Submitted

• Attention layers provably solve single-location regression
  P. Marion, R. Berthier, G. Biau, C. Boyer. [pdf] [hal] [arXiv]


• Physics-Informed Kernel Learning
  N. Doumèche, F. Bach, G. Biau, C. Boyer. [pdf] [hal] [arXiv]


• A primer on classification with missing data
  A. Reyero-Lobo, A. Ayme, C. Boyer, E. Scornet. [hal]


• An analysis of the noise schedule in score-based generative models
  S. Strasman, A. Ocello, C. Boyer, S. Le Corff, V. Lemaire. [hal]

2024

• On the convergence of PINNs
  N. Doumèche, G. Biau, C. Boyer.
  Bernoulli [hal] [arXiv]


• Model-based Clustering with Missing Not At Random Data
  A. Sportisse, C. Biernacki, C. Boyer, J. Josse, M. Marbac Lourdelle, G. Celeux, F. Laporte.
  Statistics and Computing, Springer [hal] [arXiv] + [Accompanying note]


• Physics-informed machine learning as a kernel method
  N. Doumèche, F. Bach, G. Biau, C. Boyer.
  Conference on Learning Theory (COLT 2024) [hal]


• Random features models: a way to study the success of naive imputation
  A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet.
  International Conference on Machine Learning (ICML 2024). [hal] [arXiv]

2023

• Naive imputation implicitly regularizes high-dimensional linear models
  A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet.
  International Conference on Machine Learning (ICML 2023). [hal]


• Sparse tree-based initialization for neural networks
  P. Lutz, L. Arnould, C. Boyer, E. Scornet.
  Eleventh International Conference on Learning Representations (ICLR 2023) [hal] [arXiv]


• Is interpolation benign for random forest regression?
  L. Arnould, C. Boyer, E. Scornet.
  26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023) [hal]

2022

• On the asymptotic rate of convergence of Stochastic Newton algorithms and their Weighted Averaged versions
  C. Boyer, A. Godichon-Baggioni.
  Computational optimization and applications (2022) [journal] [hal] [arXiv]


• Proximal boosting: aggregating weak learners to minimize non-differentiable losses.
  E. Fouillen, C. Boyer, M. Sangnier.
  Neurocomputing (2022) [hal] [journal]


• Near-optimal rate of consistency for linear models with missing values
  A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet.
  International Conference on Machine Learning (ICML 2022). [hal] [arXiv]


• Robust Lasso-Zero for sparse corruption and model selection with missing covariates
  P. Descloux, C. Boyer, J. Josse, A. Sportisse, S. Sardy.
  Scandinavian Journal of Statistics (2022). [hal] [arXiv]


• Sampling rates for l1-synthesis
  M. März, C. Boyer, J. Kahn, P. Weiss
  Foundations of Computational Mathematics (FoCM) (2022). [arXiv]

2021

• Analyzing the tree-layer structure of Deep Forests
  L. Arnould, C. Boyer, E. Scornet.
  International Conference on Machine Learning (ICML 2021). [arXiv]

2020

• Debiasing Stochastic Gradient Descent to handle missing values
  A. Sportisse, C. Boyer, A. Dieuleveut, J. Josse
  Conference on Neural Information Processing Systems (NeurIPS 2020). [hal] [arXiv]


• Estimation and imputation in Probabilistic Principal Component Analysis with Missing Not At Random data.
  A. Sportisse, C. Boyer, J. Josse
  Conference on Neural Information Processing Systems (NeurIPS 2020). [arXiv]


• Imputation and low-rank estimation with Missing Non At Random data.
  A. Sportisse, C. Boyer, J. Josse
  Statistics & Computing, Springer. [hal] [arXiv]


• Missing Data Imputation using Optimal Transport
  B. Muzellec, J. Josse, C. Boyer, M. Cuturi
  International Conference on Machine Learning (ICML 2020). [arXiv]


• On oracle-type local recovery guarantees in compressed sensing.
  B. Adcock, C. Boyer, S. Brugiapaglia
  Information & Inference (2020). [journal] [hal] [arXiv]

2019

• On representer theorems and convex regularization.
  C. Boyer, A. Chambolle, Y. De Castro, V. Duval, F. de Gournay, P. Weiss
  SIAM Journal on Optimization (2019) [pdf] [hal] [arXiv]

2018

• Convex Regularization and Representer Theorems.
  C. Boyer, A. Chambolle, Y. De Castro, V. Duval, F. de Gournay, P. Weiss
  iTWIST'2018 [pdf] [arXiv]
  

2017

• Compressed sensing with structured sparsity and structured acquisition.
  C. Boyer, J. Bigot, P. Weiss
  Applied and Computational Harmonic Analysis (2017). [pdf] [hal] [arXiv] [journal]

• Adapting to unknown noise level in sparse deconvolution.
  C. Boyer, Y. De Castro, J. Salmon
  Information and Inference (2017). [pdf] [arXiv] [journal]
  Code: example [notebook] , source code [.zip]

2016

• On the generation of sampling schemes for Magnetic Resonance Imaging.
  C. Boyer, N. Chauffert, P. Ciuciu, J. Kahn, P. Weiss
  SIAM Journal on Imaging Sciences, Volume 9, Issue 4, pp. 1525-2098 (2016). [pdf]

• An analysis of block sampling strategies in compressed sensing.
  J. Bigot, C. Boyer, P. Weiss
  IEEE Transactions on Information Theory, vol. 62, no. 4, pp. 2125-2139 (2016). [pdf] [arXiv]

2015

• Sur la génération de schémas d'échantillonnage compressé en IRM
  P. Weiss, N. Chauffert, C. Boyer, P. Ciuciu
  GRETSI (2015). [pdf]


• Échantillonnage compressé avec acquisition structurée et parcimonie structurée
  C. Boyer, J. Bigot, P. Weiss
  GRETSI 2015. [pdf]

2014

• An algorithm for variable density sampling with block-constrained acquisition
  C. Boyer, P. Weiss and J. Bigot
  SIAM Imaging Science 2014 (Vol. 7, Issue 2). [pdf] , [arXiv]

2013

• Sampling by blocks of measurements in compressed sensing.
  J. Bigot, C. Boyer, P. Weiss
  Proc. SampTA (2013). [pdf].

2012

• HYR2PICS: Hybrid Regularized Reconstruction for Combined Parallel Imaging and Compressive Sensing in MRI.
  C. Boyer, P. Ciuciu, P. Weiss and S. Mériaux
  Proc. ISBI 2012. [pdf].