Metadata-Version: 1.1
Name: higradpy
Version: 0.12
Summary: Python Implementation of Hierarchical Incremental Gradient Descent
Home-page: https://github.com/user/vihan13singh
Author: Vihan Singh
Author-email: vihan13singh@gmail.com
License: MIT
Download-URL: https://github.com/vihan13singh/higradpy/archive/0.1.tar.gz
Description: This is the Python package for HiGrad (Hierarchical Incremental Gradient Descent), an algorithm for statistical inference for online learning and stochastic approximation.
        
        #### Description
        Stochastic gradient descent (SGD) is an immensely popular approach for online learning in settings where data arrives in a stream or data sizes are very large. However, despite an ever-increasing volume of work on SGD, much less is known about the statistical inferential properties of SGD-based predictions. Taking a fully inferential viewpoint, this paper introduces a novel procedure termed HiGrad to conduct statistical inference for online learning, without incurring additional computational cost compared with the vanilla SGD. The HiGrad procedure begins by performing SGD iterations for a while and then split the single thread into a few, and this procedure hierarchically operates in this fashion along each thread. With predictions provided by multiple threads in place, a t-based confidence interval is constructed by decorrelating predictions using covariance structures given by the Ruppert–Polyak averaging scheme. Under certain regularity conditions, the HiGrad confidence interval is shown to attain asymptotically exact coverage probability.
        
        #### Installation
        ```python
        pip install higradpy
        ```
        
        #### Reference
        Weijie Su and Yuancheng Zhu. (2018) Statistical Inference for Online Learning and Stochastic Approximation via Hierarchical Incremental Gradient Descent.
        
Keywords: Statistical Inference,Machine Learning,Stochastic Gradient Descent
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Build Tools
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.4
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
