paper-with-me

Papers

On Structured State-Space Duality

2025-10-06 · Jerry Yao-Chieh Hu, Xiwen Zhang, Ali ElSheikh, Weimin Wu, Han Liu arxiv

Structured State-Space Duality (SSD) [Dao & Gu, ICML 2024] is an equivalence between a simple Structured State-Space Model (SSM) and a masked attention mechanism. In particular, a state-space model with a scalar-times-identity state matrix is equivalent to a masked self-attention with a $1$-semiseparable causal mask. Consequently, the same sequence transformation (model) has two algorithmic realizations: as a linear-time $O(T)$ recurrence or as a quadratic-time $O(T^2)$ attention. In this note, we formalize and generalize this duality: (i) we extend SSD from the scalar-identity case to general diagonal SSMs (diagonal state matrices); (ii) we show that these diagonal SSMs match the scalar case's training complexity lower bounds while supporting richer dynamics; (iii) we establish a necessary and sufficient condition under which an SSM is equivalent to $1$-semiseparable masked attention; and (iv) we show that such duality fails to extend to standard softmax attention due to rank explosion. Together, these results tighten bridge between recurrent SSMs and Transformers, and widen the design space for expressive yet efficient sequence models.

📄 PDF Abstract BibTeX arXiv:2510.04944

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

2024-05-31 · Tri Dao, Albert Gu

While Transformers have been the main architecture behind deep learning's success in language modeling, state-space models (SSMs) such as Mamba have recently been shown to match or outperform Transformers at small to med…

Language ModelingLanguage ModellingMambaState Space Models

Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust Losses

2019-10-10 · ICML 2020 1 · Pierre Laforgue, Alex Lambert, Luc Brogat-Motte, Florence d'Alché-Buc

Operator-Valued Kernels (OVKs) and associated vector-valued Reproducing Kernel Hilbert Spaces provide an elegant way to extend scalar kernel methods when the output space is a Hilbert space. Although primarily used in fi…

regressionRepresentation LearningStructured Prediction

SSD4Rec: A Structured State Space Duality Model for Efficient Sequential Recommendation

2024-09-02 · Haohao Qu, Yifeng Zhang, Liangbo Ning, Wenqi Fan 외

Sequential recommendation methods are crucial in modern recommender systems for their remarkable capability to understand a user's changing interests based on past interactions. However, a significant challenge faced by …

MambaRecommendation SystemsSequential RecommendationState Space Models

Dual Simplex Volume Maximization for Simplex-Structured Matrix Factorization

2024-03-29 · Maryam Abdolali, Giovanni Barbarino, Nicolas Gillis

Simplex-structured matrix factorization (SSMF) is a generalization of nonnegative matrix factorization, a fundamental interpretable data analysis model, and has applications in hyperspectral unmixing and topic modeling. …

Hyperspectral Unmixing

TiM4Rec: An Efficient Sequential Recommendation Model Based on Time-Aware Structured State Space Duality Model

2024-09-24 · Hao Fan, Mengyi Zhu, Yanrong Hu, Hailin Feng 외

The Sequential Recommendation modeling paradigm is shifting from Transformer to Mamba architecture, which comprises two generations: Mamba1, based on the State Space Model (SSM), and Mamba2, based on State Space Duality …

Computational EfficiencyMambamodelRecommendation Systems+1