2016

Bolte, Jérôme and Pauwels, Edouard (2016) Majorization-minimization procedures and convergence of SQP methods for semi-algebraic and tame programs. Mathematics of Operations Research, vol. 41 (n° 2). pp. 442-465.

2019

Bolte, Jérôme and Pauwels, Edouard (2019) Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning. Mathematical Programming. pp. 1-33. (In Press)

Bolte, Jérôme, Castera, Camille, Pauwels, Edouard and Févotte, Cédric (2019) An Inertial Newton Algorithm for Deep Learning. TSE Working Paper, n. 19-1043, Toulouse

2020

Bolte, Jérôme, Chen, Zheng and Pauwels, Edouard (2020) The multiproximal linearization method for convex composite problems. Mathematical Programming, vol. 182. pp. 1-36.

Bolte, Jérôme, Pauwels, Edouard and Rios-Zertuche, Rodolfo (2020) Long term dynamics of the subgradient method for Lipschitz path differentiable functions. TSE Working Paper, n. 20-1110, Toulouse

Bolte, Jérôme and Pauwels, Edouard (2020) Curiosities and counterexamples in smooth convex optimization. TSE Working Paper, n. 20-1080, Toulouse

Bolte, Jérôme and Pauwels, Edouard (2020) A mathematical model for automatic differentiation in machine learning. In: Advances in Neural Information Processing Systems 33 (NeurIPS 2020) Larochelle, Hugo, Ranzato, M., Hadsell, R., Balcan, M.F. and Lin, H. (eds.) MIT Press. ISBN 9781713829546 (In Press)

2021

Bolte, Jérôme, Glaudin, Lilian, Pauwels, Edouard and Serrurier, Matthieu (2021) A Hölderian backtracking method for min-max and min-min problems. TSE Working Paper, n. 21-1243, Toulouse

Bolte, Jérôme, Le, Tam, Pauwels, Edouard and Silveti Falls, AntonioORCID: https://orcid.org/0000-0002-8165-6348 (2021) Nonsmooth implicit differentiation for machine learning and optimization. In: NIPS'21: 35th International Conference on Neural Information Processing Systems, 6-14 décembre 2021, En ligne.

Bolte, JérômeORCID: https://orcid.org/0000-0002-1676-8407, Bertoin, David, Gerchinovitz, Sébastien and Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X (2021) Numerical influence of ReLU’(0) on backpropagation. Advances in Neural Information Processing Systems, Vol. 34. pp. 468-479.

2022

Bolte, Jérôme, Combettes, Cyrille and Pauwels, Edouard (2022) The Iterates of the Frank-Wolfe Algorithm May Not Converge. TSE Working Paper, n. 22-1311, Toulouse

Bolte, Jérôme, Le, Tam and Pauwels, Edouard (2022) Subgradient sampling for nonsmooth nonconvex minimization. TSE Working Paper, n. 22-1310, Toulouse

Bolte, JérômeORCID: https://orcid.org/0000-0002-1676-8407, Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X and Vaiter, SamuelORCID: https://orcid.org/0000-0002-4077-708X (2022) Automatic differentiation of nonsmooth iterative algorithms. In: 35th conference on neural information processing systems (NeurIPS 2021) Oh, A., Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D. and Cho, K. (eds.) NeurIPS/Curran Associates. Series “Advances in neural information processing systems, vol.35”, Vol. vol.36. San Mateo pp. 77089-77103. ISBN 9781713871088

2023

Bolte, JérômeORCID: https://orcid.org/0000-0002-1676-8407, Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X and Vaiter, Samuel (2023) One-step differentiation of iterative algorithms. Advances in Neural Information Processing Systems 36. pp. 77089-77103.

Bolte, JérômeORCID: https://orcid.org/0000-0002-1676-8407, Glaudin, Lilian, Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X and Serrurier, Matthieu (2023) The backtrack Hölder gradient method with application to min-max and min-min problems. Open Journal of Mathematical Optimization, vol.4 (n°8).

2024

Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X (2024) On the nature of Bregman functions. Operations Research Letters, Vol.57 (n°107183).

Bolte, Jérôme, Combettes, Cyrille and Pauwels, Edouard (2024) The iterates of the Frank–Wolfe algorithm may not converge. Mathematics of Operations Research, Vol. 49 (N° 4). pp. 2049-2802.

Bolte, JérômeORCID: https://orcid.org/0000-0002-1676-8407, Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X and Silveti Falls, AntonioORCID: https://orcid.org/0000-0002-8165-6348 (2024) Differentiating nonsmooth solutions to parametric monotone inclusion problems. SIAM Journal on Optimization, Vol. 34 (N° 1). pp. 71-97.

Iutzeler, Franck, Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X and Vaiter, Samuel (2024) Derivatives of Stochastic Gradient Descent in parametric optimization. In: Advances in Neural Information Processing Systems 37 Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J. and Zhang, Chi (eds.) Neural Information Processing Systems Foundation, Inc. (NeurIPS). Series “Advances in Neural Information Processing Systems,volume 37” Vancouver pp. 118859-118882. ISBN 9798331314385

2025

Bolte, JérômeORCID: https://orcid.org/0000-0002-1676-8407, Le, Tam, Moulines, Éric and Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X (2025) Inexact subgradient methods for semialgebraic functions. Mathematical Programming. (In Press)

2026

Bolte, JérômeORCID: https://orcid.org/0000-0002-1676-8407, Pauwels, EdouardORCID: https://orcid.org/0000-0002-8180-075X, Le, Quoc Tung and Vaiter, Samuel (2026) Geometric and computational hardness of bilevel programming. Mathematical Programming, vol.215. pp. 539-574.