Demystifying Disagreement-on-the-Line in High Dimensions

Authors: Donghwan Lee, Behrad Moniri, Xinmeng Huang, Edgar Dobriban, Hamed Hassani

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on CIFAR-10-C, Tiny Image Net-C, and Camelyon17 are consistent with our theory and support the universality of the theoretical findings.
Researcher Affiliation Academia 1Graduate Group in Applied Mathematics and Computational Science, University of Pennsylvania, PA, USA 2Department of Electrical and Systems Engineering, University of Pennsylvania, PA, USA 3Department of Statistics and Data Science, University of Pennsylvania, PA, USA.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes The associated code can be found at https://github.com/dh7401/RF-disagreement.
Open Datasets Yes We conduct experiments on the following datasets. ... CIFAR-10-C. Hendrycks & Dietterich (2018) introduced a corrupted version of CIFAR-10 (Krizhevsky et al., 2009).
Dataset Splits No The paper mentions 'training sample size n = 1000' and 'test the trained model on the rest of the sample' but does not specify a separate validation set or explicit train/validation/test splits with percentages or counts.
Hardware Specification No The paper does not explicitly describe any specific hardware (e.g., GPU models, CPU types, or memory) used for running its experiments.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies or libraries used in the experiments.
Experiment Setup Yes We use training sample size n = 1000, random features dimension N {3000, 4000, . . . , 49000}, input dimension d = 3072, regularization γ = 0.