English
Related papers

Related papers: Why Are Linear RNNs More Parallelizable?

200 papers

Despite their omnipresence in modern NLP, characterizing the computational power of transformer neural nets remains an interesting open question. We prove that transformers whose arithmetic precision is logarithmic in the number of input…

Computational Complexity · Computer Science 2023-04-28 William Merrill , Ashish Sabharwal

In recent studies, linear recurrent neural networks (LRNNs) have achieved Transformer-level performance in natural language and long-range modeling, while offering rapid parallel training and constant inference cost. With the resurgence of…

Computation and Language · Computer Science 2024-04-10 Ting-Han Fan , Ta-Chung Chi , Alexander I. Rudnicky

State-space models (SSMs) and transformers dominate the language modeling landscape. However, they are constrained to a lower computational complexity than classical recurrent neural networks (RNNs), limiting their expressivity. In…

Machine Learning · Computer Science 2025-06-13 Mark Schöne , Babak Rahmani , Heiner Kremer , Fabian Falck , Hitesh Ballani , Jannes Gladrow

Recurrent Neural Networks (RNNs) laid the foundation for sequence modeling, but their intrinsic sequential nature restricts parallel computation, creating a fundamental barrier to scaling. This has led to the dominance of parallelizable…

Machine Learning · Computer Science 2025-11-04 Federico Danieli , Pau Rodriguez , Miguel Sarabia , Xavier Suau , Luca Zappella

One fundamental problem in deep learning is understanding the outstanding performance of deep Neural Networks (NNs) in practice. One explanation for the superiority of NNs is that they can realize a large class of complicated functions,…

Machine Learning · Computer Science 2020-06-30 H. Xiong , L. Huang , M. Yu , L. Liu , F. Zhu , L. Shao

Recurrent Neural Networks (RNNs) are very successful at solving challenging problems with sequential data. However, this observed efficiency is not yet entirely explained by theory. It is known that a certain class of multiplicative RNNs…

Machine Learning · Computer Science 2019-01-31 Valentin Khrulkov , Oleksii Hrinchuk , Ivan Oseledets

Neural networks (NN) can be divided into two broad categories, recurrent and non-recurrent. Both types of neural networks are popular and extensively studied, but they are often treated as distinct families of machine learning algorithms.…

Machine Learning · Computer Science 2024-04-02 Quincy Hershey , Randy Paffenroth , Harsh Pathak , Simon Tavener

Recent work by Hewitt et al. (2020) provides an interpretation of the empirical success of recurrent neural networks (RNNs) as language models (LMs). It shows that RNNs can efficiently represent bounded hierarchical structures that are…

Computation and Language · Computer Science 2024-06-19 Anej Svete , Robin Shing Moon Chan , Ryan Cotterell

Recent theoretical results show transformers cannot express sequential reasoning problems over long inputs, intuitively because their computational depth is bounded. However, prior work treats the depth as a constant, leaving it unclear to…

Machine Learning · Computer Science 2025-11-07 William Merrill , Ashish Sabharwal

The benefits of depth in feedforward neural networks are well known: composing multiple layers of linear transformations with nonlinear activations enables complex computations. While similar effects are expected in recurrent neural…

Machine Learning · Computer Science 2026-04-03 Maude Lizaire , Michael Rizvi-Martel , Éric Dupuis , Guillaume Rabusseau

This paper studies the approximation capabilities of neural networks that combine layer normalization (LN) with linear layers. We prove that networks consisting of two linear layers with parallel layer normalizations (PLNs) inserted between…

Machine Learning · Computer Science 2026-02-10 Yunhao Ni , Yuxin Guo , Yuhe Liu , Wenxin Sun , Jie Luo , Wenjun Wu , Lei Huang

Graph neural networks (GNNs) are among the most powerful tools in deep learning. They routinely solve complex problems on unstructured networks, such as node classification, graph classification, or link prediction, with high accuracy.…

Machine Learning · Computer Science 2023-08-21 Maciej Besta , Torsten Hoefler

Masked diffusion models (MDMs) for text offer a compelling alternative to traditional autoregressive language models. Parallel generation makes them efficient, but their computational capabilities and the limitations inherent in their…

Machine Learning · Computer Science 2026-04-28 Anej Svete , Ashish Sabharwal

Linear recurrent neural networks (LRNNs) provide a structured approach to sequence modeling that bridges classical linear dynamical systems and modern deep learning, offering both expressive power and theoretical guarantees on stability and…

The ability of neural networks to represent more features than neurons makes interpreting them challenging. This phenomenon, known as superposition, has spurred efforts to find architectures that are more interpretable than standard…

Machine Learning · Computer Science 2023-05-08 Lee Sharkey

It is well understood that different neural network architectures are suited to different tasks, but is there always a single best architecture for a given task? We compare the expressive power of transformers, RNNs, and transformers with…

Machine Learning · Computer Science 2026-01-29 Gilad Yehudai , Noah Amsel , Joan Bruna

Neural language models (LMs) based on recurrent neural networks (RNN) are some of the most successful word and character-level LMs. Why do they work so well, in particular better than linear neural LMs? Possible explanations are that RNNs…

Machine Learning · Statistics 2013-06-21 Marius Pachitariu , Maneesh Sahani

The proliferation of large-scale and structurally complex data has spurred the integration of machine learning methods into statistical modeling. Recurrent neural networks (RNNs), a foundational class of models for time-dependent data, can…

Machine Learning · Statistics 2026-05-05 Yuxi Cai , Lan Li , Feiqing Huang , Guodong Li

Recurrent neural networks have achieved great success in many NLP tasks. However, they have difficulty in parallelization because of the recurrent structure, so it takes much time to train RNNs. In this paper, we introduce sliced recurrent…

Computation and Language · Computer Science 2018-07-09 Zeping Yu , Gongshen Liu

We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural Networks that replaces the softmax output layer by a log-linear output layer, of which the softmax is a special case. This conceptually simple move has two main…

Artificial Intelligence · Computer Science 2016-12-19 Marc Dymetman , Chunyang Xiao
‹ Prev 1 2 3 10 Next ›