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 Abstract and 1 Introduction 2 State Space Models 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 3.6 Additional Model Details 4 Empirical Evaluation and 4.1 Synthetic Tasks 4.2 Language Modeling 4.3 DNA Modeling 4.4 Audio Modeling and Generation 4.5 Speed and Memory Benchmarks 4.6 Model Ablations 5 Discussion 6 Conclusion and References A Discussion: Selection Mechanism B Related Work C Mechanics of Selective SSMs D Hardware-aware Algorithm For Selective SSMs E Experimental Details and Additional Results 3.5 Properties of Selection Mechanisms The selection mechanism is a broader concept that can be applied in different ways, such as to more traditional RNNs or CNNs, to different parameters (e.g. A in Algorithm 2), or using different transformations s(x). 3.5.1 Connection to Gating Mechanisms We highlight the most important connection: the classical gating mechanism of RNNs is an instance of our selection mechanism for SSMs. We note that the connection between RNN gating and the discretization of continuous-time systems is well established (Funahashi and Nakamura 1993; Tallec and Ollivier 2018). In fact, Theorem 1 is an improvement of Gu, Johnson, Goel, et al. (2021, Lemma 3.1) generalizing to the ZOH discretization and input-dependent gates (proof in Appendix C). More broadly, ∆ in SSMs can be seen to play a generalized role of the RNN gating mechanism. In line with prior work, we adopt the view that discretization of SSMs is the principled foundation of heuristic gating mechanisms. 3.5.2 Interpretation of Selection Mechanisms We elaborate on two particular mechanistic effects of selection. Filtering Context. It has been empirically observed that many sequence models do not improve with longer context (F. Shi et al. 2023), despite the principle that more context should lead to strictly better performance. An explanation is that many sequence models cannot effectively ignore irrelevant context when necessary; an intuitive example are global convolutions (and general LTI models). On the other hand, selective models can simply reset their state at any time to remove extraneous history, and thus their performance in principle improves monotonicly with context length (e.g. Section 4.3.2). Additionally, we elaborate on effects of each selective parameter. This paper is available on arxiv under CC BY 4.0 DEED license. 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. Authors: 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 Abstract and 1 Introduction Abstract and 1 Introduction 2 State Space Models 2 State Space Models 3 Selective State Space Models and 3.1 Motivation: Selection as a Means of Compression 3 Selective State Space Models and 3.1 Motivation: Selection as a Means of Compression 3.2 Improving SSMs with Selection 3.2 Improving SSMs with Selection 3.3 Efficient Implementation of Selective SSMs 3.3 Efficient Implementation of Selective SSMs 3.4 A Simplified SSM Architecture 3.4 A Simplified SSM Architecture 3.5 Properties of Selection Mechanisms 3.5 Properties of Selection Mechanisms 3.6 Additional Model Details 3.6 Additional Model Details 4 Empirical Evaluation and 4.1 Synthetic Tasks 4 Empirical Evaluation and 4.1 Synthetic Tasks 4.2 Language Modeling 4.2 Language Modeling 4.3 DNA Modeling 4.3 DNA Modeling 4.4 Audio Modeling and Generation 4.4 Audio Modeling and Generation 4.5 Speed and Memory Benchmarks 4.5 Speed and Memory Benchmarks 4.6 Model Ablations 4.6 Model Ablations 5 Discussion 5 Discussion 6 Conclusion and References 6 Conclusion and References A Discussion: Selection Mechanism A Discussion: Selection Mechanism B Related Work B Related Work C Mechanics of Selective SSMs C Mechanics of Selective SSMs D Hardware-aware Algorithm For Selective SSMs D Hardware-aware Algorithm For Selective SSMs E Experimental Details and Additional Results E Experimental Details and Additional Results 3.5 Properties of Selection Mechanisms The selection mechanism is a broader concept that can be applied in different ways, such as to more traditional RNNs or CNNs, to different parameters (e.g. A in Algorithm 2), or using different transformations s(x). 3.5.1 Connection to Gating Mechanisms 3.5.1 Connection to Gating Mechanisms We highlight the most important connection: the classical gating mechanism of RNNs is an instance of our selection mechanism for SSMs. We note that the connection between RNN gating and the discretization of continuous-time systems is well established (Funahashi and Nakamura 1993; Tallec and Ollivier 2018). In fact, Theorem 1 is an improvement of Gu, Johnson, Goel, et al. (2021, Lemma 3.1) generalizing to the ZOH discretization and input-dependent gates (proof in Appendix C). More broadly, ∆ in SSMs can be seen to play a generalized role of the RNN gating mechanism. In line with prior work, we adopt the view that discretization of SSMs is the principled foundation of heuristic gating mechanisms. 3.5.2 Interpretation of Selection Mechanisms 3.5.2 Interpretation of Selection Mechanisms We elaborate on two particular mechanistic effects of selection. Filtering Context. It has been empirically observed that many sequence models do not improve with longer context (F. Shi et al. 2023), despite the principle that more context should lead to strictly better performance. An explanation is that many sequence models cannot effectively ignore irrelevant context when necessary; an intuitive example are global convolutions (and general LTI models). On the other hand, selective models can simply reset their state at any time to remove extraneous history, and thus their performance in principle improves monotonicly with context length (e.g. Section 4.3.2). Filtering Context. Additionally, we elaborate on effects of each selective parameter. This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

How Selection Mechanisms Address Long-Context Limitations in AI Sequence Models

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

A Simplified State Space Model Architecture

Princeton and CMU Push AI Boundaries with the Mamba Sequence Model

How State Space Models Improve AI Sequence Modeling Efficiency

Why Compressing Information Helps AI Work Better

How Selection Mechanisms Transform State Space Models

Cutting-Edge Techniques That Speed Up AI Without Extra Costs

A Simplified State Space Model Architecture

Princeton and CMU Push AI Boundaries with the Mamba Sequence Model

How State Space Models Improve AI Sequence Modeling Efficiency

Why Compressing Information Helps AI Work Better

How Selection Mechanisms Transform State Space Models

Cutting-Edge Techniques That Speed Up AI Without Extra Costs

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps