Research in statistics

Pierre C Bellec

Associate Professor, Department of Statistics, Rutgers University.

Education

2016: PhD, ENSAE ParisTech, France, advised by Alexandre Tsybakov.
2012: Part III (MASt), University of Cambridge, UK.
2011: Diplôme d’Ingénieur, Ecole Polytechnique, France.

Professional appointments

2021: Associate Professor (with tenure), Department of Statistics, Rutgers University
2016: Assistant Professor, Department of Statistics, Rutgers University

Recent preprints

Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression, Kai Tan and Pierre C. Bellec. Accepted, NeurIPS 2024.

Precise Asymptotics of Bagging Regularized M-estimators, Takuya Koriyama, Pratik Patil, Jin-Hong Du, Kai Tan and Pierre C. Bellec. arXiv:2409.15252.

Uncertainty quantification for iterative algorithms in linear models with application to early stopping. Pierre C Bellec and Kai Tan. arXiv:2404.17856, 2024.

Asymptotics of resampling without replacement in robust and logistic regression, Pierre C Bellec, Takuya Koriyama. arXiv:2404.02070, 2024.

Error estimation and adaptive tuning for unregularized robust M-estimator, Pierre C Bellec and Takuya Koriyama. arXiv:2312.13257, 2023.

Existence of solutions to the nonlinear equations characterizing the precise error of M-estimators, Pierre C Bellec and Takuya Koriyama. arXiv:2312.13254, 2023.

Observable adjustments in single-index models for regularized M-estimators. Pierre C Bellec. arXiv:2206.07256, 2022.

Chi-square and normal inference in high-dimensional multi-task regression. Pierre C Bellec and Gabriel Romon. arXiv:2107.07828, 2021.

Journal articles and peer-reviewed conference proceedings

Corrected generalized cross-validation for finite ensembles of penalized estimators, Pierre C Bellec, Jin-Hong Du, Takuya Koriyama, Pratik Patil and Kai Tan. Journal of the Royal Statistical Society Series B: Statistical Methodology, https://doi.org/10.1093/jrsssb/qkae092, arXiv:2310.01374.

Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions, Kai Tan and Pierre C. Bellec. NeurIPS 2023. Advances in Neural Information Processing Systems 36 (2024).

Noise Covariance Estimation in Multi-Task High-dimensional Linear Models. Kai Tan, Gabriel Romon and Pierre C Bellec. Bernoulli 30 (3) 1695 - 1722, August 2024. https://doi.org/10.3150/23-BEJ1644. arXiv:2206.07256

Derivatives and residual distribution of regularized M-estimators with application to adaptive tuning. Pierre C Bellec and Yiwei Shen. Proceedings of Thirty Fifth Conference on Learning Theory (COLT), PMLR 178:1912-1947, 2022.

Asymptotic normality of robust M-estimators with convex penalty. Pierre C Bellec, Yiwei Shen and Cun-Hui Zhang. Electron. J. Statist. 16 (2) 5591 - 5622, 2022.

Out-of-sample error estimate for robust M-estimators with convex penalty. Pierre C Bellec. Information and Inference: A Journal of the IMA, Volume 12, Issue 4, December 2023, Pages 2782–2817. doi.org/10.1093/imaiai/iaad031

De-biasing convex regularized estimators and interval estimation in linear models . Pierre C Bellec and Cun-Hui Zhang. Ann. Statist.51 (2) 391 - 436, April 2023. doi.org/10.1214/22-AOS2243

De-biasing the Lasso with degrees-of-freedom adjustment. Pierre C Bellec and Cun-Hui Zhang. Bernoulli 28 (2) 713 - 743, May 2022.

Second order Stein: SURE for SURE and other applications in high-dimensional inference. Pierre C Bellec and Cun-Hui Zhang. Ann. Statist., 49 (4) 1864 - 1903, August 2021.

Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model. Pierre C Bellec and Yiwei Shen. Advances in Neural Information Processing Systems (NeurIPS), 33:18625–18636, 2020.

The cost-free nature of optimally tuning Tikhonov regularizers and other ordered smoothers. Pierre C Bellec and Dana Yang. Proceedings of the 37th International Conference on Machine Learning (ICML), pages 1621–1630, 2020.

First order expansion of convex regularized estimators. Pierre Bellec and Arun Kuchibhotla. In Advances in Neural Information Processing Systems (NeurIPS), pages 3457–3468, 2019.

Optimal bounds for aggregation of affine estimators. Pierre C. Bellec. Ann. Statist., 46(1):30–59, 02 2018.

Sharp oracle inequalities for Least Squares estimators in shape restricted regression. Pierre C. Bellec. Ann. Statist., 46(2):745–780, 2018.

Slope meets Lasso: Improved oracle bounds and optimality. Pierre C. Bellec, Guillaume Lecué, and Alexandre B. Tsybakov. Ann. Statist., 46(6B):3603–3642, 2018.

On the prediction loss of the lasso in the partially labeled setting. Pierre C. Bellec, Arnak S. Dalalyan, Edwin Grappin, and Quentin Paris. Electron. J. Statist., 12(2):3443–3472, 2018.

Localized Gaussian width of M-convex hulls with applications to Lasso and convex aggregation. Pierre C Bellec. Bernoulli, 25 (4A) 3016 - 3040, November 2019.

Optimal exponential bounds for aggregation of density estimators. Pierre C. Bellec. Bernoulli, 23(1):219–248, 2017.

Bounds on the prediction error of penalized least squares estimators with convex penalty. Pierre C Bellec and Alexandre B Tsybakov. In Modern Problems of Stochastic Analysis and Statistics, Selected Contributions In Honor of Valentin Konakov. Springer, 2017.

Towards the study of least squares estimators with convex penalty. Pierre C Bellec, Guillaume Lecué, and Alexandre B Tsybakov. In Seminaire et Congres, number 39. Societe mathematique de France, 2017.

A sharp oracle inequality for Graph-Slope. Pierre C. Bellec, Joseph Salmon, and Samuel Vaiter. Electron. J. Statist., 11(2):4851–4870, 2017.

Adaptive confidence sets in shape restricted regression. Pierre C. Bellec. Bernoulli, 27 (1) 66 - 92, February 2021.

Sharp Oracle Bounds for Monotone and Convex Regression Through Aggregation. Pierre C. Bellec and Alexandre B. Tsybakov. Journal of Machine Learning Research, 16:1879–1892, 2015.

Aggregation of supports along the Lasso path. Pierre C. Bellec. Proceedings of Machine Learning Research, 49 pages 488–529, Conference On Learning Theory (COLT), Columbia University, New York, USA, 23–26 Jun 2016. PMLR.

Technical reports

The noise barrier and the large signal bias of the Lasso and other convex estimators. Pierre C Bellec. arXiv:1804.01230, 2018.

Optimistic lower bounds for convex regularized least-squares. Pierre C Bellec. arXiv:1703.01332, 2017.

Concentration of quadratic forms under a Bernstein moment assumption. Pierre C. Bellec. Technical report. Arxiv:1901.08726, 2014.

Awards and Honors

Students

  • Takuya Koriyama (2022-2024). 2024 ➔ Chicago Booth.
  • Yiwei Shen (PhD student, 2018-2022). 2022 ➔ Facebook/Meta.
  • Kai Tan (PhD student, 2021-present).
  • Gabriel Romon (MSc, Spring 2020). 2020 ➔ PhD at ENSAE, France.
  • Iris Chang (Undergrad, 2023 REU program)
  • Sumi Vora (Undergrad, 2023 REU program)
  • Luisa Quezada (Undergrad, Project SUPER 2023). Now PhD student at Rutgers.
  • Shivesh Mehrotra (Undergrad, 2022 REU program).

Program commitees/editorial boards

  • Associate Editor, the Annals of Statistics. 2021-2024
  • Program Committee, IMS Annual Meeting, London, 2022
  • Senior Program Committee, Conference on Learning Theory (COLT). 2021, 2022, 2023.
  • Area Chair, Conference on Neural Information Processing Systems (NeurIPS). 2021, 2022.
  • Reviewer for Algorithmic Learning Theory (ALT) 2021.
  • Reviewer for Conference on Learning Theory (COLT) 2016-present.
  • Reviewer for Conference on Neural Information Processing Systems (NeurIPS) 2016-present.
  • Reviewer for Journal of the Royal Statistical Society, Statistical Methodology, Series B. 2018
  • Reviewer for the Annals of Statistics. 2015-present.
  • Reviewer for Bernoulli Journal. 2014-present
  • Reviewer for the Journal of Multivariate Analysis. 2018
  • Reviewer for ESAIM (European Series in Applied and Industrial Mathematics) Probability and Statistics. 2018
  • Reviewer for IEEE Transactions on Information Theory. 2017-present
  • Reviewer for Electronic Journal of Statistics. 2016-present
  • Reviewer for Scandinavian Journal of Statistics. 2016.

Past and upcoming talks

  • Meeting in Mathematics Statistics, CIRM Luminy, France, December
  • Invited session at the 2023 IMS International Conference on Statistics and Data Science (ICSDS), December 2023, Lisbon, Portugal
  • Departmental Statistics Colloquium at Michigan State University, Michigan, October 2022
  • 2nd Joint Congress of Mathematics (AMS-EMS-SMF), Grenoble, France, July 2022.
  • 35th Annual Conference on Learning Theory (COLT 2022), London, UK, July 2022.
  • Structural Breaks and Shape Constraints workshop, ICMS, Edinburgh, 16-20 May 2022.
  • University of Massachusetts Amherst, Statistics and Data Science Seminar series, November 2021.
  • Columbia University, Statistics Seminar, October 2021.
  • Annals of Statistics Editors’ invited session at JSM (Joint Statistical Meeting), Seattle, August 2021.
  • International Conference on Statistics and Related Fields (ICON STARF), University of Luxembourg, July 2021.
  • International Conference on Machine Learning (ICML) 2020 (Virtual)
  • Mathematical Methods of Modern Statistics 2, CIRM Luminy, France, June 15-19, 2020. (Conference happening virtually due to COVID-19).
  • Otto-von-Guericke-Universität Magdeburg. Fakultät für Mathematik, Germany, January 9, 2020.
  • Meeting in Mathematics Statistics, CIRM Luminy, France, December 16,
  • CMStatistics conference, London, UK, December 14, 2019.
  • Indiana University, Bloomington, November 18, 2019.
  • University of South California, Probability Seminar, Los Angeles, November 2, 2019.
  • Statistics Seminar, Columbia University, New York, April 15, 2019.
  • Department of Statistics Seminar, University of Michigan, Ann Arbor, October 2018.
  • Workshop on Higher-Order Asymptotics and Post-Selection Inference (WHOA-PSI), Washington University in St-Louis, September 2018.
  • Joint Statistical Meeting (JSM), Vancouver, August 2018.
  • Conference on Statistical Learning and Data Science (SLDS), Columbia University, June 2018.
  • Oberwolfach, “Statistical Inference for Structured High-dimensional Models”, March 2018.
  • ‘Structural Inference in Statistics’ spring school, March 8, 2017. Lubbenau, Spreewald, Germany.
  • Meeting in Mathematical Statistics (MMS), Luminy, Dec 2017.
  • Baruch College, CUNY, November 2017.
  • ICSA, June 2017, Chicago.
  • UConn, April 2017. The 31st New England Statistics Symposium.
  • NJIT, Department of Mathematical Sciences, April 2017.
  • NYU Stern, March 2017.
  • MIT, Feb 2017. MIT Stochastics and Statistics seminar series.
  • Meeting in Mathematical Statistics (MMS), Dec 2016.
  • George Mason University, Nov 18, 2016.
  • Conference On Learning Theory (COLT), June 2016. Columbia University,
  • Columbia University, Feb 3, 2016. Statistics student seminar.
  • Rutgers University, Feb 2, 2016. Statistics seminar.
  • Yale University, Jan 29, 2016. YPNG seminar.
  • Stanford University, Jan 26, 2016. Statistics seminar.
  • Orsay, Laboratoire de Mathematiques, Jan 21, 2016.
  • Institut Mathematiques de Toulouse, Jan 12, 2016.
  • Meeting in Mathematical Statistics (MMS), Dec 2015.
  • Heidelberg University, July 2014. Workshop “Nonparametric and high-dimensional statistics”.
  • Meeting in Mathematical Statistics (MMS), Dec 2014. CIRM, Luminy.
  • Yale University, April 2014. YPNG seminar.

Contact

    (Work)
Department of Statistics
Rutgers University
501 Hill Center, Busch Campus
110 Frelinghuysen Road
Piscataway, NJ 08854