English
Related papers

Related papers: Spectral State Space Models

200 papers

Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision, e.g., GPT-3 and Swin Transformer. Although originally…

Machine Learning · Computer Science 2023-06-27 Muning Wen , Runji Lin , Hanjing Wang , Yaodong Yang , Ying Wen , Luo Mai , Jun Wang , Haifeng Zhang , Weinan Zhang

Long Short-Term Memory (LSTM) neural network models have become the cornerstone for sequential data modeling in numerous applications, ranging from natural language processing to time series forecasting. Despite their success, the problem…

Machine Learning · Statistics 2026-05-26 Fahad Mostafa

Sequence models based on linear state spaces (SSMs) have recently emerged as a promising choice of architecture for modeling long range dependencies across various modalities. However, they invariably rely on discretization of a continuous…

Machine Learning · Computer Science 2023-11-15 Ankit Gupta , Harsh Mehta , Jonathan Berant

State space models (SSMs) leverage linear, time-invariant (LTI) systems to effectively learn sequences with long-range dependencies. By analyzing the transfer functions of LTI systems, we find that SSMs exhibit an implicit bias toward…

Machine Learning · Computer Science 2024-10-04 Annan Yu , Dongwei Lyu , Soon Hoe Lim , Michael W. Mahoney , N. Benjamin Erichson

This paper contrasts recursive state space models and direct multi-step predictors for linear predictive control. We provide a tutorial exposition for both model structures to solve the following problems: 1. stochastic optimal control; 2.…

Optimization and Control · Mathematics 2023-10-09 Johannes Köhler , Kim P. Wabersich , Julian Berberich , Melanie N. Zeilinger

Foundation models are typically trained at a fixed computational capacity, while real-world applications require deployment across platforms with different resource constraints. Current approaches usually rely on training families of model…

Machine Learning · Computer Science 2026-02-10 Dachuan Song , Xuan Wang

Although state-space models (SSMs) have demonstrated strong performance on long-sequence benchmarks, most research has emphasized predictive accuracy rather than interpretability. In this work, we present the first systematic kernel…

Machine Learning · Computer Science 2026-01-21 Srividya Ravikumar , Abhinav Anand , Shweta Verma , Mira Mezini

We investigate nonlinear prediction/regression in an online setting and introduce a hybrid model that effectively mitigates, via a joint mechanism through a state space formulation, the need for domain-specific feature engineering issues of…

Machine Learning · Statistics 2023-09-20 Mustafa E. Aydın , Arda Fazla , Suleyman S. Kozat

Probabilistic modeling is one of the foundations of modern machine learning and artificial intelligence. In this paper, we propose a novel type of probabilistic models named latent dependency forest models (LDFMs). A LDFM models the…

Artificial Intelligence · Computer Science 2016-11-22 Shanbo Chu , Yong Jiang , Kewei Tu

State space models (SSMs) have shown impressive results on tasks that require modeling long-range dependencies and efficiently scale to long sequences owing to their subquadratic runtime complexity. Originally designed for continuous…

Computation and Language · Computer Science 2023-10-31 Mahan Fathi , Jonathan Pilault , Orhan Firat , Christopher Pal , Pierre-Luc Bacon , Ross Goroshin

Time series with long-term structure arise in a variety of contexts and capturing this temporal structure is a critical challenge in time series analysis for both inference and forecasting settings. Traditionally, state space models have…

Machine Learning · Statistics 2020-06-12 Anna K. Yanchenko , Sayan Mukherjee

Spiking neural networks (SNNs) provide an energy-efficient solution by utilizing the spike-based and sparse nature of biological systems. Since the advent of Transformers, SNNs have struggled to compete with artificial networks on long…

Neural and Evolutionary Computing · Computer Science 2024-10-24 Yan Zhong , Ruoyu Zhao , Chao Wang , Qinghai Guo , Jianguo Zhang , Zhichao Lu , Luziwei Leng

Effectively modeling long spatiotemporal sequences is challenging due to the need to model complex spatial correlations and long-range temporal dependencies simultaneously. ConvLSTMs attempt to address this by updating tensor-valued states…

Machine Learning · Computer Science 2023-10-31 Jimmy T. H. Smith , Shalini De Mello , Jan Kautz , Scott W. Linderman , Wonmin Byeon

We propose Linear Oscillatory State-Space models (LinOSS) for efficiently learning on long sequences. Inspired by cortical dynamics of biological neural networks, we base our proposed LinOSS model on a system of forced harmonic oscillators.…

Machine Learning · Computer Science 2025-06-19 T. Konstantin Rusch , Daniela Rus

This paper presents a computationally efficient robust model predictive control law for discrete linear time invariant systems subject to additive disturbances that may depend on the state and/or input norms. Despite the dependency being…

Optimization and Control · Mathematics 2019-08-12 Danylo Malyuta , Behcet Acikmese , Martin Cacan

In this paper, we investigate the long-term memory learning capabilities of state-space models (SSMs) from the perspective of parameterization. We prove that state-space models without any reparameterization exhibit a memory limitation…

Machine Learning · Computer Science 2024-06-06 Shida Wang , Qianxiao Li

Reasoning from sequences of raw sensory data is a ubiquitous problem across fields ranging from medical devices to robotics. These problems often involve using long sequences of raw sensor data (e.g. magnetometers, piezoresistors) to…

Models using structured state space sequence (S4) layers have achieved state-of-the-art performance on long-range sequence modeling tasks. An S4 layer combines linear state space models (SSMs), the HiPPO framework, and deep learning to…

Machine Learning · Computer Science 2023-03-06 Jimmy T. H. Smith , Andrew Warrington , Scott W. Linderman

Time series analysis by state-space models is widely used in forecasting and extracting unobservable components like level, slope, and seasonality, along with explanatory variables. However, their reliance on traditional Kalman filtering…

Machine Learning · Statistics 2024-08-20 André Ramos , Davi Valladão , Alexandre Street

In recent years, advancements in deep learning have spurred the development of numerous models for Long-term Time Series Forecasting (LTSF). However, most existing approaches struggle to fully capture the complex and structured dependencies…

Machine Learning · Computer Science 2025-06-04 Zixuan Weng , Jindong Han , Wenzhao Jiang , Hao Liu