# Tractable Inference for Complex Stochastic Processes

arXiv: https://arxiv.org/abs/1301.7362 · HTML: https://mlsanity.com/paper/1301.7362/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2013.

## Built on by (most cited first, 20 of 20)

- [Shapley Explanation Networks](https://mlsanity.com/paper/2104.02297/) (2021)
- [Planning in Observable POMDPs in Quasipolynomial Time](https://mlsanity.com/paper/2201.04735/) (2022)
- [Dropout Injection at Test Time for Post Hoc Uncertainty Quantification in Neural Networks](https://mlsanity.com/paper/2302.02924/) (2023)
- [SLURP: Side Learning Uncertainty for Regression Problems](https://mlsanity.com/paper/2110.11182/) (2021)
- [A General Framework for quantifying Aleatoric and Epistemic uncertainty in Graph Neural Networks](https://mlsanity.com/paper/2205.09968/) (2022)
- [An Analytic Solution to Covariance Propagation in Neural Networks](https://mlsanity.com/paper/2403.16163/) (2024)
- [Streaming Factor Trajectory Learning for Temporal Tensor Decomposition](https://mlsanity.com/paper/2310.17021/) (2023)
- [Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs](https://mlsanity.com/paper/2204.01160/) (2022)
- [Learning Complicated Manipulation Skills via Deterministic Policy with Limited Demonstrations](https://mlsanity.com/paper/2303.16469/) (2023)
- [A Complete Characterisation of ReLU-Invariant Distributions](https://mlsanity.com/paper/2112.06532/) (2021)
- [IBIA: Bayesian Inference via Incremental Build-Infer-Approximate operations on Clique Trees](https://mlsanity.com/paper/2202.12003/) (2022)
- [Approximate Inference for Stochastic Planning in Factored Spaces](https://mlsanity.com/paper/2203.12139/) (2022)
- [IBIA: An Incremental Build-Infer-Approximate Framework for Approximate Inference of Partition Function](https://mlsanity.com/paper/2304.06366/) (2023)
- [ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs](https://mlsanity.com/paper/2510.21107/) (2025)
- [Improving Learning from Demonstrations by Learning from Experience](https://mlsanity.com/paper/2111.08156/) (2021)
- [Uncertainty Detection and Reduction in Neural Decoding of EEG Signals](https://mlsanity.com/paper/2201.00627/) (2021)
- [Denoising the Future: Top-p Distributions for Moving Through Time](https://mlsanity.com/paper/2506.07578/) (2025)
- [Kalman Bayesian Transformer](https://mlsanity.com/paper/2509.10695/) (2025)
- [A Direct Approach for Handling Contextual Bandits with Latent State Dynamics](https://mlsanity.com/paper/2604.08149/) (2026)
- [Extending Causal Metamodeling to a non-Markovian Queue](https://mlsanity.com/paper/2606.00795/) (2026)

## Abstract (arXiv)

The monitoring and control of any dynamic system depends crucially on the ability to reason about its current status and its future trajectory. In the case of a stochastic system, these tasks typically involve the use of a belief state- a probability distribution over the state of the process at a given point in time. Unfortunately, the state spaces of complex processes are very large, making an explicit representation of a belief state intractable. Even in dynamic Bayesian networks (DBNs), where the process itself can be represented compactly, the representation of the belief state is intractable. We investigate the idea of maintaining a compact approximation to the true belief state, and analyze the conditions under which the errors due to the approximations taken over the lifetime of the process do not accumulate to make our answers completely irrelevant. We show that the error in a belief state contracts exponentially as the process evolves. Thus, even with multiple approximations, the error in our process remains bounded indefinitely. We show how the additional structure of a DBN can be used to design our approximation scheme, improving its performance significantly. We demonstrate the applicability of our ideas in the context of a monitoring task, showing that orders of magnitude faster inference can be achieved with only a small degradation in accuracy.