Publications

 Articles publiés

[1] Alquier, P. and  Kengne, W. : Minimax optimality of deep neural networks on dependent data via PAC-Bayes bounds.

        Electronic Journal of Statistics 19, (2025),  5895-5924, https://doi.org/10.1214/25-EJS2475 .   

[2] Kengne, W. and  Wade, M. : Deep learning from strongly mixing observations: Sparse-penalized regularization and minimax optimality.

       Journal of Complexity (2025), https://doi.org/10.1016/j.jco.2025.101978 .   

[3] Diop, M. L. and  Kengne, W.  : Statistical learning for ψ-weakly dependent processes. 

        Statistical Inference for Stochastic Processes (2025),  https://doi.org/10.1007/s11203-025-09329-6 .

[4] Kengne, W. and  Wade, M. :  Robust deep learning from weakly dependent data.

         Neural Networks (2025),  https://doi.org/10.1016/j.neunet.2025.107227 .      

[5] Kengne, W.  : Excess Risk Bound for Deep Learning Under Weak Dependence.

         Mathematical Methods in the Applied Sciences (2025),  https://doi.org/10.1002/mma.10719 .

[6] Kengne, W. and  Wade, M. :  Sparse-penalized deep neural networks estimator under weak dependence.

         Metrika (2024),  https://doi.org/10.1007/s00184-024-00965-1 .

[7] Kengne, W. and  Wade, M. : Deep learning for ψ-weakly dependent processes. 

        Journal of Statistical Planning and Inference (2024), https://doi.org/10.1016/j.jspi.2024.106163. 

[8] Bardet, J.-M. , Kamila, K. and  Kengne, W. :  Efficient and Consistent Data-Driven Model Selection for Time Series. 

        Bernoulli 29, (2023),  2652-2690.

[9] Diop, M. L. and  Kengne, W.  : Density Power Divergence Estimator for General Integer-Valued Time Series with Exogenous Covariates.

        Communications in Mathematics and Statistics (2023), https://doi.org/10.1007/s40304-023-00351-9.

[10] Diop, M. L. and  Kengne, W.  : Epidemic change-point detection in general integer-valued time series. 

        Journal of Applied Statistics (2023),   https://doi.org/10.1080/02664763.2023.2179567.

[11] Kengne, W.  : On consistency for time series model selection. 

        Statistical Inference for Stochastic Processes (2022), https://doi.org/10.1007/s11203-022-09284-6. 

[12] Diop, M. L. and  Kengne, W.  : A general procedure for change-point detection in multivariate time series.  

        TEST, (2022), https://doi.org/10.1007/s11749-022-00824-z.

[13] Diop, M. L. and Kengne, W.  : Inference and model selection in general causal time series with exogenous covariates. 

        Electronic Journal of Statistics 16, (2022), 116-157.

[14] Kengne, W. and Ngongo I. S. : Inference for nonstationary time series of counts with application to change-point problems. 

        Annals of the Institute of Statistical Mathematics, (2022), https://doi.org/10.1007/s10463-021-00815-1.

[15] Diop, M. L. and  Kengne, W.  : Consistent model selection procedure for general integer-valued time series .  

        Statistics, (2022), https://doi.org/10.1080/02331888.2022.2029861.

[16] Diop, M. L. and  Kengne, W. : Epidemic change-point detection in general causal time series.  

        Statistics & Probability Letters, (2022), https://doi.org/10.1016/j.spl.2022.109416.

[17] Diop, M. L. and Kengne, W.  : Poisson QMLE for change-point detection in general integer-valued time series models.

        Metrika 85, (2022), 373–403.

[18] Diop, M. L. and Kengne, W.  : Piecewise autoregression for general integer-valued time series.

        Journal of Statistical Planning and Inference 211, (2021), 271-286.

[19] Kengne, W. : Strongly consistent model selection for general causal time series.

        Statistics & Probability Letters 171, (2021), https://doi.org/10.1016/j.spl.2020.109000.

[20] Bardet, J.-M. , Kamila, K. and  Kengne, W.  : Consistent model selection criteria and goodness-of-fit test for common time series models.  

        Electronic Journal of Statistics 14, (2020), 2009-2052.

[21] Diop, M. L. and Kengne, W.  : Testing parameter change in general integer-valued time series.

        Journal of Time Series Analysis 38, (2017), 880-894.

[22] Kengne, W.  : Sequential change-point detection in Poisson autoregressive models.

         Journal de la société française de statistique 156, (2015), 98-112.

[23] Doukhan, P. and  Kengne, W.  : Inference and testing for structural change in general Poisson autoregressive models.

         Electronic Journal of Statistics 9, (2015), 1267-1314.

[24] Bardet, J.-M. and  Kengne, W.  : Monitoring procedure for parameter change in causal time series.

         Journal of Multivariate Analysis 125, (2014), 204–221.

[25] Bardet, J.-M. ,  Kengne, W.  and Wintenberger, O. : Detecting multiple change-points in general causal time  series using penalized quasi-likelihood.  

        Electronic Journal of Statistics 6, (2012), 435-477.

[26]  Kengne, W. :  Testing for parameter constancy in general causal time series models.

        Journal of Time Series Analysis 33, (2012), 503-518.

[27]  Kengne, W. :  A test for parameter change in general causal time series using quasi-likelihood estimator. 

        C. R. Acad. Sci. Paris, Ser. I 350 (2012), 307–312.

 Prépublications

[1] Kengne, W. and  Wade, M. :  Penalized deep neural networks estimator with general loss functions under weak dependence (submitted).

[2] Kengne, W. and  Wade, M. : A general framework for deep learning (submitted).