Arnaud Guillin
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Neural Computing×1Analysis of PDEs×1Probability×1
Frequent co-authors
Research Timeline
2026
Quantifying Uncertainty In Wide Two-Layer Neural Networks: On The Law Of The Limiting Fluctuation Process
This paper develops a novel, computationally efficient method to quantify the uncertainty in wide neural network predictions by characterizing the limiting random fluctuations using stochastic evolution equations.
Highlighted terms show continued research focus across papers
Papers
cs.NEmath.APmath.PRRecentJun 4, 2026
Quantifying Uncertainty In Wide Two-Layer Neural Networks: On The Law Of The Limiting Fluctuation Process
Arnaud Descours, Arnaud Guillin, Geoffrey Lacour, Manon Michel +2 more
This paper develops a novel, computationally efficient method to quantify the uncertainty in wide neural network predictions by characterizing the limiting random fluctuations using stochastic evoluti…
View →