English
Related papers

Related papers: Kalman Linear Attention: Parallel Bayesian Filteri…

200 papers

The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically…

Machine Learning · Computer Science 2026-05-15 Yifan Zhang , Zhen Qin , Mengdi Wang , Quanquan Gu

This paper presents an adaptive Kalman filter for a linear dynamic system perturbed by an additive disturbance. The objective is to estimate both of the state and the unknown disturbance concurrently, while learning the disturbance as a…

Optimization and Control · Mathematics 2019-10-23 Taeyoung Lee

Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical insight-even at…

Machine Learning · Computer Science 2025-10-03 Yifei Zuo , Yutong Yin , Zhichen Zeng , Ang Li , Banghua Zhu , Zhaoran Wang

In Online Continual Learning (OCL) a learning system receives a stream of data and sequentially performs prediction and training steps. Important challenges in OCL are concerned with automatic adaptation to the particular non-stationary…

Machine Learning · Computer Science 2024-11-11 Michalis K. Titsias , Alexandre Galashov , Amal Rannen-Triki , Razvan Pascanu , Yee Whye Teh , Jorg Bornschein

Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control. Yet, they lack the computational efficiency of their…

Machine Learning · Computer Science 2024-06-24 Philipp Becker , Niklas Freymuth , Gerhard Neumann

Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…

Computation and Language · Computer Science 2024-07-09 Hugo Pitorro , Pavlo Vasylenko , Marcos Treviso , André F. T. Martins

Continual learning (CL) aims to efficiently learn from a non-stationary data stream, without storing or recomputing all seen samples. CL enables prediction on new tasks by incorporating sequential training samples. Building on this…

Machine Learning · Computer Science 2025-05-27 Chongyang Zhao , Dong Gong

Block-wise sparse attention offers significant efficiency gains for long-context modeling, yet existing methods often suffer from low selection fidelity and cumulative contextual loss by completely discarding unselected blocks. To address…

Computation and Language · Computer Science 2026-02-02 Bailin Wang , Dan Friedman , Tao Lei , Chong Wang

Low dimensional representations of words allow accurate NLP models to be trained on limited annotated data. While most representations ignore words' local context, a natural way to induce context-dependent representations is to perform…

Machine Learning · Statistics 2015-06-02 David Belanger , Sham Kakade

Architectures such as Linformer and Mamba have recently emerged as competitive linear time replacements for transformers. However, corresponding large pretrained models are often unavailable, especially in non-text domains. To remedy this,…

Computation and Language · Computer Science 2025-03-14 Mutian He , Philip N. Garner

The Kalman filter is a fundamental filtering algorithm that fuses noisy sensory data, a previous state estimate, and a dynamics model to produce a principled estimate of the current state. It assumes, and is optimal for, linear models and…

Neural and Evolutionary Computing · Computer Science 2021-04-30 Beren Millidge , Alexander Tschantz , Anil Seth , Christopher Buckley

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Computation and Language · Computer Science 2026-04-17 Zeng You , Yaofo Chen , Qiuwu Chen , Ying Sun , Shuhai Zhang , Yingjian Li , Yaowei Wang , Mingkui Tan

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remained structurally unchanged. Local Linear Attention (LLA) is an attention mechanism derived…

Machine Learning · Computer Science 2026-05-29 Yifei Zuo , Dhruv Pai , Zhichen Zeng , Alec Dewulf , Shuming Hu , Zhaoran Wang

This paper proposes new methodology for sequential state and parameter estimation within the ensemble Kalman filter. The method is fully Bayesian and propagates the joint posterior density of states and parameters over time. In order to…

Methodology · Statistics 2016-11-14 Jonathan R. Stroud , Matthias Katzfuss , Christopher K. Wikle

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they…

Machine Learning · Computer Science 2025-06-18 Yeonju Ro , Zhenyu Zhang , Souvik Kundu , Zhangyang Wang , Aditya Akella

The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of standard quadratic attention, linear attention has been…

Artificial Intelligence · Computer Science 2026-02-13 Hanno Ackermann , Hong Cai , Mohsen Ghafoorian , Amirhossein Habibian

The traditional Kalman filter (KF) is widely applied in control systems, but it relies heavily on the accuracy of the system model and noise parameters, leading to potential performance degradation when facing inaccuracies. To address this…

Systems and Control · Electrical Eng. & Systems 2024-04-08 Jiaming Wang , Xinyu Geng , Jun Xu

Linear attention offers a linear-time alternative to self-attention but often struggles to capture long-range patterns. We revisit linear attention through a prediction-correction lens and show that prevalent variants can be written as a…

Machine Learning · Computer Science 2025-10-01 Xunhao Lai , Jialiang Kang , Jianqiao Lu , Tong Lin , Pengyu Zhao

Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attention. Recent LA models such as Mamba2 and GDN interpret linear recurrences as…

Machine Learning · Computer Science 2026-05-08 Yulong Huang , Xiang Liu , Hongxiang Huang , Xiaopeng Lin , Zunchang Liu , Xiaowen Chu , Zeke Xie , Bojun Cheng