Hacker News Reader

More on SLIDE for those curious: https://twimlai.com/slide-the-algorithmic-alternative-that-o...

It's a CPU-based deep learning training algorithm that beats GPUs for some tasks.

I've not seen anything convincing that slide can approximate convolutional layers like at all without almost doing a full convolution at which point it is not competitive.

Can you link me to paper about recent (2021?) work or improvements with slide?

I thought SLIDE was optimized for classification with mind-boggingly sparse data. I.e. "choose the best label for this image out of those 1 mio choices".

The current work

https://proceedings.mlsys.org/paper/2021/hash/3636638817772e...

seems mostly about tuning the original idea instead of expanding its scope. But it's still a neat idea. I guess it could be possible to adpt many of the approximations used in the SLIDE idea to GPUs too though...

They also have a company called ThirdAI to commercialize SLIDE