Bibliography

Publications of the year

Doctoral Dissertations and Habilitation Theses

• 1J.-B. Alayrac.
  
  Structured Learning from Videos and Language, Ecole normale supérieure - ENS PARIS, September 2018.
  
  https://hal.inria.fr/tel-01885412
• 2A. Beaugnon.
  
  Expert-in-the-Loop Supervised Learning for Computer Security Detection Systems, PSL Research University, June 2018.
  
  https://hal.archives-ouvertes.fr/tel-01888971
• 3R. Leblond.
  
  Asynchronous Optimization for Machine Learning, Ecole Normale Superieure de Paris - ENS Paris, November 2018.
  
  https://hal.inria.fr/tel-01950576
• 4A. Recanati.
  
  Relaxations of the Seriation problem and applications to de novo genome assembly, PSL Research University, November 2018.
  
  https://hal.archives-ouvertes.fr/tel-01984368
• 5D. Scieur.
  
  Acceleration in Optimization, PSL Research University, September 2018.
  
  https://hal.archives-ouvertes.fr/tel-01887163

Articles in International Peer-Reviewed Journals

• 6D. Babichev, F. Bach.
  
  Slice inverse regression with score functions, in: Electronic journal of statistics , May 2018, vol. Volume 12, Number 1 (2018), pp. 1507-1543. [ DOI : 10.1214/18-EJS1428 ]
  
  https://hal.inria.fr/hal-01388498
• 7F. Bach.
  
  Submodular Functions: from Discrete to Continous Domains, in: Mathematical Programming, Series A, 2018, https://arxiv.org/abs/1511.00394.
  
  https://hal.archives-ouvertes.fr/hal-01222319
• 8A. D'Aspremont, C. Guzman, M. Jaggi.
  
  Optimal Affine-Invariant Smooth Minimization Algorithms, in: SIAM Journal on Optimization, July 2018, vol. 28, n^o 3, pp. 2384 - 2405. [ DOI : 10.1137/17M1116842 ]
  
  https://hal.archives-ouvertes.fr/hal-01927392
• 9D. Garreau, S. Arlot.
  
  Consistent change-point detection with kernels, in: Electronic journal of statistics , December 2018, vol. 12, n^o 2, pp. 4440-4486, https://arxiv.org/abs/1612.04740.
  
  https://hal.archives-ouvertes.fr/hal-01416704
• 10R. Leblond, F. Pedregosa, S. Lacoste-Julien.
  
  Improved asynchronous parallel optimization analysis for stochastic incremental methods, in: Journal of Machine Learning Research (JMLR), 2018.
  
  https://hal.inria.fr/hal-01950558
• 11T. Lelievre, L. Pillaud-Vivien, J. Reygner.
  
  Central Limit Theorem for stationary Fleming–Viot particle systems in finite spaces, in: ALEA : Latin American Journal of Probability and Mathematical Statistics, September 2018, vol. 15, pp. 1163-1182, https://arxiv.org/abs/1806.04490. [ DOI : 10.30757/ALEA.v15-43 ]
  
  https://hal-enpc.archives-ouvertes.fr/hal-01812120
• 12J. Lin, A. Rudi, L. Rosasco, V. Cevher.
  
  Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces, in: Applied and Computational Harmonic Analysis, October 2018.
  
  https://hal.inria.fr/hal-01958890
• 13T. Schatz, F. Bach, E. Dupoux.
  
  Evaluating automatic speech recognition systems as quantitative models of cross-lingual phonetic category perception, in: Journal of the Acoustical Society of America, May 2018, vol. 143, n^o 5, pp. EL372 - EL378. [ DOI : 10.1121/1.5037615 ]
  
  https://hal.archives-ouvertes.fr/hal-01888735

International Conferences with Proceedings

• 14D. Babichev, F. Bach.
  
  Constant Step Size Stochastic Gradient Descent for Probabilistic Modeling, in: UAI 2018 - Conference on Uncertainty in Artificial Intelligence, Monterey, United States, August 2018, https://arxiv.org/abs/1804.05567.
  
  https://hal.inria.fr/hal-01929810
• 15L. Carratino, A. Rudi, L. Rosasco.
  
  Learning with SGD and Random Features, in: Advances in Neural Information Processing Systems, Montreal, Canada, December 2018, pp. 10213–10224, https://arxiv.org/abs/1807.06343 - Spotlight.
  
  https://hal.archives-ouvertes.fr/hal-01958906
• 16R. Leblond, J.-B. Alayrac, A. Osokin, S. Lacoste-Julien.
  
  SeaRNN: Training RNNs with Global-Local Losses, in: ICLR 2018 : 6th International Conference on Learning Representations, Vancouver, Canada, April 2018.
  
  https://hal.inria.fr/hal-01950555
• 17G. Luise, A. Rudi, M. Pontil, C. Ciliberto.
  
  Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance, in: NIPS 2018 - Advances in Neural Information Processing Systems, Montreal, Canada, December 2018, pp. 5864-5874, https://arxiv.org/abs/1805.11897 - 26 pages, 4 figures.
  
  https://hal.inria.fr/hal-01958887
• 18A. Rudi, D. Calandriello, L. Carratino, L. Rosasco.
  
  On Fast Leverage Score Sampling and Optimal Learning, in: NeurIPS 2018 - Thirty-second Conference on Neural Information Processing Systems, Montreal, Canada, Advances in Neural Information Processing Systems - NIPS-2018, December 2018, vol. 31, pp. 5677–5687, https://arxiv.org/abs/1810.13258.
  
  https://hal.inria.fr/hal-01958879
• 19A. Rudi, C. Ciliberto, G. M. Marconi, L. Rosasco.
  
  Manifold Structured Prediction, in: NIPS 2018 - Neural Information Processing Systems Conference, Montreal, Canada, Advances in Neural Information Processing Systems, December 2018, vol. 31, pp. 5615-5626, https://arxiv.org/abs/1806.09908.
  
  https://hal.archives-ouvertes.fr/hal-01958900
• 20T. Shpakova, F. Bach, A. Osokin.
  
  Marginal Weighted Maximum Log-likelihood for Efficient Learning of Perturb-and-Map models, in: UAI 2018 - Conference on Uncertainty in Artificial Intelligence 2018, Monterey, United States, August 2018, https://arxiv.org/abs/1811.08725.
  
  https://hal.inria.fr/hal-01939549
• 21A. B. Taylor, B. Van Scoy, L. Lessard.
  
  Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees, in: Proceedings of the 35th International Conference on Machine Learning. PMLR 80:4897-4906, Stockholm, Sweden, July 2018, https://arxiv.org/abs/1803.06073.
  
  https://hal.inria.fr/hal-01902068

Conferences without Proceedings

• 22F. Bach.
  
  Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization, in: Advances in Neural Information Processing Systems, Montreal, Canada, December 2018, https://arxiv.org/abs/1707.09157.
  
  https://hal.archives-ouvertes.fr/hal-01569934
• 23A. Beaugnon, P. Chifflier, F. Bach.
  
  End-to-End Active Learning for Computer Security Experts, in: KDD Workshop on Interactive Data Exploration and Analytics (IDEA), Londres, United Kingdom, August 2018.
  
  https://hal.archives-ouvertes.fr/hal-01888983
• 24A. Beaugnon, P. Chifflier, F. Bach.
  
  End-to-End Active Learning for Computer Security Experts, in: AAAI Workshop on Artificial Intelligence for Cyber Security (AICS), New Orleans, United States, February 2018.
  
  https://hal.archives-ouvertes.fr/hal-01888976
• 25L. Chizat, F. Bach.
  
  On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport, in: Advances in Neural Information Processing Systems (NIPS), Montréal, Canada, December 2018, https://arxiv.org/abs/1805.09545.
  
  https://hal.archives-ouvertes.fr/hal-01798792
• 26A. Défossez, N. Zeghidour, N. Usunier, L. Bottou, F. Bach.
  
  SING: Symbol-to-Instrument Neural Generator, in: Conference on Neural Information Processing Systems (NIPS), Montréal, Canada, December 2018, https://arxiv.org/abs/1810.09785.
  
  https://hal.archives-ouvertes.fr/hal-01899949
• 27R. M. Gower, N. Le Roux, F. Bach.
  
  Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods, in: International Conference on Artificial Intelligence and Statistics (AISTATS), Canary Islands, Spain, 2018, https://arxiv.org/abs/1710.07462 - 17 pages, 2 figures, 1 table. [ DOI : 10.07462 ]
  
  https://hal.archives-ouvertes.fr/hal-01652152
• 28M. E. Halabi, F. Bach, V. Cevher.
  
  Combinatorial Penalties: Which structures are preserved by convex relaxations?, in: AISTATS 2018 - 22nd International Conference on Artificial Intelligence and Statistics, Canary Islands, Spain, April 2018, https://arxiv.org/abs/1710.06273. [ DOI : 10.06273 ]
  
  https://hal.archives-ouvertes.fr/hal-01652151
• 29T. Kerdreux, F. Pedregosa, A. D'Aspremont.
  
  Frank-Wolfe with Subsampling Oracle, in: ICML 2018 - 35th International Conference on Machine Learning, Stockholm, Sweden, July 2018, https://arxiv.org/abs/1803.07348.
  
  https://hal.archives-ouvertes.fr/hal-01927391
• 30A. Kundu, F. Bach, C. Bhattacharyya.
  
  Convex optimization over intersection of simple sets: improved convergence rate guarantees via an exact penalty approach, in: AISTATS 2018 - 22nd International Conference on Artificial Intelligence and Statistics, Canary Islands, Spain, April 2018, https://arxiv.org/abs/1710.06465. [ DOI : 10.06465 ]
  
  https://hal.archives-ouvertes.fr/hal-01652149
• 31E. Pauwels, F. Bach, J.-P. Vert.
  
  Relating Leverage Scores and Density using Regularized Christoffel Functions, in: Neural Information Processing Systems, Montréal, Canada, December 2018.
  
  https://hal.archives-ouvertes.fr/hal-01796591
• 32L. Pillaud-Vivien, A. Rudi, F. Bach.
  
  Exponential convergence of testing error for stochastic gradient methods, in: Conference on Learning Theory (COLT), Stockholm, Sweden, July 2018, https://arxiv.org/abs/1712.04755.
  
  https://hal.archives-ouvertes.fr/hal-01662278
• 33L. Pillaud-Vivien, A. Rudi, F. Bach.
  
  Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes, in: Neural Information Processing Systems (NeurIPS), Montréal, Canada, December 2018, https://arxiv.org/abs/1805.10074.
  
  https://hal.archives-ouvertes.fr/hal-01799116
• 34S. J. Reddi, M. Zaheer, S. Sra, B. Poczos, F. Bach, R. Salakhutdinov, A. J. Smola.
  
  A Generic Approach for Escaping Saddle points, in: AISTATS 2018 - 22nd International Conference on Artificial Intelligence and Statistics, Canary Islands, Spain, April 2018, https://arxiv.org/abs/1709.01434.
  
  https://hal.archives-ouvertes.fr/hal-01652150
• 35K. Scaman, F. Bach, S. Bubeck, Y. T. Lee, L. Massoulié.
  
  Optimal Algorithms for Non-Smooth Distributed Optimization in Networks, in: Advances In Neural Information Processing systems, Montreal, Canada, December 2018, https://arxiv.org/abs/1806.00291 - 17 pages.
  
  https://hal.archives-ouvertes.fr/hal-01957013
• 36D. Scieur, E. Oyallon, A. D'Aspremont, F. Bach.
  
  Nonlinear Acceleration of CNNs, in: ICLR Workshop track, Vancouver, Canada, April 2018.
  
  https://hal.archives-ouvertes.fr/hal-01805251
• 37N. Tripuraneni, N. Flammarion, F. Bach, M. I. Jordan.
  
  Averaging Stochastic Gradient Descent on Riemannian Manifolds, in: Computational Learning Theory (COLT), Stockholm, Sweden, July 2018, https://arxiv.org/abs/1802.09128 - COLT 2018.
  
  https://hal.archives-ouvertes.fr/hal-01957015

Other Publications

• 38M. Barré, A. D'Aspremont.
  
  ${𝐌}^{*}$-Regularized Dictionary Learning, October 2018, https://arxiv.org/abs/1810.02748 - working paper or preprint. [ DOI : 10.02748 ]
  
  https://hal.archives-ouvertes.fr/hal-01897496
• 39R. Berthier, F. Bach, P. Gaillard.
  
  Gossip of Statistical Observations using Orthogonal Polynomials, May 2018, https://arxiv.org/abs/1805.08531 - working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01797016
• 40R. Bollapragada, D. Scieur, A. d'Aspremont.
  
  Nonlinear Acceleration of Momentum and Primal-Dual Algorithms, October 2018, https://arxiv.org/abs/1810.04539 - working paper or preprint. [ DOI : 10.04539 ]
  
  https://hal.archives-ouvertes.fr/hal-01893921
• 41L. Chizat, F. Bach.
  
  A Note on Lazy Training in Supervised Differentiable Programming, December 2018, https://arxiv.org/abs/1812.07956 - working paper or preprint.
  
  https://hal.inria.fr/hal-01945578
• 42C. Ciliberto, F. Bach, A. Rudi.
  
  Localized Structured Prediction, December 2018, https://arxiv.org/abs/1806.02402 - 53 pages, 7 figures, 1 algorithm.
  
  https://hal.inria.fr/hal-01958863
• 43A. Dieuleveut, A. Durmus, F. Bach.
  
  Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains, April 2018, https://arxiv.org/abs/1707.06386 - working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01565514
• 44Y. Drori, A. B. Taylor.
  
  Efficient First-order Methods for Convex Minimization: a Constructive Approach, October 2018, https://arxiv.org/abs/1803.05676 - Code available at https://github.com/AdrienTaylor/GreedyMethods.
  
  https://hal.inria.fr/hal-01902048
• 45P. Gaillard, S. Gerchinovitz, M. Huard, G. Stoltz.
  
  Uniform regret bounds over $R^d$ for the sequential linear regression problem with the square loss, February 2018, https://arxiv.org/abs/1805.11386 - working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01802004
• 46P. Gaillard, O. Wintenberger.
  
  Efficient online algorithms for fast-rate regret bounds under sparsity, May 2018, https://arxiv.org/abs/1805.09174 - working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01798201
• 47H. Hendrikx, F. Bach, L. Massoulié.
  
  Accelerated decentralized optimization with local updates for smooth and strongly convex objectives, October 2018, working paper or preprint.
  
  https://hal.inria.fr/hal-01893568
• 48T. Kerdreux, A. d'Aspremont, S. Pokutta.
  
  Restarting Frank-Wolfe, October 2018, https://arxiv.org/abs/1810.02429 - working paper or preprint. [ DOI : 10.02429 ]
  
  https://hal.archives-ouvertes.fr/hal-01893922
• 49A. Nowak-Vila, F. Bach, A. Rudi.
  
  Sharp Analysis of Learning with Discrete Losses, October 2018, https://arxiv.org/abs/1810.06839 - working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01893006
• 50D. M. Ostrovskii, F. Bach.
  
  Finite-sample Analysis of M-estimators using Self-concordance, October 2018, https://arxiv.org/abs/1810.06838 - working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01895127
• 51A. Recanati, T. Kerdreux, A. D'Aspremont.
  
  Reconstructing Latent Orderings by Spectral Clustering, July 2018, https://arxiv.org/abs/1807.07122 - working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01846269
• 52A. Recanati, N. Servant, J.-P. Vert, A. D'Aspremont.
  
  Robust Seriation and Applications to Cancer Genomics, July 2018, https://arxiv.org/abs/1806.00664 - working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01851960
• 53E. K. Ryu, A. B. Taylor, C. Bergeling, P. Giselsson.
  
  Operator Splitting Performance Estimation: Tight contraction factors and optimal parameter selection, December 2018, https://arxiv.org/abs/1812.00146 - working paper or preprint.
  
  https://hal.inria.fr/hal-01943622
• 54D. Scieur, E. Oyallon, A. D'Aspremont, F. Bach.
  
  Nonlinear Acceleration of Deep Neural Networks, May 2018, working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01799269
• 55J. Tang, M. Golbabaee, F. Bach, M. E. Davies.
  
  Structure-Adaptive Accelerated Coordinate Descent, October 2018, working paper or preprint.
  
  https://hal.archives-ouvertes.fr/hal-01889990
• 56T.-H. Vu, A. Osokin, I. Laptev.
  
  Tube-CNN: Modeling temporal evolution of appearance for object detection in video, January 2019, https://arxiv.org/abs/1812.02619 - 13 pages, 8 figures, technical report.
  
  https://hal.archives-ouvertes.fr/hal-01980339