English
Related papers

Related papers: Why Are Linear RNNs More Parallelizable?

200 papers

Designing models that are both expressive and preserve known invariances of tasks is an increasingly hard problem. Existing solutions tradeoff invariance for computational or memory resources. In this work, we show how to leverage…

Machine Learning · Computer Science 2023-09-29 Leonardo Cotta , Gal Yehuda , Assaf Schuster , Chris J. Maddison

Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest. While most solutions have focused on single layer…

Machine Learning · Computer Science 2021-04-22 Wen Tang , Emilie Chouzenoux , Jean-Christophe Pesquet , Hamid Krim

Large language models (LLMs) are increasingly costly to deploy, motivating extensive research on model pruning. However, most existing studies focus on instruction-following LLMs, leaving it unclear whether established pruning strategies…

Machine Learning · Computer Science 2026-01-27 Longwei Ding , Anhao Zhao , Fanghua Ye , Ziyang Chen , Xiaoyu Shen

In this paper, we will introduce a novel deep model named Reconciled Polynomial Network (RPN) for deep function learning. RPN has a very general architecture and can be used to build models with various complexities, capacities, and levels…

Machine Learning · Computer Science 2024-07-09 Jiawei Zhang

Recurrent neural networks are convenient and efficient models for language modeling. However, when applied on the level of characters instead of words, they suffer from several problems. In order to successfully model long-term…

Machine Learning · Computer Science 2015-11-25 Piotr Bojanowski , Armand Joulin , Tomas Mikolov

One hypothesis for the success of deep neural networks (DNNs) is that they are highly expressive, which enables them to be applied to many problems, and they have a strong inductive bias towards solutions that are simple, known as…

Quantum Physics · Physics 2024-07-04 Jessica Pointing

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, and music generation all require that a model produce outputs that are sequences. In other domains, such as time series prediction, video…

Machine Learning · Computer Science 2015-10-20 Zachary C. Lipton , John Berkowitz , Charles Elkan

Despite significant advances in Graph Neural Networks (GNNs), their limited expressivity remains a fundamental challenge. Research on GNN expressivity has produced many expressive architectures, leading to architecture hierarchies with…

Machine Learning · Computer Science 2025-10-06 Yam Eitan , Moshe Eliasof , Yoav Gelberg , Fabrizio Frasca , Guy Bar-Shalom , Haggai Maron

Employing equivariance in neural networks leads to greater parameter efficiency and improved generalization performance through the encoding of domain knowledge in the architecture; however, the majority of existing approaches require an a…

Machine Learning · Computer Science 2023-05-31 Emmanouil Theodosis , Karim Helwani , Demba Ba

Simple recurrent neural networks (RNNs) and their more advanced cousins LSTMs etc. have been very successful in sequence modeling. Their theoretical understanding, however, is lacking and has not kept pace with the progress for feedforward…

Machine Learning · Computer Science 2021-06-02 Abhishek Panigrahi , Navin Goyal

Autoregressive language models execute Transformer layers sequentially, creating a latency bottleneck that is not removed by conventional tensor or pipeline parallelism. We study whether this layerwise dependency can be relaxed by treating…

Machine Learning · Computer Science 2026-05-28 Ligong Han , Kai Xu , Hao Wang , Akash Srivastava

Analogical reasoning -- the capacity to identify and map structural relationships between different domains -- is fundamental to human cognition and learning. Recent studies have shown that large language models (LLMs) can sometimes match…

Computation and Language · Computer Science 2025-11-21 Sam Musker , Alex Duchnowski , Raphaël Millière , Ellie Pavlick

Training recurrent neural networks (RNNs) is a hard problem due to degeneracies in the optimization landscape, a problem also known as vanishing/exploding gradients. Short of designing new RNN architectures, previous methods for dealing…

Neural and Evolutionary Computing · Computer Science 2020-02-11 A. Emin Orhan , Xaq Pitkow

Accurate modeling of complex physical problems, such as fluid-structure interaction, requires multiphysics coupling across the interface, which often has intricate geometry and dynamic boundaries. Conventional numerical methods face…

Numerical Analysis · Mathematics 2023-08-08 Yunlong Li , Fei Wang

Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-structured data. While numerous approaches have been proposed to improve GNNs in terms of the Weisfeiler-Lehman (WL) test, generally there is still a…

Machine Learning · Computer Science 2024-02-13 Bohang Zhang , Shengjie Luo , Liwei Wang , Di He

Conventional wisdom states that deep linear neural networks benefit from expressiveness and optimization advantages over a single linear layer. This paper suggests that, in practice, the training process of deep linear fully-connected…

Machine Learning · Computer Science 2022-06-10 Oriel BenShmuel

Recurrent Graph Neural Networks (RGNNs) extend standard GNNs by iterating message-passing until some stopping condition is met. Various RGNN models have been proposed in the literature. In this paper, we study three such models: converging…

Machine Learning · Computer Science 2026-04-29 Jeroen Bollen , Stijn Vansummeren

Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have…

Machine Learning · Computer Science 2025-10-17 Jonas Geiping , Xinyu Yang , Guinan Su

Large language models (LLMs) have shown significant progress in reasoning tasks. However, recent studies show that transformers and LLMs fail catastrophically once reasoning problems exceed modest complexity. We revisit these findings…

Artificial Intelligence · Computer Science 2025-10-28 Revanth Rameshkumar , Jimson Huang , Yunxin Sun , Fei Xia , Abulhair Saparov

Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are hard to optimize and slow to train. Deep state-space models (SSMs) have recently been shown to perform remarkably well on long sequence modeling tasks, and have…

Machine Learning · Computer Science 2023-03-14 Antonio Orvieto , Samuel L Smith , Albert Gu , Anushan Fernando , Caglar Gulcehre , Razvan Pascanu , Soham De