paper-with-me

홈 › Papers

Uncertainty relations and fluctuation theorems for Bayes nets

2019-11-07 · David H. Wolpert

Recent research has considered the stochastic thermodynamics of multiple interacting systems, representing the overall system as a Bayes net. I derive fluctuation theorems governing the entropy production (EP)of arbitrary sets of the systems in such a Bayes net. I also derive ``conditional'' fluctuation theorems, governing the distribution of EP in one set of systems conditioned on the EP of a different set of systems. I then derive thermodynamic uncertainty relations relating the EP of the overall system to the precisions of probability currents within the individual systems.

📄 PDF Abstract BibTeX arXiv:1911.02700

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes

2022-11-04 · Mizu Nishikawa-Toomey, Tristan Deleu, Jithendaraa Subramanian, Yoshua Bengio 외

Bayesian causal structure learning aims to learn a posterior distribution over directed acyclic graphs (DAGs), and the mechanisms that define the relationship between parent and child variables. By taking a Bayesian appr…

Bayesian Hypernetworks

2017-10-13 · ICLR 2018 1 · David Krueger, Chin-wei Huang, Riashat Islam, Ryan Turner 외

We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork $\h$ is a neural network which learns to transform a simple noise distribution, $p(\vec\epsilon)…

Active LearningAnomaly DetectionBayesian InferenceVariational Inference

Uncertainty Reasoning for Probabilistic Petri Nets via Bayesian Networks

2020-09-30 · Rebecca Bernemann, Benjamin Cabrera, Reiko Heckel, Barbara König

This paper exploits extended Bayesian networks for uncertainty reasoning on Petri nets, where firing of transitions is probabilistic. In particular, Bayesian networks are used as symbolic representations of probability d…

BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

2021-12-06 · NeurIPS 2021 12 · Chris Cundy, Aditya Grover, Stefano Ermon

A structural equation model (SEM) is an effective framework to reason over causal relationships represented via a directed acyclic graph (DAG). Recent advances have enabled effective maximum-likelihood point estimation o…

Causal DiscoveryStochastic OptimizationVariational Inference

Machine learning in and out of equilibrium

2023-06-06 · Shishir Adhikari, Alkan Kabakçıoğlu, Alexander Strang, Deniz Yuret 외

The algorithms used to train neural networks, like stochastic gradient descent (SGD), have close parallels to natural processes that navigate a high-dimensional parameter space -- for example protein folding or evolution…

NavigateProtein Folding