Skip to main content

PyTorch implementation of α-geodesical skew divergence

Project description

α-Geodesical Skew Divergence

GitHub license GitHub repo size GitHub Workflow Status PyPI arXiv GitHub Repo stars

Official PyTorch Implementation of "α-Geodesical Skew Divergence".

[arXiv]

The asymmetric skew divergence smooths one of the distributions by mixing it, to a degree determined by the parameter λ, with the other distribution. Such divergence is an approximation of the KL divergence that does not require the target distribution to be absolutely continuous with respect to the source distribution. In this paper, an information geometric generalization of the skew divergence called the α-geodesical skew divergence is proposed, and its properties are studied.

Installation

From PyPi

$ pip install gs_divergence

From GitHub

$ git clone https://github.com/nocotan/geodesical_skew_divergence
$ python setup.py install

Usage

import torch
from gs_divergence import gs_div

a = torch.Tensor([0.1, 0.2, 0.3, 0.4])
b = torch.Tensor([0.2, 0.2, 0.4, 0.2])

div = gs_div(a, b, alpha=-1, lmd=0.5)
parameter description
input Tensor of arbitrary shape
target Tensor of the same shape as input
alpha Specifies the coordinate systems which equiped the geodesical skew divergence (default=-1)
lmd Specifies the position on the geodesic (default=0.5)
reduction Specifies the reduction to apply to the output: 'none' | 'batchmean' | 'sum' | 'mean'. 'none': no reduction will be applied 'batchmean': the sum of the output will be divided by the batchsize 'sum': the output will be summed 'mean': the output will be divided by the number of elements in the output default='sum'

Definition of α-Geodesical Skew Divergence

Visualizations of the α-Geodesical Skew Divergence

Monotonicity of the α-geodesical skew divergence with respect to α

Continuity of the α-geodesical skew divergence with respect to α and λ.

Citation

@misc{kimura2021geodesical,
    title={$α$-Geodesical Skew Divergence},
    author={Masanari Kimura and Hideitsu Hino},
    year={2021},
    eprint={2103.17060},
    archivePrefix={arXiv},
    primaryClass={cs.IT}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gs_divergence-1.0.8.tar.gz (4.8 kB view hashes)

Uploaded Source

Built Distribution

gs_divergence-1.0.8-py3-none-any.whl (6.5 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page