Stochastic Differential Equations
PulseAugur coverage of Stochastic Differential Equations — every cluster mentioning Stochastic Differential Equations across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Two new papers explore theoretical underpinnings of score-based generative models
Two new arXiv papers explore score-based generative models from different theoretical angles. The first paper introduces Score Anisotropy Directions (SADs) to analyze network architecture's influence on model biases and…
-
New Dynamic Structural Causal Models paper introduced on arXiv
Philip Boeken has introduced Dynamic Structural Causal Models (DSCMs) in a new arXiv paper. These models are designed to represent time-dependent systems, including those with cyclic time and latent confounding variable…
-
New framework connects causal graphs and do-calculus to SDEs · 2 sources tracked
Researchers have developed a framework for understanding causal graphs and do-calculus within the context of stochastic differential equations (SDEs). This work establishes the sigma-separation Markov property and do-ca…
-
New bounds established for identifying parameters in interventional SDEs
Researchers have developed new theoretical bounds for the unique recovery of parameters in stochastic differential equations (SDEs) when subjected to multiple interventions. This work provides the first provable bounds …
-
New Math Paper Explores Universal Approximation with Brownian Signatures
A new paper introduces $L^p$-universal approximation theorems for functionals on rough path spaces, demonstrating that linear functionals on signatures of time-extended rough paths can approximate any $p$-integrable sto…
-
New method improves SDE surrogate model accuracy for path-dependent observables
This paper introduces a novel variational loss function for learning surrogate models of stochastic differential equations (SDEs). The proposed goal-oriented learning approach uses an error bound for path-space observab…
-
Paper explores variational approach to SDEs in generative machine learning
A new paper introduces a variational perspective on using stochastic differential equations (SDEs) for generative machine learning. The work provides an informal introduction to SDEs and their application in generative …
-
Differential Equations Inspire New Deep Neural Network Architectures
A new paper explores the integration of differential equations with deep neural networks to enhance theoretical understanding, interpretability, and generalization capabilities in AI. The research reviews architectures …
-
New SSFM Framework Learns Strong Solution Maps for SDEs
Researchers have introduced Strong Stochastic Flow Maps (SSFMs), a new framework designed to learn the strong solution map of additive-noise stochastic differential equations (SDEs). This approach directly generalizes d…
-
New framework learns complex multiscale dynamics using normalizing flows
Researchers have developed a new data-driven framework to learn effective stochastic dynamics from limited observational data of complex multiscale systems. This approach models coupled stochastic differential equations…