Publications

Pierre Bras (2023). Adaptive Gradient Langevin Algorithms for Stochastic Optimization and Bayesian Inference. PhD thesis.

PDF Cite Slides

Pierre Bras, Gilles Pagès (2023). Policy Gradient Optimal Correlation Search for Variance Reduction in Monte Carlo simulation and Maximum Optimal Transport. In arXiv e-prints.

PDF Cite arXiv GitHub

Pierre Bras, Gilles Pagès (2022). Langevin algorithms for Markovian Neural Networks and Deep Stochastic control. In International Joint Conference on Neural Networks IJCNN23.

PDF Cite IJCNN23 arXiv GitHub Slides Poster

Pierre Bras (2022). Langevin algorithms for very deep Neural Networks with applications to image classification. In International Neural Network Society Workshop on Deep Learning Innovations and Applications part of the conference IJCNN23.

PDF Cite Workshop arXiv GitHub Slides Poster

Pierre Bras (2022). A note on $L^1$-Convergence of the Empiric Minimizer for unbounded functions with fast growth. In arXiv e-prints.

Pierre Bras, Masaaki Fukasawa (2022). Weak error rates for numerical schemes of non-singular Stochastic Volterra equations with application to stochastic volatility models. To appear in SIAM Journal on Financial Mathematics (2025).

Pierre Bras, Gilles Pagès, Fabien Panloup (2021). Total variation distance between two diffusions in small time with unbounded drift: application to the Euler-Maruyama scheme. In Electron. J. Probab. 27, 1-19 (2022).

Cite DOI PDF arXiv Slides

Pierre Bras, Gilles Pagès (2021). Convergence of Langevin-Simulated Annealing algorithms with multiplicative noise II: Total Variation. In Monte Carlo Methods and Applications.

PDF Cite DOI arXiv

Pierre Bras, Gilles Pagès (2021). Convergence of Langevin-Simulated Annealing algorithms with multiplicative noise . To be published in Mathematics of Computation.

PDF Cite arXiv Slides Jupyter

Pierre Bras, Arturo Kohatsu-Higa (2021). Simulation of Reflected Brownian motion on two dimensional wedges. In Stoch. Proc. and App. 156, 349-378 (2023).

Cite DOI arXiv Slides Jupyter Notebook

Pierre Bras (2021). Convergence rates of Gibbs measures with degenerate minimum. In Bernoulli 2022, Vol. 28, No. 4, 2431-2458.

Cite DOI arXiv Slides Jupyter Notebook