Fractional Brownian motion
PulseAugur coverage of Fractional Brownian motion — every cluster mentioning Fractional Brownian motion across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New algorithm for online expectile estimation from dependent data detailed on arXiv
A new paper published on arXiv details a one-pass, stochastic-gradient algorithm for estimating expectiles from dependent data. The research addresses the limited statistical theory for online expectile estimation, part…
-
New theory explains correlated initialization in deep residual networks
Researchers have developed a new theoretical framework for understanding the behavior of deep residual networks with correlated initializations across layers. Their work extends previous conjectures, demonstrating that …
-
New framework links generalized splines and Gaussian Processes
This paper introduces a generalized framework for understanding the relationship between minimum mean square error estimators and regularized least-squares fits in linear inverse problems. The research extends this equi…
-
New research details global universality via discrete-time signatures
A new arXiv paper introduces a method for achieving global universality in non-anticipative and path-dependent functionals using discrete-time signatures. The research establishes that linear functionals of these signat…
-
Gaussian Process Minima Analysis Unveiled in New Research
This paper investigates the high minima of Gaussian processes, focusing on overshoots and the locations of minimizers. It demonstrates that under certain conditions, the scaled overshoot converges to an exponential rand…
-
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 Fractional Stochastic Neural Networks Improve Long Memory Recovery and Robustness
Researchers have introduced Fractional Stochastic Neural Networks (FSNNs), a novel architecture that incorporates fractional Brownian motion to drive residual dynamics. This approach utilizes a discrete stochastic maxim…