Contrastive Learning from Pairwise Measurements

Authors: Yi Chen, Zhuoran Yang, Yuchen Xie, Zhaoran Wang

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We provide numerical experiments to corroborate our theory. We lay out the simulation results in this section and demonstrate the accuracy of the contrastive estimator bΘ stated in Theorem 4.4. In Figure 1. (a)-(b), we plot the rescaled estimation error 1/d bΘ Θ F against 1/ n, where n is the sample size.
Researcher Affiliation Academia Northwestern University Princeton University
Pseudocode No The paper describes the theoretical framework and estimator but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements or links indicating the availability of open-source code for the described methodology.
Open Datasets No The paper describes generating its own synthetic data for numerical experiments ('we first generate two matrices U Rd r and V Rr d, whose entries are independently and identically distributed standard normal random variables.') and does not provide concrete access information for a publicly available dataset.
Dataset Splits No The paper describes generating synthetic data for simulations but does not specify any training, validation, or test dataset splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions using the 'proximal gradient method' but does not specify any software dependencies with version numbers (e.g., Python version, library names and versions).
Experiment Setup Yes For the regularization parameter λ, we set λ in (3.2) as 0.5 1/ nd log(2d), as suggested in Theorem 4.4.