Antoine Guillaume

Noticed some issue with the base class structure for the case of #1311, where the optimisation relies on lower bounding and not returning the distance profile fully computed, so I'll...

Sorry for the mess in this PR ... To summarize : The previous `BaseQuerySearch` class was made to allow any matching condition on the output of the similarity search (e.g....

Hi Tony, as a note for RDST, the way I wanted to use FFT was to use [Mueen algorithm for computing distance profiles](https://www.cs.ucr.edu/~eamonn/PID4481997_extend_Matrix%20Profile_I.pdf) in the Matrix Profile (See below for...

Hi, thanks for raising the issue. Could you please provide the version of the other packages in your environment by pasting the output of the following function in a comment...

In my mind there is 4 main cases : - single query to single series - single query to collection of series - collection of queries to single series -...

Pasting the message I made on slack here to keep track of it. Hi everyone, regarding PR #1310 and the update of the similarity search module, and to prepare for...

We could also do the same for MSM distance based on https://arxiv.org/pdf/2301.01977.pdf

Putted back RDST and RIST regressor on ignore list, I can't seem to figure out why they produce different results for now Edit : A possible source of inconsistency for...

I can't seem to figure out why the RDST / RIST are failing, on both windows and Linux I'm getting consistent result locally with the test method on thousand of...

True, forgot about this option ! That or we set a global variable such as `AEON_JOBLIB_BACKEND` and document its usage