heat

heat copied to clipboard

Add tall-skinny SVD

2

mrfh92

A new PyTorch release is out. Action needed: - run CPU tests - run GPU tests - fix bugs - expand tests - release as minor version

github-actions[bot]

Features/1411 implement sketched percentile

11

This solves #1411 by implementing a sketched version of percentile / median and a corresponding option for the RobustScaler in the preprocessing module. All new features integrate into the current...

mrfh92

Allow random arrays of arbitrary size / speed up random arrays

4

The current very elaborate implementation of our random generator and random arrays suffers from two drawbacks: * the maximum number of entries is quite low (~maxint32 / maxint64 for the...

mrfh92

Add randomized SVD

1

mrfh92

Add incremental SVD/PCA

3

mrfh92

Implement sketched percentile

2

Allow for inexact, but hopefully much faster percentile computation by using a sketch of the data set Related: #1389 on speeding up the existing implementation for exact computation of percentiles

mrfh92

Implement ASSET

3

**Feature functionality** Implement the ASSET analysis method. It is a statistical method for the detection of repeating sequences of synchronous events in peak sequences. **Additional context** Find the reference implementation...

Markus-Goetz

vectorized sorting

1

**Related** When specifying an axis for the `unique` function, the array is searched for unique vectors along this axis. However a sorted result is difficult to compute when `split !=...

TheSlimvReal

Support batch 1-d convolution in `ht.signal.convolve`

7

## Due Diligence - General: - [x] **title** of the PR is suitable to appear in the [Release Notes](https://github.com/helmholtz-analytics/heat/releases/latest) - Implementation: - [x] unit tests: all split configurations tested -...

ClaudiaComito