English
Related papers

Related papers: Can a Transformer Represent a Kalman Filter?

200 papers

Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this…

Machine Learning · Computer Science 2024-06-04 Romain Ilbert , Ambroise Odonnat , Vasilii Feofanov , Aladin Virmaux , Giuseppe Paolo , Themis Palpanas , Ievgen Redko

In this paper, we propose a new model reduction technique for linear stochastic systems that builds upon knowledge filtering and utilizes optimal Kalman filtering techniques. This new technique will reduce the dimension of the noise…

Systems and Control · Electrical Eng. & Systems 2023-09-18 Maico Hendrikus Wilhelmus Engelaar , Licio Romao , Yulong Gao , Mircea Lazar , Alessandro Abate , Sofie Haesaert

State estimation is a fundamental problem in control and signal processing, for which the Kalman Filter provides an optimal solution under linear dynamics, Gaussian noise, and known noise covariances. However, these assumptions often fail…

Machine Learning · Computer Science 2026-05-27 Vasileios Saketos , Ming Xiao

In this paper we provide novel closed-form expressions enabling differentiation of any scalar function of the Kalman filter's outputs with respect to all its tuning parameters and to the measurements. The approach differs from the previous…

Optimization and Control · Mathematics 2023-04-03 Colin Parellier , Axel Barrau , Silvere Bonnabel

Transformers are increasingly adopted for modeling and forecasting time-series, yet their internal mechanisms remain poorly understood from a dynamical systems perspective. In contrast to classical autoregressive and state-space models,…

Machine Learning · Computer Science 2025-12-25 Gregory Duthé , Nikolaos Evangelou , Wei Liu , Ioannis G. Kevrekidis , Eleni Chatzi

In Kalman filtering, unknown inputs are often estimated by augmenting the state vector, which introduces reliance on fictitious input models. In contrast, minimum-variance unbiased methods estimate inputs and states separately, avoiding…

Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. The self-attention mechanism underpinning the strength of ViTs has a quadratic complexity in both computation and memory usage. This motivates the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Jiachen Lu , Junge Zhang , Xiatian Zhu , Jianfeng Feng , Tao Xiang , Li Zhang

In order to integrate uncertainty estimates into deep time-series modelling, Kalman Filters (KFs) (Kalman et al., 1960) have been integrated with deep learning models, however, such approaches typically rely on approximate inference…

Machine Learning · Computer Science 2019-05-20 Philipp Becker , Harit Pandya , Gregor Gebhardt , Cheng Zhao , James Taylor , Gerhard Neumann

Contemporary data assimilation often involves millions of prediction variables. The classical Kalman filter is no longer computationally feasible in such a high dimensional context. This problem can often be resolved by exploiting the…

Statistics Theory · Mathematics 2016-06-30 Andrew J. Majda , Xin T. Tong

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Machine Learning · Computer Science 2025-07-15 Sai Surya Duvvuri , Inderjit S. Dhillon

Powerful generative artificial intelligence from large language models (LLMs) harnesses extensive computational resources for inference. In this work, we investigate the transformer architecture, a key component of these models, under the…

We introduce a novel nonlinear Kalman filter that utilizes reparametrization gradients. The widely used parametric approximation is based on a jointly Gaussian assumption of the state-space model, which is in turn equivalent to minimizing…

Machine Learning · Computer Science 2023-03-09 San Gultekin , Brendan Kitts , Aaron Flores , John Paisley

Inference and simulation in the context of high-dimensional dynamical systems remain computationally challenging problems. Some form of dimensionality reduction is required to make the problem tractable in general. In this paper, we propose…

Machine Learning · Statistics 2024-01-04 Jonathan Schmidt , Philipp Hennig , Jörg Nick , Filip Tronarp

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

Recent advances in diffusion-based robot policies have demonstrated significant potential in imitating multi-modal behaviors. However, these approaches typically require large quantities of demonstration data paired with corresponding robot…

Robotics · Computer Science 2025-03-26 Jianxin Bi , Kelvin Lim , Kaiqi Chen , Yifei Huang , Harold Soh

Self-attention in Transformers is typically implemented as $\mathrm{softmax}(QK^\top/\sqrt{d})V$, where $Q=XW_Q$, $K=XW_K$, and $V=XW_V$ are learned linear projections of the input $X$. We ask whether these learned projections are…

Machine Learning · Computer Science 2026-05-05 Debarshi Kundu , Archisman Ghosh , Swaroop Ghosh , Vasant Honavar

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of…

Machine Learning · Computer Science 2025-12-01 Wei Shi , Yuan Cao

Robustness and adaptivity are two competing objectives in Kalman filters (KF). Robustness involves temporarily inflating prior estimates of noise covariances, while adaptivity updates prior beliefs by exploiting measurements. In practical…

Information Theory · Computer Science 2026-05-11 Shilei Li , Dawei Shi , Hao Yu , Ling Shi

The Kalman filter is a fundamental tool for state estimation in dynamical systems. While originally developed for linear Gaussian settings, it has been extended to nonlinear problems through approaches such as the extended and unscented…

Optimization and Control · Mathematics 2025-09-10 Yuan Wu , Sicheng He