تقرير
RotRNN: Modelling Long Sequences with Rotations
العنوان: | RotRNN: Modelling Long Sequences with Rotations |
---|---|
المؤلفون: | Dolga, Rares, Biegun, Kai, Cunningham, Jake, Barber, David |
سنة النشر: | 2024 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Computer Science - Machine Learning, Statistics - Machine Learning |
الوصف: | Linear recurrent models, such as State Space Models (SSMs) and Linear Recurrent Units (LRUs), have recently shown state-of-the-art performance on long sequence modelling benchmarks. Despite their success, they come with a number of drawbacks, most notably their complex initialisation and normalisation schemes. In this work, we address some of these issues by proposing RotRNN -- a linear recurrent model which utilises the convenient properties of rotation matrices. We show that RotRNN provides a simple model with fewer theoretical assumptions than prior works, with a practical implementation that remains faithful to its theoretical derivation, achieving comparable scores to the LRU and SSMs on several long sequence modelling datasets. Comment: Next Generation of Sequence Modeling Architectures Workshop at ICML 2024 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2407.07239 |
رقم الأكسشن: | edsarx.2407.07239 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |