Valentin De Bortoli

Publications

Note that this list can be also seen and filtered here.

. On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent . 2021 - Submitted (journal)

. On quantitative Laplace-type convergence results for some exponential probability measures, with two applications . 2021 - Submitted (journal)

. Simulating Diffusion Bridges with Score Matching . 2021 - Preprint

. Quantitative Uniform Stability of the Iterative Proportional Fitting Procedure . 2021 - Submitted (journal)

. Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling. 2021 - Accepted at NeuRIPS (conference).

. Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie. 2021 - Submitted (journal).

. Maximum entropy methods for texture synthesis: theory and practice. 2021 - Published in SIMODS (journal).

. Quantitative Propagation of Chaos for SGD in Wide Neural Networks. 2020 - Accepted at NeuRIPS (conference).

. Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian. Part I: Methodology and Experiments approach. 2020 - Published in SIIMS (journal).

. Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian. Part II: Theoretical Analysis approach. 2020 - Published in SIIMS (journal).

. Approximate Bayesian Computation with the Sliced-Wasserstein Distance. 2020 - Accepted at ICASSP (conference) (Best student paper award).

. Redundancy in Gaussian random fields. 2020 - Published in ESAIM: Probability and Statistics

. Continuous and Discrete-Time Analysis of Stochastic Gradient Descent for Convex and Non-Convex Functions. 2021 - Accepted at Conference on Learning Theory (conference).

. Patch redundancy in images: a statistical testing framework and some applications. 2019 - Published in SIAM Journal on Imaging Science (journal).

. Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation. 2019 - Accepted at Statistics and Computing (journal).

. Convergence of diffusion and their discretizations: from continuous to discrete processes and back. 2019 - Submitted (journal).

. Macrocanonical models for texture synthesis. 2019 - Accepted at Scale Space and Variational Methods in Computer Vision (conference).

. Review of wavelet-based unsupervised texture segmentation, advantage of adaptive wavelets. 2018 - Published in IET (journal).

Projects


Plug and Play methods

P&P methods for Bayesian imaging


Maximum entropy methods

Entropy methods for texture synthesis

Empirical Bayes methods

Bayesian framework for parameter estimation

Propagation of chaos

Propagation of chaos in neural networks

Convergence of SGD

A study of SGD in discrete and continuous time with optimal rates

A contrario methods and redundancy

A contrario methods with applications

ABC methods and sliced Wasserstein

ABC method with application to denoising

Texture classification

Texture classification with empirical wavelets

Teaching

Differential Calculus

ENS Paris Saclay L3 differential calculus

Hilbert Analysis

ENS Paris Saclay agrégation Hilbert analysis

Fourier Analysis

ENS Paris Saclay agrégation Fourier analysis

Optimization

ENS Paris Saclay M1 optimization

Generative Modeling

MVA course (M2) generative modeling

Contact