5 citations · 8 across the 9 of their papers we have counts for
9 papers
Policy Gradient Optimal Correlation Search for Variance Reduction in Monte Carlo simulation and Maximum Optimal Transport
Pierre Bras, Gilles Pagès
We propose a new algorithm for variance reduction when estimating where is the solution to some stochastic differential equation and is a test function. The new es…
A note on -Convergence of the Empiric Minimizer for unbounded functions with fast growth
Pierre Bras
For coercive, we study the convergence rate for the -distance of the empiric minimizer, which is the true minimum of the function sampled…
Langevin algorithms for Markovian Neural Networks and Deep Stochastic control
Pierre Bras, Gilles Pagès
Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases…
Langevin algorithms for very deep Neural Networks with application to image classification
Pierre Bras
Training a very deep neural network is a challenging task, as the deeper a neural network is, the more non-linear it is. We compare the performances of various preconditioned Lange…
Convergence of Langevin-Simulated Annealing algorithms with multiplicative noise II: Total Variation
Pierre Bras, Gilles Pagès
We study the convergence of Langevin-Simulated Annealing type algorithms with multiplicative noise, i.e. for a potential function to minimize, we…
Total variation distance between two diffusions in small time with unbounded drift: application to the Euler-Maruyama scheme
Pierre Bras, Gilles Pagès, Fabien Panloup
We give bounds for the total variation distance between the solutions to two stochastic differential equations starting at the same point and with close coefficients, which applies…
Convergence of Langevin-Simulated Annealing algorithms with multiplicative noise
Pierre Bras, Gilles Pagès
We study the convergence of Langevin-Simulated Annealing type algorithms with multiplicative noise, i.e. for a potential function to minimize, we…
Simulation of Reflected Brownian motion on two dimensional wedges
Pierre Bras, Arturo Kohatsu-Higa
We study a correlated Brownian motion in two dimensions, which is reflected, stopped or killed in a wedge represented as the intersection of two half spaces. First, we provide expl…
Convergence rates of Gibbs measures with degenerate minimum
Pierre Bras
We study convergence rates for Gibbs measures, with density proportional to , as where admits a unique glob…