s4
s4 copied to clipboard
state-spaces
Structured state space sequence models
Hi everyone, I am looking to reduce size of S4/ Hippo and was wondering if quantization is an approach that I can try out. I am concerned that this can...
First of all, thank you for the comprehensive code base for all variants of S4 models. However, as I try to run the Listops experiments with S4 (HYYT version), the...
Hi, I really really like the Sashimi, it's raw paper. Thank you. I'm going to replicate to get my head around it, I'm thinking it should work with an expanded...
Albert - Thank you for the wonderful S4 model you've invented and kept improving. I am getting very big difference of inference result between forward() and step(), for models trained...
The repeat function in generate.py can only take the dataset with two dimensions, but the weather-dataset has three dimensions, I've tried change the size of repeating but it still doesn't...
Hello, So I've cloned the repo and downloaded the sashimi checkpoints on hugging face in order to reproduce them and apply the method on my dataset. I've found three main...
Hi, a few things that are not fully clear to me on Table 1. It says convolution has LH parameters. How can it be if only the A matrix, which...
Removes all the mentions I could find to a `config/experiment/old` folder that appears to never have been released in the public github repo (See issue https://github.com/state-spaces/s4/issues/130). Proposed edits should avoid...
Hi, in s4.py line 1444 `K_ = krylov(self.l_max, self.dA, self.dB, self.dC)`, this `krylov()` method was not imported from any library. Is this a bug?
I am new to series forecasting and have some questions about dataset parameters. What's the meaning of d_input, d_output, l_output, L in src/dataloaders/xxx.py, and what is __l_max inc configs/datasets/xxx.yaml Thank...
