Inspectable Neural Markov Models for Non-Stationary Time Series

• URL: http://arxiv.org/abs/2605.30943v1
• Date: Fri, 29 May 2026 07:29:35 GMT
• Title: Inspectable Neural Markov Models for Non-Stationary Time Series
• Abstract summary: We propose a hybrid approach that parameterizes the manifold of Markov chains through a neural network.<n>We show that conditioning on realized volatility produces a more internally consistent Markovian structure than return-based states.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modeling non-stationary stochastic systems requires balancing the representational capacity of deep learning with the structural transparency of classical probabilistic models. Markov transition matrices provide such a framework, but traditional frequency-based estimation collapses at high resolutions due to data sparsity. We propose a hybrid approach that parameterizes the manifold of stochastic matrices through a neural network, enabling estimation of time-inhomogeneous Markov chains in sparse-data regimes, and use financial markets as a testbed to investigate the Markov state variable as a critical inductive bias. We show that conditioning on realized volatility produces a more internally consistent Markovian structure than return-based states, achieving a $5.6\%$ reduction in Chapman-Kolmogorov discrepancy and superior held-out likelihood in 9 of 10 assets. Unlike black-box sequence models, our approach generates explicit matrices amenable to direct geometric analysis, surfacing structural findings such as the universal homogenization of transition probabilities under high-volatility regimes.

Related papers

• Volterra Generative Models [0.0]
  We introduce Volterra generative models, a continuous-time score-based framework whose forward process injects path-dependent noise through fractional kernels.<n>We prove squared error bounds, derive an augmented linear-Gaussian forward process, and show that the learning can remain data-dimensional.<n>Experiments on MNIST and CIFAR-10 show that persistent fractional perturbations with small Markovian lifts can improve score-based generation.
  arXiv  Detail & Related papers  (2026-06-16T15:40:09Z)
• Nonlinear and Heavy-Tailed Predictability in Transition-Energy Financial Markets [0.0]
  This paper investigates whether transition-related financial returns exhibit residual non-linear predictability.<n>We develop a hybrid forecasting framework combining Student-t Vector Autoregressions with nonlinear recurrent residual learning architectures.
  arXiv  Detail & Related papers  (2026-05-26T11:52:31Z)
• Learning Time-Inhomogeneous Markov Dynamics in Financial Time Series via Neural Parameterization [0.0]
  We introduce a framework that utilizes neural networks strictly as parameterization engines to generate explicit, time-varying Markov transition matrices.<n>By constraining the neural network to output its predictions as a formal operator, we maintain complete structural interpretability.<n>This framework demonstrates how neural networks can be constrained to make rigorous, classical operator analysis viable for complex real-world time series.
  arXiv  Detail & Related papers  (2026-05-06T09:39:04Z)
• KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra [65.11254608352982]
  We introduce a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators.<n>By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation.
  arXiv  Detail & Related papers  (2026-02-15T06:32:23Z)
• On Forgetting and Stability of Score-based Generative models [6.259598237089842]
  Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning.<n>This paper provides quantitative bounds on the sampling error of score-based generative models by leveraging stability and forgetting properties of the Markov chain associated with the reverse-time dynamics.
  arXiv  Detail & Related papers  (2026-01-29T15:37:50Z)
• SIGMA: Scalable Spectral Insights for LLM Collapse [51.863164847253366]
  We introduce SIGMA (Spectral Inequalities for Gram Matrix Analysis), a unified framework for model collapse.<n>By utilizing benchmarks that deriving and deterministic bounds on the matrix's spectrum, SIGMA provides a mathematically grounded metric to track the contraction of the representation space.<n>We demonstrate that SIGMA effectively captures the transition towards states, offering both theoretical insights into the mechanics of collapse.
  arXiv  Detail & Related papers  (2026-01-06T19:47:11Z)
• Low-Rank Tensors for Multi-Dimensional Markov Models [33.35376484951434]
  We present low-rank tensors for representing transition probabilities on multi-dimensional state spaces. Our proposed model yields a parsimonious representation with fewer parameters than matrix-based approaches.
  arXiv  Detail & Related papers  (2024-11-04T14:06:49Z)
• A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics [51.147876395589925]
  A non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time. A fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance.
  arXiv  Detail & Related papers  (2024-02-26T04:39:01Z)
• On the Identifiability of Switching Dynamical Systems [34.514858559727266]
  identifiability of latent variable models has received increasing attention due to its relevance in interpretability and out-of-distribution generalisation. We study the identifiability of Switching Dynamical Systems, taking an initial step toward extending identifiability analysis to sequential latent variable models.
  arXiv  Detail & Related papers  (2023-05-25T10:53:18Z)
• Regularized Vector Quantization for Tokenized Image Synthesis [126.96880843754066]
  Quantizing images into discrete representations has been a fundamental problem in unified generative modeling. deterministic quantization suffers from severe codebook collapse and misalignment with inference stage while quantization suffers from low codebook utilization and reconstruction objective. This paper presents a regularized vector quantization framework that allows to mitigate perturbed above issues effectively by applying regularization from two perspectives.
  arXiv  Detail & Related papers  (2023-03-11T15:20:54Z)
• 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)
• Estimation of Switched Markov Polynomial NARX models [75.91002178647165]
  We identify a class of models for hybrid dynamical systems characterized by nonlinear autoregressive (NARX) components. The proposed approach is demonstrated on a SMNARX problem composed by three nonlinear sub-models with specific regressors.
  arXiv  Detail & Related papers  (2020-09-29T15:00:47Z)

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.