Nicolas Courty

Hi @Yura52 , sorry for delay. EMD can be solved with *any* type of cost matrix. As for mini-batch, I do not think it is possible to solve the exact...

Hi theo, thanks for reporting this bug. I suspect there is an overflow somewhere in the solver, it will be hard to identify. Here is a quick fixup, if it...

Hi @patricieni , sorry for long time reply. Could you post a short code that is reproducing your error ? Thanks in advance

Hi all, Yes good idea to revive this discussion. Regarding the module import name, I would call for pot. 'import pot' seems more consistent to me with the library name....

sorry for long time reply. Yes, regularization values should be chosen with care, as it depends closely to the nature of data(and cost) at hand. Yet, the behavior should be...

Hello @MrPr3ntice . Indeed this extension could be useful. Please note that nothing prevents it in theory. You can take a look at this repo https://github.com/rflamary/JDOT where we use an...

Yes ! also you can take a look at https://arxiv.org/pdf/2202.06208.pdf (this is shameless self-promotion, sorry) for a work (under- review) on a specific type of regularizer for DA in the...

hi @bionicles , regarding the `FGW` function, the first parameters `M, C1, C2` refer respectively to distances between attributes of your 'atom' (assuming X ?), and inner distances in the...

Hello I am having similar troubles with the side parameter. I am trying to get a minimal code for reproducing the bug but it seems the trouble is happening randomly.

Great ! Your last update solved the bug on my side. Thanks for the nice code 👍