Learning Manifold Implicitly via Explicit Heat-Kernel Learning

Authors: Yufan Zhou, Changyou Chen, Jinhui Xu

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show that our framework can achieve state-of-the-art results compared to existing methods for the two tasks.
Researcher Affiliation Academia Yufan Zhou, Changyou Chen, Jinhui Xu Department of Computer Science and Engineering State University of New York at Buffalo {yufanzho, changyou, jinhui}@buffalo.edu
Pseudocode Yes Algorithm 1 Heat Kernel Learning
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the methodology.
Open Datasets Yes UCI datasets, CIFAR-10, STL-10, Image Net, Celeb A
Dataset Splits No The provided text does not explicitly detail the training/validation/test dataset splits, specific percentages, or sample counts.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or cloud instance types) used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes For all experiments, a 2-layer BNN with 50 hidden units, 10 weight particles, Re LU activation is used. We assign the isotropic Gaussian prior to the network weights. ... images are scaled to the resolution of 32 32, 48 48, 64 64 and 160 160 respectively. ... we test 2 architectures on CIFAR-10 and STL-10, 1 architecture on Celeb A and Image Net.