiments is publicly available or an open dataset? Answer: [No] Justification: The paper discusses a theoretical model under Gaussian distribution and does not use specific external datasets. The NeurIPS checklist confirms 'The paper is a theoretical work and contains no data set.' |
| Dataset Splits | No | Question: Does the paper explicitly provide training/test/validation dataset splits needed to reproduce the experiment? Answer: [No] Justification: The paper is theoretical and does not involve experimental evaluation with specific datasets or their splits. The NeurIPS checklist confirms 'The paper does not include experiments.' |
| Hardware Specification | No | Question: Does the paper explicitly describe the hardware used to run its experiments? Answer: [NA] Justification: The paper does not include experiments. |
| Software Dependencies | No | Question: Does the paper provide a reproducible description of the ancillary software. A reproducible description must include specific version numbers for key software components. Answer: [No] Justification: The paper is theoretical and does not describe any experimental setup requiring specific software versions. The NeurIPS checklist confirms 'The paper does not include experiments.' |
| Experiment Setup | No | Question: Does the paper explicitly provide details about the experimental setup, especially hyperparameters or system-level training settings? Answer: [NA] Justification: The paper does not include experiments. |