# Epoch-evolving Gaussian Process Guided Learning

Source: [Epoch-evolving Gaussian Process Guided Learning](<https://www.sota2.com/research/paper/68fa72751e209131cea567e9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:31:06.454Z

Authors: Jiabao Cui, Xuewei Li, Bin Li, Hanbin Zhao, Bourahla Omar, Xi Li

Published: 2020-06-25T12:45:17.000Z

## Abstract

In this paper, we propose a novel learning scheme called epoch-evolving Gaussian Process Guided Learning (GPGL), which aims at characterizing the correlation information between the batch-level distribution and the global data distribution. Such correlation information is encoded as context labels and needs renewal every epoch. With the guidance of the context label and ground truth label, GPGL scheme provides a more efficient optimization through updating the model parameters with a triangle consistency loss. Furthermore, our GPGL scheme can be further generalized and naturally applied to the current deep models, outperforming the existing batch-based state-of-the-art models on mainstream datasets (CIFAR-10, CIFAR-100, and Tiny-ImageNet) remarkably.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2006.14347>)

[PDF](<https://arxiv.org/pdf/2006.14347.pdf>)