Variance Reduced Online Gradient Descent for Kernelized Pairwise Learning with Limited Memory - ACML23

method

Prerequisites

Before running this code, you need to have the following dependencies installed:

  • Python 3.x
  • numpy
  • scikit-learn
  • matplotlib

Installation

1- Clone the repository:

git clone https://github.com/halquabeh/ACML-2023-FPOGD.git
cd your-repo

2- Configuration

You can modify the following parameters in the main.py file to customize the behavior of the code:

dataname: Name of the dataset to be used.
s: Value of 's' buffer.
epochs: Number of running times.
early_stop: Early stopping criteria.
path_to_data: Path to the dataset.

Make sure to update the values accordingly.

Citation

If you use this code or algorithm in your research, please consider citing it as follows:

@InProceedings{lastname23,
      title = {Variance Reduced  Online Gradient Descent for Kernelized Pairwise Learning with Limited Memory},
      author = {AlQuabeh, Hilal and Mukhoty, Bhaskar and Gu, Bin },
      pages = {},
      crossref = {Asian Conference on Machine Learning, 2023},
    }