Liquid Structural State-Space Models

Authors: Ramin Hasani, Mathias Lechner, Tsun-Hsuan Wang, Makram Chahine, Alexander Amini, Daniela Rus

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Through extensive empirical evaluation, we show that Liquid-S4 consistently leads to better generalization performance compared to all variants of S4, CNNs, RNNs, and Transformers across many time-series modeling tasks. In this section, we present an extensive evaluation of Liquid-S4 on sequence modeling tasks with very long-term dependencies and compare its performance to a large series of baselines...
Researcher Affiliation Academia Ramin Hasani CSAIL, MIT Mathias Lechner CSAIL, MIT Tsun-Hsuan Wang CSAIL, MIT Makram Chahine CSAIL, MIT Alexander Amini CSAIL, MIT Daniela Rus CSAIL, MIT
Pseudocode Yes Algorithm 1 LIQUID-S4 KERNEL
Open Source Code Yes Code: https://github.com/raminmh/liquid-s4.
Open Datasets Yes We first evaluate Liquid-S4 s performance on the well-studied Long Range Arena (LRA) benchmark (Tay et al., 2020b)... We then report Liquid-S4 s performance... on the BIDMC Vital Signals dataset (Pimentel et al., 2016; Goldberger et al., 2000). We also experiment with the s CIFAR dataset... Finally, we perform Raw Speech Command (SC) recognition...
Dataset Splits Yes Table 1: Performance on Long Range Arena Tasks. Numbers indicate validation accuracy (standard deviation). Table 2: Performance on BIDMC Vital Signs dataset. Numbers indicate RMSE on the test set. Table 3: Performance on s CIFAR. Numbers indicate Accuracy (standard deviation). Table 4: Performance on Raw Speech Command dataset with Full 35 Labels.Numbers indicate Accuracy on test set.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions 'Py Keops package' but does not specify its version number, nor does it list other key software components with versions.
Experiment Setup Yes Table 5: Hyperparameters for obtaining best performing models. BN= Batch normalization, LN = Layer normalization, WD= Weight decay. (followed by a table with specific values for Depth, Features, H State Size, Norm, Pre-norm, Dropout, LR, Batch Size, Epochs, WD for various tasks).