## Sklearn - MiniBatchKMeans

The MiniBatchKMeans is a variant of the KMeans algorithm which uses mini-batches to reduce the computation time, while still attempting to optimise the same objective function. Mini-batches are subsets of the input data, randomly sampled in each training iteration. These mini-batches drastically reduce the amount of computation required to converge to a local solution. In contrast to other algorithms that reduce the convergence time of k-means, mini-batch k-means produces results that are generally only slightly worse than the standard algorithm.

KMeansClusteringSklearn
10

#### Authorship

Authorship is unclear, you can claim the item.

#### Classification(s)

Method-focused categoriesData-perspectiveGeoinformation analysis

#### Model Description

English {{currentDetailLanguage}} English

The MiniBatchKMeans is a variant of the KMeans algorithm which uses mini-batches to reduce the computation time, while still attempting to optimise the same objective function. Mini-batches are subsets of the input data, randomly sampled in each training iteration. These mini-batches drastically reduce the amount of computation required to converge to a local solution. In contrast to other algorithms that reduce the convergence time of k-means, mini-batch k-means produces results that are generally only slightly worse than the standard algorithm.

The algorithm iterates between two major steps, similar to vanilla k-means. In the first step, b samples are drawn randomly from the dataset, to form a mini-batch. These are then assigned to the nearest centroid. In the second step, the centroids are updated. In contrast to k-means, this is done on a per-sample basis. For each sample in the mini-batch, the assigned centroid is updated by taking the streaming average of the sample and all previous samples assigned to that centroid. This has the effect of decreasing the rate of change for a centroid over time. These steps are performed until convergence or a predetermined number of iterations is reached.

MiniBatchKMeans converges faster than KMeans, but the quality of the results is reduced. In practice this difference in quality can be quite small, as shown in the example and cited reference.

Examples:

References:

Model Domain
{{domain}}

Principles
{{principle}}
Incorporated Models
{{incorporatedModel}}
Model part of larger framework: {{metadata.design.framework}}
Incorporated Models
{{process}}

Inputs
{{input}}
Outputs
{{output}}

#### How to Cite

songjie (2021). Sklearn - MiniBatchKMeans, Model Item, OpenGMS, https://geomodeling.njnu.edu.cn/modelItem/2e8ca7a8-1c01-42a5-b8c2-45b340c58245

#### Comment(s)

{{comment.date}}
{{comment.content}}
{{subComm.date}}
{{subComm.content}}

#### Authorship

Authorship is unclear, you can claim the item.

#### History

Last modifier :
songjie
Last modify time :
2021-01-12
Modify times :
View History

#### QR Code

• {{curRelation.name}}
{{curRelation.name}}

{{curRelation.overview}}
{{curRelation.author.join('; ')}}
{{curRelation.journal}}

You can link related {{typeName}} from repository to this model item, or you can create a new {{typeName.toLowerCase()}}.

Related Items
{{ props.row.description }}
{{ props.row.description }}
Related Items
{{props.row.name}}

You can link resource from repository to this model item, or you can create a new {{typeName.toLowerCase()}}.

{{ props.row.description }}
{{ props.row.description }}
Drop the file here, orclick to upload.
File size should not exceed 10m.
Select From My Space

These authorship information will be submitted to the contributor to review.

Cancel Submit
Model Classifications
Cancel Submit
{{ item.label }} {{ item.value }}
{{props.row.localName}}
Model Name :
Cancel Submit
Name:
Version:
Model Type:
Model Domain:
Scale:
Purpose:
Principles:
Incorporated models:

Model part of

larger framework

Process:
Information:
Initialization:
Hardware Requirements:
Software Requirements:
Inputs:
Outputs:
Cancel Submit
Title Author Date Journal Volume(Issue) Pages Links Doi Operation
Cancel Submit

Yes, this is it Cancel

OK
Cancel Confirm
Model Classifications 1
Model Classifications 2
Title Author Date Journal Volume(Issue) Pages Links Doi Operation

#### NEW

Name:
Affiliation:
Email:
Homepage:

Yes, this is it Cancel

Confirm
path
:
/{{path.label}}
search results of '{{searchContentShown}}'

#### No content to show

{{item.label}}

.

{{item.suffix}}

.{{item.suffix}}

{{item.fileName}}.{{item.suffix}}

Copy
Delete
Rename
/{{path.label}}
Change
/{{path.label}}
Select File
Cancel Confirm
path
:
/{{path.label}}
/..
Cancel Confirm
{{ node.label }}
##### You have select  {{multipleSelection.length+multipleSelectionMyData.length}} data .
• Output Data
• {{item.computableName}}@{{formatDate(item.runTime)}}
{{scope.row.type}}
{{ scope.row.tag }}