AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections

Albert Gu, Isys Johnson, Aman Timalsina, Atri Rudra, Christopher Re

ICLR 2023 · Architectures and efficiency › RNNs and normalization · approach: Sparse dictionary representations · 11 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the LegS initialization instead of original S4S4 · LRA averageaccuracy: 80.48 -> 86.09Improved
Use the LegS initialization instead of original S4S4 · Path-Xaccuracy: 88.10 -> 96.35Improved
Use the FouT initialization instead of LegSS4 · Imageaccuracy: 88.65 -> 89.07Improved
Use the FouT initialization instead of LegSS4 · Pathfinderaccuracy: 94.20 -> 94.46Improved
Use the FouT initialization instead of LegSS4 · Path-XaccuracyHurt
Initialize half the kernels as LegS and half as FouT rather than using FouT aloneS4-FouT · LRA averageaccuracy: 77.90 -> 78.50Improved
Set the timescale Δ to match known task dependenciesS4 variants · Path-XaccuracyImproved
Set Δ to the theoretically optimal value for the 1000-step lagS4-FouT · Delay TaskRMSEImproved
Set Δ incorrectly rather than matching the task timescaleS4-FouT · Delay TaskRMSEHurt
Initialize C with standard deviation 1.0 rather than 0.01 (ablation)S4-LegS · Sequential CIFARaccuracy: 85.91 (0.41) -> 86.49 (0.51)Improved
Initialize C with standard deviation 1.0 rather than 0.1 (ablation)S4-LegS · Sequential CIFARaccuracy: 86.33 (0.01) -> 86.49 (0.51)No clear effect
Initialize C with standard deviation 1.0 rather than 10.0 (ablation)S4-LegS · Sequential CIFARaccuracy: 84.40 (0.16) -> 86.49 (0.51)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy