Bibliography

Publications of the year

Doctoral Dissertations and Habilitation Theses

• 1D. Babichev.
  On Efficient Methods for High-dimensional Statistical Estimation, PSL Research University, February 2019.
  https://hal.archives-ouvertes.fr/tel-02433016
• 2T. Shpakova.
  On Parameter Learning for Perturb-and-MAP Models, PSL Research University, February 2019.
  https://hal.archives-ouvertes.fr/tel-02431640

Articles in International Peer-Reviewed Journals

• 3P. Askenazy, F. Bach.
  IA et emploi : Une menace artificielle, in: Pouvoirs - Revue française d’études constitutionnelles et politiques, September 2019, vol. 170, pp. 1-7.
  https://hal.archives-ouvertes.fr/hal-02343633
• 4M. Brégère, P. Gaillard, Y. Goude, G. Stoltz.
  Target Tracking for Contextual Bandits: Application to Demand Side Management, in: Proceedings of Machine Learning Research, June 2019, vol. 97, pp. 754-763, https://arxiv.org/abs/1901.09532.
  https://hal.archives-ouvertes.fr/hal-01994144
• 5Y. Drori, A. B. Taylor.
  Efficient First-order Methods for Convex Minimization: a Constructive Approach, in: Mathematical Programming, Series A, 2019, https://arxiv.org/abs/1803.05676 - Code available at https://github.com/AdrienTaylor/GreedyMethods, forthcoming. [ DOI : 10.1007/s10107-019-01410-2 ]
  https://hal.inria.fr/hal-01902048
• 6P. Gaillard, S. Gerchinovitz, M. Huard, G. Stoltz.
  Uniform regret bounds over $R^d$ for the sequential linear regression problem with the square loss, in: Proceedings of Machine Learning Research, 2019, vol. 98, pp. 404-432, https://arxiv.org/abs/1805.11386.
  https://hal.archives-ouvertes.fr/hal-01802004
• 7J.-L. Peyrot, L. Duval, F. Payan, L. Bouard, L. Chizat, S. Schneider, M. Antonini.
  HexaShrink, an exact scalable framework for hexahedral meshes with attributes and discontinuities: multiresolution rendering and storage of geoscience models, in: Computational Geosciences, August 2019, vol. 23, n^o 4, pp. 723-743, https://arxiv.org/abs/1903.07614. [ DOI : 10.1007/s10596-019-9816-2 ]
  https://hal-ifp.archives-ouvertes.fr/hal-01857997
• 8V. Roulet, N. Boumal, A. D'Aspremont.
  Computational complexity versus statistical performance on sparse recovery problems, in: Information and Inference, January 2019, https://arxiv.org/abs/1506.03295. [ DOI : 10.1093/imaiai/iay020 ]
  https://hal.archives-ouvertes.fr/hal-02340337

International Conferences with Proceedings

• 9A. Bietti, G. Mialon, D. Chen, J. Mairal.
  A Kernel Perspective for Regularizing Deep Neural Networks, in: ICML 2019 - 36th International Conference on Machine Learning, Long Beach, United States, Proceedings of Machine Learning Research, June 2019, vol. 97, pp. 664-674, https://arxiv.org/abs/1810.00363.
  https://hal.inria.fr/hal-01884632
• 10R. Bollapragada, D. Scieur, A. D'Aspremont.
  Nonlinear Acceleration of Momentum and Primal-Dual Algorithms, in: AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics, Naha, Japan, The 22nd International Conference on Artificial Intelligence and Statistics,, April 2019, vol. 89, https://arxiv.org/abs/1810.04539. [ DOI : 10.04539 ]
  https://hal.archives-ouvertes.fr/hal-01893921
• 11T. Kerdreux, A. D'Aspremont, S. Pokutta.
  Restarting Frank-Wolfe, in: AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics, Naha, Japan, Proceedings of Machine Learning Research, April 2019, vol. 89, https://arxiv.org/abs/1810.02429. [ DOI : 10.02429 ]
  https://hal.archives-ouvertes.fr/hal-01893922
• 12U. Marteau-Ferey, F. Bach, A. Rudi.
  Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses, in: NeurIPS 2019 - Conference on Neural Information Processing Systems, Vancouver, Canada, December 2019, https://arxiv.org/abs/1907.01771.
  https://hal.inria.fr/hal-02169626
• 13T. Ryffel, E. Dufour-Sans, R. Gay, F. Bach, D. Pointcheval.
  Partially Encrypted Machine Learning using Functional Encryption, in: NeurIPS 2019 - Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, Advances in Neural Information Processing Systems, December 2019, https://arxiv.org/abs/1905.10214.
  https://hal.inria.fr/hal-02357181
• 14A. Taylor, F. Bach.
  Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions, in: COLT 2019 - Conference on Learning Theory, Phoenix, United States, June 2019, https://arxiv.org/abs/1902.00947 - 12 pages + appendix; code available at https://github.com/AdrienTaylor/Potential-functions-for-first-order-methods.
  https://hal.inria.fr/hal-02009309

Conferences without Proceedings

• 15P. Ablin, A. Gramfort, J.-F. Cardoso, F. Bach.
  Stochastic algorithms with descent guarantees for ICA, in: AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics, Naha, Japan, April 2019.
  https://hal.archives-ouvertes.fr/hal-02372092
• 16L. Chizat, E. Oyallon, F. Bach.
  On Lazy Training in Differentiable Programming, in: NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems, Vancouver, Canada, December 2019, https://arxiv.org/abs/1812.07956.
  https://hal.inria.fr/hal-01945578
• 17A. Genevay, L. Chizat, F. Bach, M. Cuturi, G. Peyré.
  Sample Complexity of Sinkhorn divergences, in: AISTATS'19 - 22nd International Conference on Artificial Intelligence and Statistics, Okinawa, Japan, K. Chaudhuri, M. Sugiyama (editors), April 2019, https://arxiv.org/abs/1810.02733. [ DOI : 10.02733 ]
  https://hal.archives-ouvertes.fr/hal-02411822
• 18R. M. Gower, N. Loizou, X. Qian, A. Sailanbayev, E. Shulgin, P. Richtárik.
  SGD: General Analysis and Improved Rates, in: International Conference on Machine Learning, Los Angeles, United States, June 2019.
  https://hal.telecom-paristech.fr/hal-02365318
• 19D. M. Ostrovskii, A. Rudi.
  Affine Invariant Covariance Estimation for Heavy-Tailed Distributions, in: COLT 2019 - 32nd Annual Conference on Learning Theory, Phoenix, United States, June 2019, https://arxiv.org/abs/1902.03086.
  https://hal.archives-ouvertes.fr/hal-02011464
• 20A. Podosinnikova, A. Perry, A. Wein, F. Bach, A. D'Aspremont, D. Sontag.
  Overcomplete Independent Component Analysis via SDP, in: AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics, Naha, Japan, April 2019, https://arxiv.org/abs/1901.08334 - Appears in: Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019). 21 pages.
  https://hal.archives-ouvertes.fr/hal-02340366

Other Publications

• 21A. Askari, A. D'Aspremont, L. E. Ghaoui.
  Naive Feature Selection: Sparsity in Naive Bayes, October 2019, https://arxiv.org/abs/1905.09884 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02340374
• 22D. Babichev, D. M. Ostrovskii, F. Bach.
  Efficient Primal-Dual Algorithms for Large-Scale Multiclass Classification, February 2019, https://arxiv.org/abs/1902.03755 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02012569
• 23F. Bach.
  Max-Plus Matching Pursuit for Deterministic Markov Decision Processes, June 2019, https://arxiv.org/abs/1906.08524 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02155865
• 24M. Barré, A. D'Aspremont.
  Polyak Steps for Adaptive Fast Gradient Method, October 2019, https://arxiv.org/abs/1906.03056 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02340373
• 25R. Berthier, F. Bach, P. Gaillard.
  Accelerated Gossip in Networks of Given Dimension using Jacobi Polynomial Iterations, February 2019, https://arxiv.org/abs/1805.08531 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-01797016
• 26A. D'Aspremont, M. Cucuringu, H. Tyagi.
  Ranking and synchronization from pairwise measurements via SVD, October 2019, https://arxiv.org/abs/1906.02746 - 42 pages, 9 figures.
  https://hal.archives-ouvertes.fr/hal-02340372
• 27R.-A. Dragomir, A. D'Aspremont, J. Bolte.
  Quartic First-Order Methods for Low Rank Minimization, October 2019, https://arxiv.org/abs/1901.10791 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02340369
• 28R.-A. Dragomir, A. Taylor, A. D'Aspremont, J. Bolte.
  Optimal Complexity and Certification of Bregman First-Order Methods, November 2019, https://arxiv.org/abs/1911.08510 - working paper or preprint.
  https://hal.inria.fr/hal-02384167
• 29A. Défossez, N. Usunier, L. Bottou, F. Bach.
  Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed, September 2019, https://arxiv.org/abs/1909.01174 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02277338
• 30A. Défossez, N. Usunier, L. Bottou, F. Bach.
  Music Source Separation in the Waveform Domain, November 2019, https://arxiv.org/abs/1911.13254 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02379796
• 31H. Hendrikx, F. Bach, L. Massoulié.
  An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums, September 2019, working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02280763
• 32R. Jézéquel, P. Gaillard, A. Rudi.
  Efficient online learning with kernels for adversarial large scale problems, May 2019, https://arxiv.org/abs/1902.09917 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02019402
• 33U. Marteau-Ferey, D. M. Ostrovskii, F. Bach, A. Rudi.
  Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance, June 2019, https://arxiv.org/abs/1902.03046 - working paper or preprint.
  https://hal.inria.fr/hal-02011895
• 34G. Mialon, A. D'Aspremont, J. Mairal.
  Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions, December 2019, working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02395624
• 35F.-P. Paty, A. D'Aspremont, M. Cuturi.
  Regularity as Regularization: Smooth and Strongly Convex Brenier Potentials in Optimal Transport, October 2019, https://arxiv.org/abs/1905.10812 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02340371
• 36L. Pillaud-Vivien, F. Bach, T. Lelièvre, A. Rudi, G. Stoltz.
  Statistical Estimation of the Poincaré constant and Application to Sampling Multimodal Distributions, November 2019, https://arxiv.org/abs/1910.14564 - working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-02327453
• 37T.-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