paper-with-me

홈 › Papers

Length independent generalization bounds for deep SSM architectures

2024-05-30 · Dániel Rácz, Mihály Petreczky, Bálint Daróczy

Many state-of-the-art models trained on long-range sequences, for example S4, S5 or LRU, are made of sequential blocks combining State-Space Models (SSMs) with neural networks. In this paper we provide a PAC bound that holds for these kind of architectures with stable SSM blocks and does not depend on the length of the input sequence. Imposing stability of the SSM blocks is a standard practice in the literature, and it is known to help performance. Our results provide a theoretical justification for the use of stable SSM blocks as the proposed PAC bound decreases as the degree of stability of the SSM blocks increases.

📄 PDF Abstract BibTeX arXiv:2405.20278

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsState Space Models

Similar Papers 제목 키워드 기반

Sequence Length Independent Norm-Based Generalization Bounds for Transformers

2023-10-19 · Jacob Trauger, Ambuj Tewari

This paper provides norm-based generalization bounds for the Transformer architecture that do not depend on the input sequence length. We employ a covering number based approach to prove our bounds. We use three novel co…

Generalization Bounds

On Rank-Dependent Generalisation Error Bounds for Transformers

2024-10-15 · Lan V. Truong

In this paper, we introduce various covering number bounds for linear function classes, each subject to different constraints on input and matrix norms. These bounds are contingent on the rank of each class of matrices. …

Generalization Bounds

f-divergences and their applications in lossy compression and bounding generalization error

2022-06-21 · Saeed Masiha, Amin Gohari, Mohammad Hossein Yassaee

In this paper, we provide three applications for $f$-divergences: (i) we introduce Sanov's upper bound on the tail probability of the sum of independent random variables based on super-modular $f$-divergence and show tha…

Generalization Bound for a General Class of Neural Ordinary Differential Equations

2025-08-26 · Madhusudan Verma, Manoj Kumar arxiv

Neural ordinary differential equations (neural ODEs) are a popular type of deep learning model that operate with continuous-depth architectures. To assess how well such models perform on unseen data, it is crucial to und…

Length Generalization Bounds for Transformers

2026-02-13 · Andy Yang, Pascal Bergsträßer, Georg Zetzsche, David Chiang 외 arxiv

Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data. To provide such a guarantee, one needs to be able to comput…