, Moreover, we write fl prox ?g (x) := prox ?g(s,·) (x ? 2??f ? (s, x)) and ?g ? := ?g ? (s, x ? 2??f ? (s, x)), for all x ? X. By assumption, the sequel and write u n := u n (t), v n := v n (s, t), w n := w n (s, t), h ? := h ? (s, ·), ?g := ?g(s, ·), ?f := ?f (s, ·), ? := ? n , prox ?f := prox ?f (s,·) , ?f ? := ?f ? (s, ·), z := z(t)

A. Alacaoglu, Q. Tran-dinh, O. Fercoq, and V. Cevher, Smooth primal-dual coordinate descent algorithms for nonsmooth convex optimization, NIPS, pp.5854-5863, 2017.

Y. F. Atchade, G. Fort, and E. Moulines, On stochastic proximal gradient algorithms, 2014.

Y. Atchadé, G. Fort, and E. Moulines, On perturbed proximal gradient algorithms, J. Mach. Learn. Res, vol.18, issue.1, pp.310-342, 2017.

H. Attouch, Familles d'opérateurs maximaux monotones et mesurabilité, Ann. Mat. Pura Appl, vol.120, issue.1, pp.35-111, 1979.

H. Attouch, J. Bolte, and B. Svaiter, Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized gauss-seidel methods, Math. Program, vol.137, issue.1-2, pp.91-129, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00790042

J. Aubin and A. Cellina, Differential inclusions, Grundlehren der Mathematischen Wissenschaften, vol.264
URL : https://hal.archives-ouvertes.fr/hal-01037957

. Springer-verlag, Set-valued maps and viability theory, 1984.

J. Aubin, H. Frankowska, and A. Lasota, Poincaré's recurrence theorem for set-valued dynamical systems, Ann. Polon. Math, vol.54, issue.1, pp.85-91, 1991.

U. Ayesta, M. Erausquin, M. Jonckheere, and I. M. Verloop, Scheduling in a random environment: stability and asymptotic optimality, IEEE/ACM Trans. Netw, vol.21, issue.1, pp.258-271, 2013.
URL : https://hal.archives-ouvertes.fr/hal-01121985

A. Barbero and S. Sra, Modular proximal optimization for multidimensional total-variation regularization, 2014.

H. H. Bauschke and J. M. Borwein, Legendre functions and the method of random bregman projections, J. Convex Anal, vol.4, issue.1, pp.27-67, 1997.

H. H. Bauschke, J. M. Borwein, and W. Li, Strong conical hull intersection property, bounded linear regularity, Jameson's property (G), and error bounds in convex optimization, Math. Program, vol.86, issue.1, pp.135-160, 1999.

H. H. Bauschke and P. L. Combettes, Convex analysis and monotone operator theory in Hilbert spaces, CMS Books in Mathematics/Ouvrages de Mathématiques de la SMC, 2011.
URL : https://hal.archives-ouvertes.fr/hal-01517477

W. Ben-ameur, P. Bianchi, and J. Jakubowicz, Robust distributed consensus using total variation, IEEE Trans. Automat. Contr, vol.61, issue.6, pp.1550-1564, 2016.
DOI : 10.1109/tac.2015.2471755

URL : https://hal.archives-ouvertes.fr/hal-01259850

M. Benaïm, Dynamics of stochastic approximation algorithms, Séminaire de Probabilités, XXXIII, vol.1709, pp.1-68, 1999.

M. Benaïm and M. W. Hirsch, Asymptotic pseudotrajectories and chain recurrent flows, with applications, J. Dynam. Differential Equations, vol.8, issue.1, pp.141-176, 1996.

M. Benaïm and M. W. Hirsch, Stochastic approximation algorithms with constant step size whose average is cooperative, Ann. Appl. Probab, vol.9, issue.1, pp.216-241, 1999.

M. Benaïm, J. Hofbauer, and S. Sorin, Stochastic approximations and differential inclusions, SIAM J. Control Optim, vol.44, issue.1, pp.328-348, 2005.

M. Benaïm, J. Hofbauer, and S. Sorin, Stochastic approximations and differential inclusions, II. Applications. Math. Oper. Res, vol.31, issue.4, pp.673-695, 2006.

M. Benaïm and S. J. Schreiber, Ergodic properties of weak asymptotic pseudotrajectories for semiflows, J. Dynam. Differential Equations, vol.12, issue.3, pp.579-598, 2000.

A. Benveniste, M. Métivier, and P. Priouret, Adaptive algorithms and stochastic approximations, Applications of Mathematics, vol.22, 1990.

D. P. Bertsekas, Incremental proximal methods for large scale convex optimization, Math. Program, vol.129, issue.2, pp.163-195, 2011.

P. Bianchi, Ergodic convergence of a stochastic proximal point algorithm, SIAM J. Optim, vol.26, issue.4, pp.2235-2260, 2016.

P. Bianchi, G. Fort, and W. Hachem, Performance of a distributed stochastic approximation algorithm, IEEE Trans. Inf. Theory, vol.59, issue.11, pp.7405-7418, 2013.

P. Bianchi and W. Hachem, Dynamical behavior of a stochastic Forward-Backward algorithm using random monotone operators, J. Optim. Theory Appl, vol.171, issue.1, pp.90-120, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01183959

P. Bianchi, W. Hachem, and A. Salim, Building stochastic optimization algorithms with random monotone operators, EUCCO, 2016.

P. Bianchi, W. Hachem, and A. Salim, Convergence d'un algorithme du gradient proximal stochastique à pas constant et généralisation aux opérateurs monotones aléatoires, GRETSI, 2017.

P. Bianchi, W. Hachem, and A. Salim, A constant step Forward-Backward algorithm involving random maximal monotone operators, J. Convex Anal, 2019.
URL : https://hal.archives-ouvertes.fr/hal-01725134

P. Bianchi, W. Hachem, and A. Salim, Constant step stochastic approximations involving differential inclusions: Stability, long-run convergence and applications, 2019.

P. Billingsley, Convergence of probability measures. Wiley Series in Probability and Statistics: Probability and Statistics, 1999.

J. Bolte, T. Nguyen, J. Peypouquet, and B. W. Suter, From error bounds to the complexity of first-order descent methods for convex functions, Mathematical Programming, vol.165, issue.2, pp.471-507, 2017.

V. S. Borkar, Stochastic approximation. A dynamical systems viewpoint, 2008.

J. M. Borwein and A. S. Lewis, Convex analysis and nonlinear optimization, CMS Books in Mathematics/Ouvrages de Mathématiques de la SMC, vol.3

L. Bottou, Large-scale machine learning with stochastic gradient descent, COMPSTAT'2010, pp.177-186, 2010.

L. Bottou, F. E. Curtis, and J. Nocedal, Optimization methods for large-scale machine learning, SIAM Review, vol.60, issue.2, pp.223-311, 2018.

S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, Distributed optimization and statistical learning via the alternating direction method of multipliers, Machine Learning, vol.3, pp.1-122, 2011.

H. Brézis, Opérateurs maximaux monotones et semi-groupes de contractions dans les espaces de Hilbert. North-Holland mathematics studies, 1973.

J. Brodie, I. Daubechies, C. De-mol, D. Giannone, and I. Loris, Sparse and stable markowitz portfolios, Proc. Natl. Acad. Sci. USA, vol.106, pp.12267-12272, 2009.

R. E. Bruck, Asymptotic convergence of nonlinear contraction semigroups in Hilbert space, J. Funct. Anal, vol.18, pp.15-26, 1975.

R. H. Byrd, P. Lu, J. Nocedal, and C. Y. Zhu, A limited memory algorithm for bound constrained optimization, SIAM J. Sci. Comput, vol.16, issue.5, pp.1190-1208, 1995.

C. Castaing and M. Valadier, Convex analysis and measurable multifunctions, Lecture Notes in Mathematics, vol.580, 1977.

A. Chambolle, V. Caselles, D. Cremers, M. Novaga, and T. Pock, An introduction to total variation for image analysis. Theoretical foundations and numerical methods for sparse recovery, vol.9, pp.263-340, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00437581

A. Chambolle and T. Pock, A first-order primal-dual algorithm for convex problems with applications to imaging, J. Math. Imaging Vision, vol.40, issue.1, pp.120-145, 2011.
URL : https://hal.archives-ouvertes.fr/hal-00490826

S. Chen, A. Sandryhaila, G. Lederman, Z. Wang, J. Moura et al., Signal inpainting on graphs via total variation minimization, ICASSP, pp.8267-8271, 2014.

G. Chierchia, A. Cherni, E. Chouzenoux, and J. Pesquet, Approche de Douglas-Rachford aléatoire par blocs appliquée à la régression logistique parcimonieuse, GRETSI, pp.1-4, 2017.

F. Chung, Spectral graph theory, vol.92, 1997.

P. L. Combettes, Iterative construction of the resolvent of a sum of maximal monotone operators, J. Convex Anal, vol.16, issue.4, pp.727-748, 2009.

P. L. Combettes and J. Pesquet, Stochastic quasi-Fejér block-coordinate fixed point iterations with random sweeping, SIAM J. Optim, vol.25, issue.2, pp.1221-1248, 2015.

P. L. Combettes and J. Pesquet, Stochastic approximations and perturbations in forwardbackward splitting for monotone operators, Pure Appl. Funct. Anal, vol.1, issue.1, pp.13-37, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01380000

P. L. Combettes and J. Pesquet, Stochastic forward-backward and primal-dual approximation algorithms with application to online image restoration, EUSIPCO, pp.1813-1817, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01422154

L. Condat, A direct algorithm for 1D total variation denoising, IEEE Signal Process. Lett, vol.20, issue.11, pp.1054-1057, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00675043

L. Condat, A primal-dual splitting method for convex optimization involving Lipschitzian, proximable and linear composite terms, J. Optim. Theory Appl, vol.158, issue.2, pp.460-479, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00609728

P. L. Davies and A. Kovac, Local extremes, runs, strings and multiresolution, Ann. Stat, pp.1-48, 2001.

J. De-vries, Elements of topological dynamics, Mathematics and its Applications, vol.257, 1993.

B. Delyon, Stochastic Approximation with Decreasing Gain: Convergence and Asymptotic Theory. Unpublished Lecture Notes, 2000.

A. Dieuleveut, A. Durmus, and F. Bach, Bridging the gap between constant step size stochastic gradient descent and markov chains, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01565514

J. Eckstein and D. P. Bertsekas, On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators, Math. Program, vol.55, issue.1, pp.293-318, 1992.

A. E. Alaoui, X. Cheng, A. Ramdas, M. Wainwright, and M. Jordan, Asymptotic behavior of ? p-based Laplacian regularization in semi-supervised learning, COLT, pp.879-906, 2016.

M. Faure and G. Roth, Stochastic approximations of set-valued dynamical systems: convergence with positive probability to an attractor, Math. Oper. Res, vol.35, issue.3, pp.624-640, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00383277

M. Faure and G. Roth, Ergodic properties of weak asymptotic pseudotrajectories for set-valued dynamical systems, Stoch. Dyn, vol.13, issue.1, p.23, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00555214

J. Fort and G. Pagès, Asymptotic behavior of a Markovian stochastic algorithm with constant step, SIAM J. Control Optim, vol.37, issue.5, pp.1456-1482, 1999.

N. Gast and B. Gaujal, Markov chains with discontinuous drifts have differential inclusion limits, Perform. Eval, vol.69, issue.12, pp.623-642, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00787999

R. Glowinski and A. Marroco, Sur l'approximation, par éléments finis d'ordre un, et la résolution, par pénalisation-dualité d'une classe de problèmes de dirichlet non linéaires. Revue française d'automatique, informatique, recherche opérationnelle. Analyse numérique, vol.9, pp.41-76, 1975.

D. Hallac, J. Leskovec, and S. Boyd, Network lasso: Clustering and optimization in large graphs, SIGKDD, pp.387-396, 2015.

R. Z. Ha'sminskii, The average principle for parabolic and elliptic differential equations and Markov processes with small diffusions, Theor. Probab. Appl, vol.8, pp.1-21, 1963.

F. Hiai and H. Umegaki, Integrals, conditional expectations, and martingales of multivalued functions, J. Multivar. Anal, vol.7, issue.1, pp.149-182, 1977.

J. Hiriart-urruty, About properties of the mean value functional and of the continuous infimal convolution in stochastic convex analysis, pp.763-789, 1976.

J. Hiriart-urruty, Thèse présentée à l'Université de Clermont-Ferrand II pour obtenir le grade de Docteur ès Sciences Mathématiques, 1977.

P. W. Holland, K. B. Laskey, and S. Leinhardt, Stochastic blockmodels: First steps, Soc. Networks, vol.5, issue.2, pp.109-137, 1983.

J. Hütter and P. Rigollet, Optimal rates for total variation denoising, COLT, pp.1115-1146, 2016.

S. Jegelka, F. Bach, and S. Sra, Reflection methods for user-friendly submodular optimization, NIPS, pp.1313-1321, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00905258

N. Johnson, A dynamic programming algorithm for the fused lasso and ? 0-segmentation, J. Comput. Graph. Stat, vol.22, issue.2, pp.246-260, 2013.

H. Karimi, J. Nutini, and M. Schmidt, Linear convergence of gradient and proximal-gradient methods under the Polyak-?ojasiewicz condition, ECML-PKDD, pp.795-811, 2016.

H. J. Kushner and G. G. Yin, Stochastic approximation and recursive algorithms and applications, Applications of Mathematics, vol.35, 2003.

L. Jure and A. K. Snap-datasets, , 2014.

L. Landrieu and G. Obozinski, Cut pursuit: Fast algorithms to learn piecewise constant functions, AISTATS, pp.1384-1393, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01306786

P. Laurent, Approximation et optimisation, Collection Enseignement des Sciences, issue.13, 1972.

Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE, vol.86, issue.11, pp.2278-2324, 1998.

P. Lions and B. Mercier, Splitting algorithms for the sum of two nonlinear operators, SIAM J. Numer. Anal, vol.16, issue.6, pp.964-979, 1979.

L. Ljung, Analysis of recursive stochastic algorithms, IEEE Trans. Automat. Contr, vol.22, issue.4, pp.551-575, 1977.

S. Majewski, B. Miasojedow, and E. Moulines, Analysis of nonsmooth stochastic approximation: the differential inclusion approach, 2018.

E. Mammen and S. Van-de-geer, Locally adaptive regression splines, Ann. Stat, vol.25, issue.1, pp.387-413, 1997.

B. Martinet, Brève communication. régularisation d'inéquations variationnelles par approximations successives. Revue française d'informatique et de recherche opérationnelle, Série rouge, vol.4, pp.154-158, 1970.

P. Mertikopoulos, H. Zenati, B. Lecouat, C. Foo, V. Chandrasekhar et al., Mirror descent in saddle-point problems: Going the extra (gradient) mile, 2018.
URL : https://hal.archives-ouvertes.fr/hal-01891551

W. Miller and E. Akin, Invariant measures for set-valued dynamical systems, Trans. Amer. Math. Soc, vol.351, issue.3, pp.1203-1225, 1999.

G. Minty, Monotone (nonlinear) operators in Hilbert space, Duke Mathematical Journal, vol.29, issue.3, pp.341-346, 1962.

I. Molchanov, Theory of random sets. Probability and its Applications, 2005.

J. Moreau, Fonctions convexes duales et points proximaux dans un espace Hilbertien, CR Acad. Sci. Paris Ser. A Math, vol.255, pp.2897-2899, 1965.
URL : https://hal.archives-ouvertes.fr/hal-01867195

E. Moulines and F. Bach, Non-asymptotic analysis of stochastic approximation algorithms for machine learning, NIPS, pp.451-459, 2011.
URL : https://hal.archives-ouvertes.fr/hal-00608041

R. Mourya, P. Bianchi, A. Salim, and C. Richard, An adaptive distributed asynchronous algorithm with application to target localization, CAMSAP 2017, pp.1-5, 2017.

I. Necoara, P. Richtarik, and A. Patrascu, Randomized projection methods for convex feasibility problems: conditioning and convergence rates, 2018.

J. Neveu, Bases mathématiques du calcul des probabilités, Masson et Cie, Éditeurs, 1964.

H. Ouyang, N. He, L. Tran, and A. Gray, Stochastic alternating direction method of multipliers, ICML, pp.80-88, 2013.

O. H. Padilla, J. Sharpnack, and J. Scott, The dfs fused lasso: Linear-time denoising over general graphs, J. Mach. Learn. Res, vol.18, issue.1, pp.6410-6445, 2017.

G. B. Passty, Ergodic convergence to a zero of the sum of monotone operators in Hilbert space, J. Math. Anal. Appl, vol.72, issue.2, pp.383-390, 1979.

A. Patrascu and I. Necoara, Nonasymptotic convergence of stochastic proximal point algorithms for constrained convex optimization, J. Mach. Learn. Res, 2017.

J. Peypouquet and S. Sorin, Evolution equations for maximal monotone operators: asymptotic analysis in continuous and discrete time, J. Convex Anal, vol.17, issue.3-4, pp.1113-1163, 2010.

R. R. Phelps, Lectures on maximal monotone operators, Extracta Math, vol.12, issue.3, pp.193-230, 1997.

S. Reddi, S. Sra, B. Poczos, and A. Smola, Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization, NIPS, pp.1145-1153, 2016.

H. Robbins and S. Monro, A stochastic approximation method, Ann. Math. Stat, vol.22, issue.3, pp.400-407, 1951.

H. Robbins and D. Siegmund, A convergence theorem for non negative almost supermartingales and some applications, Optimizing Methods in Statistics, pp.233-257, 1971.

R. T. Rockafellar, Convex analysis, Princeton Mathematical Series, issue.28, 1970.

R. T. Rockafellar, R. , and J. Wets, On the interchange of subdifferentiation and conditional expectations for convex functionals, Stochastics, vol.7, issue.3, pp.173-182, 1982.

R. T. Rockafellar, R. , and J. Wets, Variational analysis, volume 317 of Grundlehren der Mathematischen Wissenschaften

. Springer-verlag, , 1998.

L. Rosasco, S. Villa, and B. C. V?uv?u, Convergence of stochastic proximal gradient algorithm, 2014.

L. Rosasco, S. Villa, and B. C. V?uv?u, Stochastic inertial primal-dual algorithms, 2015.

L. Rosasco, S. Villa, and B. C. V?uv?u, A stochastic inertial forward-backward splitting algorithm for multivariate monotone inclusions, Optimization, vol.65, issue.6, pp.1293-1314, 2016.

G. Roth and W. Sandholm, Stochastic approximations with constant step size and differential inclusions, SIAM J. Control Optim, vol.51, issue.1, pp.525-555, 2013.

E. Ryu and S. Boyd, Stochastic proximal iteration: a non-asymptotic improvement upon stochastic gradient descent

A. Salim, P. Bianchi, and W. Hachem, Snake: a stochastic proximal gradient algorithm for regularized problems over large graphs, CAp, 2017.
URL : https://hal.archives-ouvertes.fr/hal-02287871

A. Salim, P. Bianchi, and W. Hachem, A stochastic Douglas-Rachford algorithm with constant step size, 2017.

A. Salim, P. Bianchi, and W. Hachem, A constant step stochastic douglas-rachford algorithm with application to non separable regularizations, ICASSP, pp.2886-2890, 2018.

A. Salim, P. Bianchi, and W. Hachem, A splitting algorithm for minimization under stochastic linear constraints, ISMP, 2018.

A. Salim, P. Bianchi, and W. Hachem, Snake: a stochastic proximal gradient algorithm for regularized problems over large graphs, IEEE Trans. Automat. Contr, 2019.
URL : https://hal.archives-ouvertes.fr/hal-02287871

A. Salim, P. Bianchi, W. Hachem, and J. Jakubowicz, A stochastic proximal point algorithm for total variation regularization over large scale graphs, CDC, pp.4490-4495, 2016.

S. Scardapane, D. Comminiello, A. Hussain, and A. Uncini, Group sparse regularization for deep neural networks, Neurocomputing, vol.241, pp.81-89, 2017.

Z. Shi and R. Liu, Online and stochastic Douglas-Rachford splitting method for large scale machine learning, 2013.

D. Spielman, Algorithms, graph theory, and linear equations in laplacian matrices, Proc. ICM, vol.4, pp.2698-2722, 2010.
DOI : 10.1142/9789814324359_0164

URL : http://www.cs.yale.edu/homes/spielman/PAPERS/icm10post.pdf

D. Spielman and S. Teng, Nearly linear time algorithms for preconditioning and solving symmetric, diagonally dominant linear systems, SIAM J. Matrix Anal. Appl, vol.35, issue.3, pp.835-885, 2014.
DOI : 10.1137/090771430

URL : http://cs-www.cs.yale.edu/homes/spielman/PAPERS/77143.pdf

W. Tansey and J. Scott, A fast and flexible algorithm for the graph-fused lasso, 2015.

R. J. Tibshirani, Adaptive piecewise polynomial estimation via trend filtering, Ann. Stat, vol.42, issue.1, pp.285-323, 2014.
DOI : 10.1214/13-aos1189

URL : https://doi.org/10.1214/13-aos1189

P. Toulis and E. Airoldi, Asymptotic and finite-sample properties of estimators based on stochastic gradients, Ann. Stat, vol.45, issue.4, pp.1694-1727, 2017.

P. Toulis, T. Horel, and E. Airoldi, Stable robbins-monro approximations through stochastic proximal updates, 2015.

N. Vishnoi, Laplacian solvers and their algorithmic applications, Theor. Comput. Sci, vol.8, issue.1-2, pp.1-141, 2012.

B. C. V?uv?u, A splitting algorithm for dual monotone inclusions involving cocoercive operators, Adv. Appl. Math, vol.38, issue.3, pp.667-681, 2013.

D. W. Walkup, R. , and J. Wets, Stochastic programs with recourse. II: On the continuity of the objective, SIAM J. Appl. Math, vol.17, pp.98-103, 1969.
DOI : 10.1137/0115113

M. Wang and D. P. Bertsekas, Incremental constraint projection methods for variational inequalities, Math. Program, vol.150, issue.2, pp.321-363, 2015.
DOI : 10.1007/s10107-014-0769-x

Y. Wang, J. Sharpnack, A. Smola, and R. Tibshirani, Trend filtering on graphs, J. Mach. Learn. Res, vol.17, issue.105, pp.1-41, 2016.

V. Yaji and S. Bhatnagar, Stochastic recursive inclusions with non-additive iterate-dependent markov noise, Stochastics, vol.90, issue.3, pp.330-363, 2018.
DOI : 10.1080/17442508.2017.1353984

URL : http://arxiv.org/pdf/1607.04735

J. Yoon and S. J. Hwang, Combined group and exclusive sparsity for deep neural networks, ICML, pp.3958-3966, 2017.

K. Yosida, Functional analysis, berlin, p.126, 1965.

H. Yu, M. Neely, and X. Wei, Online convex optimization with stochastic constraints, NIPS, pp.1427-1437, 2017.

L. Yuan, J. Liu, and J. Ye, Efficient methods for overlapping group lasso, NIPS, pp.352-360, 2011.

A. Yurtsever, B. C. V?uv?u, and V. Cevher, Stochastic three-composite convex minimization, NIPS, pp.4329-4337, 2016.

X. Zhu, Z. Ghahramani, and J. Lafferty, Semi-supervised learning using gaussian fields and harmonic functions, ICML, pp.912-919, 2003.