Delay Embedding Theory of Neural Sequence Models

• URL: http://arxiv.org/abs/2406.11993v1
• Date: Mon, 17 Jun 2024 18:07:16 GMT
• Title: Delay Embedding Theory of Neural Sequence Models
• Abstract summary: Theory of delay embeddings in dynamical systems prove that unobserved variables can be recovered from the history of only a handful of observed variables. We measure the capacities of sequence models to reconstruct unobserved dynamics.
• Score: 6.294884163829946
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To generate coherent responses, language models infer unobserved meaning from their input text sequence. One potential explanation for this capability arises from theories of delay embeddings in dynamical systems, which prove that unobserved variables can be recovered from the history of only a handful of observed variables. To test whether language models are effectively constructing delay embeddings, we measure the capacities of sequence models to reconstruct unobserved dynamics. We trained 1-layer transformer decoders and state-space sequence models on next-step prediction from noisy, partially-observed time series data. We found that each sequence layer can learn a viable embedding of the underlying system. However, state-space models have a stronger inductive bias than transformers-in particular, they more effectively reconstruct unobserved information at initialization, leading to more parameter-efficient models and lower error on dynamics tasks. Our work thus forges a novel connection between dynamical systems and deep learning sequence models via delay embedding theory.

Related papers

• Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks [50.79340930913805]
  We study a class of inductive tasks that unifies several synthetic tasks known in the literature, including in-context n-grams and multi-hop reasoning.<n>By casting circuit formation as a low-dimensional dynamical phenomenon, we take a step toward a predictive theory of how Transformers learn.
  arXiv  Detail & Related papers  (2026-07-13T17:56:11Z)
• Transformer Learning of Chaotic Collective Dynamics in Many-Body Systems [0.0]
  We show that a self-attention-based transformer framework provides an effective approach for modeling chaotic collective dynamics.<n>We study the one-dimensional semiclassical Holstein model, where interaction quenches induce strongly nonlinear and chaotic dynamics.<n>Our results establish self-attention as a powerful mechanism for learning effective reduced dynamics in chaotic many-body systems.
  arXiv  Detail & Related papers  (2026-01-27T01:33:33Z)
• A Mechanistic Analysis of Transformers for Dynamical Systems [4.590170084532207]
  We study the representational capabilities and limitations of single-layer Transformers when applied to dynamical data.<n>For linear systems, we show that the convexity constraint imposed by softmax attention fundamentally restricts the class of dynamics that can be represented.<n>For nonlinear systems under partial observability, attention instead acts as an adaptive delay-embedding mechanism.
  arXiv  Detail & Related papers  (2025-12-24T11:21:07Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models [71.63194926457119]
  We introduce Dynamical Diffusion (DyDiff), a theoretically sound framework that incorporates temporally aware forward and reverse processes. Experiments across scientifictemporal forecasting, video prediction, and time series forecasting demonstrate that Dynamical Diffusion consistently improves performance in temporal predictive tasks.
  arXiv  Detail & Related papers  (2025-03-02T16:10:32Z)
• Latent Space Energy-based Neural ODEs [73.01344439786524]
  This paper introduces a novel family of deep dynamical models designed to represent continuous-time sequence data. We train the model using maximum likelihood estimation with Markov chain Monte Carlo. Experiments on oscillating systems, videos and real-world state sequences (MuJoCo) illustrate that ODEs with the learnable energy-based prior outperform existing counterparts.
  arXiv  Detail & Related papers  (2024-09-05T18:14:22Z)
• Neural Persistence Dynamics [8.197801260302642]
  We consider the problem of learning the dynamics in the topology of time-evolving point clouds. Our proposed model - $textitNeural Persistence Dynamics$ - substantially outperforms the state-of-the-art across a diverse set of parameter regression tasks.
  arXiv  Detail & Related papers  (2024-05-24T17:20:18Z)
• eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling [9.52474299688276]
  We introduce a low-rank structured variational autoencoder framework for nonlinear state-space graphical models. We show that our approach consistently demonstrates the ability to learn a more predictive generative model.
  arXiv  Detail & Related papers  (2024-03-03T02:19:49Z)
• Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective [63.60312929416228]
  textbftextitAttraos incorporates chaos theory into long-term time series forecasting. We show that Attraos outperforms various LTSF methods on mainstream datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
  arXiv  Detail & Related papers  (2024-02-18T05:35:01Z)
• Foundational Inference Models for Dynamical Systems [5.549794481031468]
  We offer a fresh perspective on the classical problem of imputing missing time series data, whose underlying dynamics are assumed to be determined by ODEs. We propose a novel supervised learning framework for zero-shot time series imputation, through parametric functions satisfying some (hidden) ODEs. We empirically demonstrate that one and the same (pretrained) recognition model can perform zero-shot imputation across 63 distinct time series with missing values.
  arXiv  Detail & Related papers  (2024-02-12T11:48:54Z)
• Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks? [18.92828441607381]
  We show that embeddings induce a model that fits observations well but simultaneously has incorrect dynamical behaviours. We propose a simple embedding-free alternative based on parametrising two additive vector-field components.
  arXiv  Detail & Related papers  (2023-05-20T12:41:47Z)
• Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections [6.345523830122166]
  We propose PolyODE, a formulation that enforces long-range memory and preserves a global representation of the underlying dynamical system. Our construction is backed by favourable theoretical guarantees and we demonstrate that it outperforms previous works in the reconstruction of past and future data.
  arXiv  Detail & Related papers  (2023-03-03T10:49:09Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics [6.829711787905569]
  We propose a new decomposed dynamical system model that represents complex non-stationary and nonlinear dynamics of time series data. Our model is trained through a dictionary learning procedure, where we leverage recent results in tracking sparse vectors over time. In both continuous-time and discrete-time instructional examples we demonstrate that our model can well approximate the original system.
  arXiv  Detail & Related papers  (2022-06-07T02:25:38Z)
• Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations [68.62843292346813]
  We propose a structured latent ODE model that captures system input variations within its latent representation. Building on a static variable specification, our model learns factors of variation for each input to the system, thus separating the effects of the system inputs in the latent space.
  arXiv  Detail & Related papers  (2022-02-25T20:00:56Z)
• 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.