mlsanityData to 7 Oct 2026

Neural Markov Jump Processes

arXiv 2305.19744 ↗First posted 31 May 2023cs.LG stat.MLcited by 11

Not on the map. Why?

Abstract (arXiv)

Markov jump processes are continuous-time stochastic processes with a wide range of applications in both natural and social sciences. Despite their widespread use, inference in these models is highly non-trivial and typically proceeds via either Monte Carlo or expectation-maximization methods. In this work we introduce an alternative, variational inference algorithm for Markov jump processes which relies on neural ordinary differential equations, and is trainable via back-propagation. Our methodology learns neural, continuous-time representations of the observed data, that are used to approximate the initial distribution and time-dependent transition probability rates of the posterior Markov jump process. The time-independent rates of the prior process are in contrast trained akin to generative adversarial networks. We test our approach on synthetic data sampled from ground-truth Markov jump processes, experimental switching ion channel data and molecular dynamics simulations. Source code to reproduce our experiments is available online.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 24 of its 77 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

24 of 77 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  8. 2022On Neural Differential Equationscited by 264
  9. 2015Conditional Computation in Neural Networks for faster modelscited by 166
  10. 2019Neural Jump Stochastic Differential Equationscited by 147
  11. 2017VAMPnets: Deep learning of molecular kineticscited by 135
  12. 2016Learning in Implicit Generative Modelscited by 124
12 more
  1. 2018Fast Decoding in Sequence Models using Discrete Latent Variablescited by 103
  2. 2020Neural Spatio-Temporal Point Processescited by 92
  3. 2018Machine Learning of coarse-grained Molecular Dynamics Force Fieldscited by 68
  4. 2020STEER: Simple Temporal Regularization For Neural ODEscited by 58
  5. 2018Semi-Implicit Variational Inferencecited by 55
  6. 2019Self-attention with Functional Time Representation Learningcited by 52
  7. 2017Variational Inference using Implicit Distributionscited by 39
  8. 2018Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networkscited by 13
  9. 2019Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoderscited by 13
  10. 2021Variational Inference for Continuous-Time Switching Dynamical Systemscited by 9
  11. 2019Moment-Based Variational Inference for Markov Jump Processescited by 6
  12. 2015JUMP-Means: Small-Variance Asymptotics for Markov Jump Processescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 5; 2026: 2.

11 papers.

  1. 2024Zero-shot Imputation with Foundation Inference Models for Dynamical Systemscited by 13
  2. 2024Foundation Inference Models for Markov Jump Processescited by 13
  3. 2024When to Sense and Control? A Time-adaptive Approach for Continuous-Time RLcited by 9
  4. 2023Entropic Matching for Expectation Propagation of Markov Jump Processescited by 2
  5. 2025Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Predictioncited by 2
  6. 2025Towards Fast Coarse-graining and Equation Discovery with Foundation Inference Modelscited by 1
  7. 2025Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learningcited by 0
  8. 2025On Foundation Models for Temporal Point Processes to Accelerate Scientific Discoverycited by 0
  9. 2025Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Spacecited by 0
  10. 2026EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMscited by 0
  11. 2026Variational Inference for L'evy Process-Driven SDEs via Neural Tiltingcited by 0