$H$-Consistency Bounds for Pairwise Misranking Loss Surrogates

Authors: Anqi Mao, Mehryar Mohri, Yutao Zhong

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

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we provide empirical results for general pairwise ranking with abstention on the CIFAR-10 dataset (Krizhevsky, 2009).
Researcher Affiliation Collaboration 1Courant Institute of Mathematical Sciences, New York, NY; 2Google Research, New York, NY. Correspondence to: Anqi Mao <aqmao@cims.nyu.edu>, Mehryar Mohri <mohri@google.com>, Yutao Zhong <yutao@cims.nyu.edu>.
Pseudocode No The paper presents mathematical derivations and theoretical concepts, but does not include any pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statement about releasing source code or a link to a code repository for the methodology described.
Open Datasets Yes In this section, we provide empirical results for general pairwise ranking with abstention on the CIFAR-10 dataset (Krizhevsky, 2009).
Dataset Splits No The paper mentions that pairs are randomly sampled from CIFAR-10 for training and 10,000 pairs from the test data for evaluation, but it does not specify explicit training/validation/test splits (e.g., percentages or counts for each split).
Hardware Specification No The paper mentions using "Res Net-34" but does not provide any specific details about the hardware (e.g., GPU model, CPU, memory) used for the experiments.
Software Dependencies No The paper mentions models (Res Net-34), optimizers (Stochastic Gradient Descent with Nesterov momentum), and learning rate schedules (cosine decay), but it does not provide specific software versions for libraries or frameworks (e.g., PyTorch 1.9, TensorFlow 2.x).
Experiment Setup Yes We set the batch size, weight decay, and initial learning rate to 1,024, 1 10 4 and 0.1 respectively. We adopted the cosine decay learning rate schedule (Loshchilov & Hutter, 2016) for a total of 200 epochs.