Saved in:
Bibliographic Details
Main Authors: Foong, Tham Yik, Zhang, Heng, Yuan, Mao Po, Vargas, Danilo Vasconcellos
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.05168
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916197532958720
author Foong, Tham Yik
Zhang, Heng
Yuan, Mao Po
Vargas, Danilo Vasconcellos
author_facet Foong, Tham Yik
Zhang, Heng
Yuan, Mao Po
Vargas, Danilo Vasconcellos
contents Input distribution shift presents a significant problem in many real-world systems. Here we present Xenovert, an adaptive algorithm that can dynamically adapt to changes in input distribution. It is a perfect binary tree that adaptively divides a continuous input space into several intervals of uniform density while receiving a continuous stream of input. This process indirectly maps the source distribution to the shifted target distribution, preserving the data's relationship with the downstream decoder/operation, even after the shift occurs. In this paper, we demonstrated how a neural network integrated with Xenovert achieved better results in 4 out of 5 shifted datasets, saving the hurdle of retraining a machine learning model. We anticipate that Xenovert can be applied to many more applications that require adaptation to unforeseen input distribution shifts, even when the distribution shift is drastic.
format Preprint
id arxiv_https___arxiv_org_abs_2404_05168
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adapting to Covariate Shift in Real-time by Encoding Trees with Motion Equations
Foong, Tham Yik
Zhang, Heng
Yuan, Mao Po
Vargas, Danilo Vasconcellos
Machine Learning
Input distribution shift presents a significant problem in many real-world systems. Here we present Xenovert, an adaptive algorithm that can dynamically adapt to changes in input distribution. It is a perfect binary tree that adaptively divides a continuous input space into several intervals of uniform density while receiving a continuous stream of input. This process indirectly maps the source distribution to the shifted target distribution, preserving the data's relationship with the downstream decoder/operation, even after the shift occurs. In this paper, we demonstrated how a neural network integrated with Xenovert achieved better results in 4 out of 5 shifted datasets, saving the hurdle of retraining a machine learning model. We anticipate that Xenovert can be applied to many more applications that require adaptation to unforeseen input distribution shifts, even when the distribution shift is drastic.
title Adapting to Covariate Shift in Real-time by Encoding Trees with Motion Equations
topic Machine Learning
url https://arxiv.org/abs/2404.05168