New Story
How Selection Mechanisms Transform State Space Models
by The Serialization PublicationDecember 15th, 2024
Too Long; Didn't Read
Selective mechanisms enhance State Space Models (SSMs) by introducing input-dependent parameters, transitioning them from time-invariant to time-varying systems. This allows SSMs to efficiently process tasks requiring content-aware dynamics, like Selective Copying and associative recall, though with trade-offs in efficiency.
Authors:
(1) Albert Gu, Machine Learning Department, Carnegie Mellon University and with equal contribution;
(2) Tri Dao, Department of Computer Science, Princeton University and with equal contribution.
Table of Links
3 Selective State Space Models and 3.1 Motivation: Selection as a Means of Compression
3.2 Improving SSMs with Selection
3.3 Efficient Implementation of Selective SSMs
3.4 A Simplified SSM Architecture
3.5 Properties of Selection Mechanisms
4 Empirical Evaluation and 4.1 Synthetic Tasks
4.4 Audio Modeling and Generation
4.5 Speed and Memory Benchmarks
A Discussion: Selection Mechanism
D Hardware-aware Algorithm For Selective SSMs
E Experimental Details and Additional Results
3.2 Improving SSMs with Selection
One method of incorporating a selection mechanism into models is by letting their parameters that affect interactions along the sequence (e.g. the recurrent dynamics of an RNN or the convolution kernel of a CNN) be input-dependent.
This paper is available on arxiv under CC BY 4.0 DEED license.
L O A D I N G
. . . comments & more!
. . . comments & more!
