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..
Can gradient clipping mitigate label noise?
Authors: Aditya Krishna Menon, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
ICLR 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 5 EXPERIMENTAL ILLUSTRATION We now present experiments illustrating that: (a) we may exhibit label noise scenarios that defeat a Huberised but not partially Huberised loss, con๏ฌrming Propositions 4, 7, and (b) partially Huberised versions of existing losses perform well on real-world datasets subject to label noise. |
| Researcher Affiliation | Industry | Aditya Krishna Menon, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar Google Research New York, NY USA EMAIL |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not explicitly state that source code for the methodology is available or provide a link to it. |
| Open Datasets | Yes | We now demonstrate that partially Huberised losses perform well with deep neural networks trained on MNIST, CIFAR-10 and CIFAR-100 (Krizhevsky & Hinton, 2009). |
| Dataset Splits | Yes | We pick ฯ {2, 10} (equivalently corresponding to probability thresholds 0.5 and 0.1 respectively) so as to maximize accuracy on a validation set of noisy samples with the maximal noise rate ฯ = 0.6; the chosen value of ฯ was then used for each noise level. |
| Hardware Specification | No | The paper does not provide specific hardware details (like GPU/CPU models or memory specifications) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | Yes | For MNIST, we train a Le Net (Lecun et al., 1998) using Adam with batch size N = 32, and weight decay of 10 3. For CIFAR-10 and CIFAR-100, we train a Res Net-50 (He et al., 2016) using SGD with momentum 0.1, weight decay of 5 10 3, batch normalisation, and N = 64, 128 respectively. For each dataset, we pick ฯ {2, 10} (equivalently corresponding to probability thresholds 0.5 and 0.1 respectively) so as to maximize accuracy on a validation set of noisy samples with the maximal noise rate ฯ = 0.6; the chosen value of ฯ was then used for each noise level. |