Oscillatory State-Space Models

• URL: http://arxiv.org/abs/2410.03943v1
• Date: Fri, 4 Oct 2024 22:00:13 GMT
• Title: Oscillatory State-Space Models
• Authors: T. Konstantin Rusch, Daniela Rus,
• Abstract summary: We propose Lineary State-Space models (LinOSS) for efficiently learning on long sequences. A stable discretization, integrated over time using fast associative parallel scans, yields the proposed state-space model. We show that LinOSS is universal, i.e., it can approximate any continuous and causal operator mapping between time-varying functions.
• Score: 61.923849241099184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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. A stable discretization, integrated over time using fast associative parallel scans, yields the proposed state-space model. We prove that LinOSS produces stable dynamics only requiring nonnegative diagonal state matrix. This is in stark contrast to many previous state-space models relying heavily on restrictive parameterizations. Moreover, we rigorously show that LinOSS is universal, i.e., it can approximate any continuous and causal operator mapping between time-varying functions, to desired accuracy. In addition, we show that an implicit-explicit discretization of LinOSS perfectly conserves the symmetry of time reversibility of the underlying dynamics. Together, these properties enable efficient modeling of long-range interactions, while ensuring stable and accurate long-horizon forecasting. Finally, our empirical results, spanning a wide range of time-series tasks from mid-range to very long-range classification and regression, as well as long-horizon forecasting, demonstrate that our proposed LinOSS model consistently outperforms state-of-the-art sequence models. Notably, LinOSS outperforms Mamba by nearly 2x and LRU by 2.5x on a sequence modeling task with sequences of length 50k.

Related papers

• DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs [59.434893231950205]
  Dynamic graph learning aims to uncover evolutionary laws in real-world systems. We propose DyG-Mamba, a new continuous state space model for dynamic graph learning. We show that DyG-Mamba achieves state-of-the-art performance on most datasets.
  arXiv  Detail & Related papers  (2024-08-13T15:21:46Z)
• Longhorn: State Space Models are Amortized Online Learners [51.10124201221601]
  State-space models (SSMs) offer linear decoding efficiency while maintaining parallelism during training. In this work, we explore SSM design through the lens of online learning, conceptualizing SSMs as meta-modules for specific online learning problems. We introduce a novel deep SSM architecture, Longhorn, whose update resembles the closed-form solution for solving the online associative recall problem.
  arXiv  Detail & Related papers  (2024-07-19T11:12:08Z)
• Accelerating Phase Field Simulations Through a Hybrid Adaptive Fourier Neural Operator with U-Net Backbone [0.7329200485567827]
  We propose U-Shaped Adaptive Fourier Neural Operators (U-AFNO), a machine learning (ML) model inspired by recent advances in neural operator learning. We use U-AFNOs to learn the dynamics mapping the field at a current time step into a later time step. Our model reproduces the key micro-structure statistics and QoIs with a level of accuracy on-par with the high-fidelity numerical solver.
  arXiv  Detail & Related papers  (2024-06-24T20:13:23Z)
• Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models [5.37935922811333]
  State Space Models (SSMs) are classical approaches for univariate time series modeling. We present Chimera that uses two input-dependent 2-D SSM heads with different discretization processes to learn long-term progression and seasonal patterns. Our experimental evaluation shows the superior performance of Chimera on extensive and diverse benchmarks.
  arXiv  Detail & Related papers  (2024-06-06T17:58:09Z)
• Deep Latent State Space Models for Time-Series Generation [68.45746489575032]
  We propose LS4, a generative model for sequences with latent variables evolving according to a state space ODE. Inspired by recent deep state space models (S4), we achieve speedups by leveraging a convolutional representation of LS4. We show that LS4 significantly outperforms previous continuous-time generative models in terms of marginal distribution, classification, and prediction scores on real-world datasets.
  arXiv  Detail & Related papers  (2022-12-24T15:17:42Z)
• Learning and Inference in Sparse Coding Models with Langevin Dynamics [3.0600309122672726]
  We describe a system capable of inference and learning in a probabilistic latent variable model. We demonstrate this idea for a sparse coding model by deriving a continuous-time equation for inferring its latent variables via Langevin dynamics. We show that Langevin dynamics lead to an efficient procedure for sampling from the posterior distribution in the 'L0 sparse' regime, where latent variables are encouraged to be set to zero as opposed to having a small L1 norm.
  arXiv  Detail & Related papers  (2022-04-23T23:16:47Z)
• Role of stochastic noise and generalization error in the time propagation of neural-network quantum states [0.0]
  Neural-network quantum states (NQS) have been shown to be a suitable variational ansatz to simulate out-of-equilibrium dynamics. We show that stable and accurate time propagation can be achieved in regimes of sufficiently regularized variational dynamics.
  arXiv  Detail & Related papers  (2021-05-03T17:55:09Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.