Alexandre d'Aspremont - Research

Working Papers

• C. Lezane, C. Guzmán, A. d'Aspremont. An Oblivious Stochastic Composite Optimization Algorithm for Eigenvalue Optimization Problems
  Preprint on ArXiv: 2306.17470.

• I. Fayad, P. Ciais, M. Schwartz, J.P. Wigneron, N. Baghdadi, A. de Truchis, A. d'Aspremont, F. Frappart, S. Saatchi, A. Pellissier-Tanon, H. Bazzi. Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights
  Preprint on ArXiv: 2304.11487.

• Shushi Peng, Clément Giron, Gang Liu, Alexandre d'Aspremont, Antoine Benoit, Thomas Lauvaux, Xin Lin, Hugo De Almeida Rodrigues, Marielle Saunois, Philippe Ciais, High resolution assessment of coal mining methane emissions by satellite in Shanxi, China
  Preprint on EarthArXiv: 3401.

• T. Kerdreux, A. d'Aspremont, S. Pokutta, Local and Global Uniform Convexity Conditions.
  Preprint on ArXiv: 2102.05134.

Monographs

• A. d'Aspremont, D. Scieur, A Taylor, Acceleration Methods.
  Preprint on ArXiv: 2101.09545. Foundations and Trends in Optimization, Vol. 5, No. 1-2, pp 1-245, December 2021.

Refereed Publications

• A. d'Aspremont, C. Guzmán, C. Lezane Optimal Algorithms for Stochastic Complementary Composite Minimization
  Preprint on ArXiv: 2211.01758. To appear in SIAM Journal on Optimization.

• Sizhuo Li, Martin Brandt, Rasmus Fensholt, Ankit Kariryaa, Christian Igel, Fabian Gieseke, Thomas Nord-Larsen, Stefan Oehmke, Ask Holm-Carlsen, Samuli Junttila, Xiaoye Tong, Alexandre d’Aspremont, Philippe Ciais, Digital twinning of all forest and non-forest trees at national level via deep learning
  Preprint on HAL: 03837835. To appear in Proceedings of the National Academy of Science.

• A. Groshenry, C. Giron, A. d'Aspremont, T. Lauvaux, T. Ehret, Detecting Methane Plumes using PRISMA: Deep Learning Model and Data Augmentation
  Preprint on ArXiv: 2211.15429. NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning.

• Thibaud Ehret, Aurélien De Truchis, Matthieu Mazzolini, Jean-Michel Morel, Alexandre d'Aspremont, Thomas Lauvaux, Gabriele Facciolo, Global Tracking and Quantification of Oil and Gas Methane Leaks from Recurrent Sentinel-2 Imagery.
  Preprint on ArXiv: 2110.11832. Environmental Science & Technology, 56 (14), 10517-10529, July 2022.

• T. kerdreux, A. d'Aspremont, I. Colin, Stable Bounds on the Duality Gap of Separable Nonconvex Optimization Problems.
  Preprint on ArXiv: 1712.08559. To appear in Mathematics of Operations Research.

• M. Barré, A. Taylor, A. d'Aspremont, Convergence of Constrained Anderson Acceleration.
  Preprint on ArXiv: 2010.15482. SIAM Journal on the Mathematics of Data Science, 4 (3), 979-1002, 2022.

• Z. Deng, P. Ciais, Z. Tzompa-Sosa, M. Saunois, C. Qiu, C. Tan, T. Sun, P. Ke, Y. Cui, K. Tanaka, X Lin, R. L. Thompson, H. Tian, Y. Yao, Y. Huang, R. Lauerwald, A. K. Jain, X. Xu, A. Bastos, S. Sitch, P. I. Palmer, T. Lauvaux, A. d’Aspremont, C. Giron, A. Benoit, B. Poulter, J. Chang, A. M. R. Petrescu, S. J. Davis, Z. Liu, G. Grassi, C. Albergel, F. Chevallier. Comparing national greenhouse gas budgets reported in UNFCCC inventories against atmospheric inversions.
  Preprint on ESSD: essd-2021-235. Earth System Science Data 14  1639–1675, 2022.

• R. Bollapragada, D. Scieur, A. d'Aspremont, Nonlinear Acceleration of Momentum and Primal-Dual Algorithms.
  Preprint on ArXiv: 1810.04539. Mathematical Programming, February 2022.

• T. Lauvaux, C. Giron, M. Mazzolini, A. d'Aspremont, R. Duren, D. Cusworth, D. Shindell, P. Ciais, Global Assessment of Oil and Gas Methane Ultra-Emitters.
  Preprint on ArXiv: 2105.06387. Science, Vol 375, Issue 6580, pp. 557-561, February 2022.

• T. Kerdreux, A. d'Aspremont, S. Pokutta, Restarting Frank-Wolfe.
  Preprint on ArXiv: 1810.02429. Journal of Optimization Theory and Applications, 192 (3), 799-829, March 2022.

• A. Askari, A. d'Aspremont, L. El Ghaoui, Approximation Bounds for Sparse Programs.
  Preprint on ArXiv: 2102.06742. SIAM Journal on the Mathematics of Data Science, Vol. 4 (2), pp. 514-530, 2022.

• T. Kerdreux, C. Roux, A. d'Aspremont, S. Pokutta, Linear Bandits on Uniformly Convex Sets.
  Preprint on ArXiv: 2103.05907. JMLR 22(284):1−23, 2021.

• A. Askari, Q. Rebjock, A. d'Aspremont, L. El Ghaoui, FANOK: Knockoffs in Linear Time.
  Preprint on ArXiv: 2006.08790. SIAM Journal on the Mathematics of Data Science, 3 (3), 833-853, 2021.

• T. Kerdreux, A. d'Aspremont, Frank-Wolfe on Uniformly Convex Sets.
  Preprint on ArXiv: 2004.11053. AISTATS 2021.

• R. Dragomir, J. Bolte, A. d'Aspremont, Quartic First-Order Methods for Low Rank Minimization.
  Preprint on ArXiv: 1901.10791. Journal of Optimization Theory and Applications, 189 (2), 341-363 (2021).

• G. Mialon, D. Chen, A. d'Aspremont, J. Mairal, A Trainable Optimal Transport Embedding for Feature Aggregation.
  Preprint on ArXiv: 2006.12065 ICLR 2021.

• A. d'Aspremont, M. Cucuringu, H. Tyagi, Ranking and Synchronization from Pairwise Measurements via SVD.
  Preprint on ArXiv: 1906.02746. Journal of Machine Learning Research, 22 (19), February 2021.

• R. Dragomir, A. Taylor, A. d'Aspremont, J. Bolte, Optimal Complexity and Certification of Bregman First-Order Methods.
  Preprint on ArXiv: 1911.08510. Mathematical Programming, 194 (1), 41-83, July 2022.

• A. Askari, A. d'Aspremont, L. El Ghaoui, Naive Feature Selection: Sparsity in Naive Bayes.
  Preprint on ArXiv: 1905.09884. AISTATS 2020.

• M. Barré, A. Taylor, A. d'Aspremont, Complexity Guarantees for Polyak Steps with Momentum.
  Preprint on ArXiv: 2002.00915. COLT 2020.

• G. Mialon, A. d'Aspremont, J. Mairal, Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Function.
  Preprint on ArXiv: 1912.02566. AISTATS 2020.

• F.P. Paty, A. d'Aspremont, M. Cuturi, Regularity as Regularization: Smooth and Strongly Convex Brenier Potentials in Optimal Transport.
  Preprint on ArXiv: 1905.10812. AISTATS 2020.

• A. Podosinnikova, A. Perry, A. Wein, F. Bach, A. d'Aspremont, D. Sontag, Overcomplete Independent Component Analysis via SDP.
  Preprint on ArXiv: 1901.08334. AISTATS 2019

• V. Roulet, A. d'Aspremont, Sharpness, Restart and Acceleration.
  Preprint on ArXiv: 1702.03828. SIAM Journal on Optimization, 30(1), pp. 262–289, 2020.

• T. Kerdreux, F. Pedregosa, A. d'Aspremont Frank-Wolfe with Subsampling Oracle.
  Preprint on ArXiv: 1803.07348. ICML 2018.

• D. Scieur, E. Oyallon, A. d'Aspremont and F. Bach, Nonlinear Acceleration of CNNs.
  Preprint on ArXiv: 1806.00370. ICLR 2018.

• V. Roulet, N. Boumal, A. d'Aspremont, Computational Complexity versus Statistical Performance on Sparse Recovery Problems.
  Preprint on ArXiv: 1506.03295. Information and Inference, 2019.

• D. Scieur, A. d'Aspremont, F. Bach, Regularized Nonlinear Acceleration.
  Preprint on ArXiv: 1606.04133. Mathematical Programming Series A, 2018.

• D. Scieur, A. d'Aspremont, F. Bach, Nonlinear Acceleration of Stochastic Algorithms.
  Preprint on ArXiv: 1706.07270. NIPS 2017

• D. Scieur, V. Roulet, F. Bach, A. d'Aspremont, Integration Methods and Accelerated Optimization Algorithms.
  Preprint on ArXiv: 1702.06751. NIPS 2017

• A. d'Aspremont, C. Guzmán, M. Jaggi, An Optimal Affine Invariant Smooth Minimization Algorithm.
  Preprint on ArXiv: 1301.0465. SIAM Journal on Optimization, 28(3), pp. 2384–2405, 2018.

• A. Recanati, T. Brüls, A. d'Aspremont, A Spectral Algorithm for Fast de Novo Layout of Uncorrected Long Nanopore Reads.
  Preprint on ArXiv: 1609.07293. Bioinformatics, Volume 33, Issue 20, pp. 3188–3194, October 2017.

• F. Fogel, A. d'Aspremont, M. Vojnovic, Serialrank: Spectral Ranking using Seriation.
  Preprint on ArXiv: 1406.5370. Journal of Machine Learning Research, 17, pp. 1-45, February 2016.

• F. Fogel, I. Waldspurger, A. d'Aspremont, Phase Retrieval for Imaging Problems.
  Preprint on ArXiv: 1304.7735, source code). Mathematical Programming Computations, 8(3), pp. 311-335, September 2016.

• M. H. Seaberg, A. d'Aspremont, J. J. Turner, Coherent Diffractive Imaging Using Randomly Coded Masks.
  Preprint on ArXiv: 1509.03229. Applied Physics Letters, 107(23), 231103, December 2015.

• F. Fogel, R. Jenatton, F. Bach, A. d'Aspremont, Convex Relaxations for Permutation Problems.
  Preprint on ArXiv: 1306.4805. SIAM Journal on Matrix Analysis and Applications, 36(4), pp. 1381-1589, 2015.

• A. d'Aspremont, N. El Karoui, A Stochastic Smoothing Algorithm for Semidefinite Programming.
  Preprint on ArXiv: 1204.0665. SIAM Journal on Optimization, 24(3), pp. 1138-1177, 2014.

• A. d'Aspremont, F. Bach, L. El Ghaoui, Approximation Bounds for Sparse Principal Component Analysis.
  Preprint on ArXiv: 1205.0121. Mathematical Programming B, 148(1–2), pp. 89-110, December 2014.

• I. Waldspurger, A. d'Aspremont, S. Mallat, Phase Recovery, MaxCut and Complex Semidefinite Programming.
  Preprint on ArXiv: 1206.0102. Mathematical Programming A, 149(1-2), pp. 47-81, February 2015.

• A. d'Aspremont, N. El Karoui, Weak Recovery Conditions from Graph Partitioning Bounds and Order Statistics.
  Preprint on ArXiv: 1004.5151. Mathematics of Operations Research, 38(2), pp. 228-247, 2013.

• R. Luss, A. d'Aspremont Predicting Abnormal Returns from News using Text Classification.
  Preprint on ArXiv: 0809.2792. Quantitative Finance, 15(6), pp.999-1012, 2015.

• A. d'Aspremont Subsampling Algorithms for Semidefinite Programming.
  Preprint on ArXiv: 0803.1990, source code). Stochastic Systems, 2(1), pp. 274-305, October 2011.

• Y. Zhang, A. d'Aspremont, L. El Ghaoui, Sparse PCA: Convex Relaxations, Algorithms and Applications.
  Preprint on ArXiv: 1011.3781. Handbook on Semidefinite, Cone and Polynomial Optimization, pp. 915-940, M. Anjos and J.B. Lasserre, editors, 2011.

• N. El Karoui, A. d'Aspremont, Second Order Accurate Distributed Eigenvector Computation for Extremely Large Matrices.
  Preprint on ArXiv: 0908.0137. Electronic Journal of Statistics, 4, pp. 1345-1385, 2010.

• V. Krishnamurthy, A. d'Aspremont, A Pathwise Algorithm for Covariance Selection.
  Preprint on ArXiv: 0908.0143. Optimization for Machine Learning, S. Sra, S. Nowozin and S. Wright, editors, MIT Press, 2011.

• M. Cuturi, J-P. Vert, A. d'Aspremont, White Functionals for Anomaly Detection in Dynamical Systems.
  Preprint on ArXiv: 0908.0143. NIPS 2009.

• A. d'Aspremont, Identifying Small Mean Reverting Portfolios.
  Preprint on ArXiv: 0708.3048. Quantitative Finance, 11(3), pp. 351-364, March 2011.

• A. d'Aspremont, L. El Ghaoui, Testing the Nullspace Property using Semidefinite Programming.
  Preprint on ArXiv: 0807.3520, NSProp source code). Mathematical Programming, Series B, 127(1), pp. 123-144, 2011.

• R. Luss, A. d'Aspremont, Support Vector Machine Classification with Indefinite Kernels.
  Preprint on ArXiv: 0804.0188, IndefiniteSVM source code). Mathematical Programming Computations, 1(2), pp. 97-118, October 2009.

• A. d'Aspremont, F. Bach, L. El Ghaoui, Optimal Solutions for Sparse Principal Component Analysis.
  Preprint on ArXiv: 0707.0705, PathSPCA source code). Journal of Machine Learning Research, 9, pp. 1269-1294, July 2008.

• O. Banerjee, L. El Ghaoui, A. d'Aspremont, Model Selection Through Sparse Maximum Likelihood Estimation.
  Preprint on ArXiv: 0707.0704, COVSEL source code). Journal of Machine Learning Research, 9, pp. 485-516, March 2008.

• R. Luss, A. d'Aspremont, Clustering and Feature Selection using Sparse Principal Component Analysis.
  Preprint on ArXiv: 0707.0701, DSPCA source code). Optimization and Engineering, 11(1), pp. 145-157, February 2010.

• A. d'Aspremont, O. Banerjee, L. El Ghaoui, First-Order Methods for Sparse Covariance Selection.
  Preprint on ArXiv: math.OC/0609812, COVSEL source code). SIAM Journal on Matrix Analysis and its Applications, 30(1), pp. 56-66, February 2008.

• A. d'Aspremont, Smooth Optimization with Approximate Gradient.
  Preprint on ArXiv: math.OC/0512344. SIAM Journal on Optimization, 19(3), pp. 1171-1183, December 2008.

• A. d'Aspremont, A Market Test for the Positivity of Arrow-Debreu Prices.
  Preprint on ArXiv: cs.CE/0510027. In Frontiers in Quantitative Finance: Credit Risk and Volatility Modeling, Wiley, November 2008.

• A. d'Aspremont, L. El Ghaoui, M. I. Jordan, G. R. G. Lanckriet, A Direct Formulation for Sparse PCA Using Semidefinite Programming.
  Preprint on ArXiv: cs.CE/0406021, DSPCA source code). SIAM Review, 49(3), pp. 434-448, July 2007.
  Received the SIAM Optimization Prize for 2004-2007.

• A. d'Aspremont, L. El Ghaoui, Static Arbitrage Bounds on Basket Option Prices.
  Preprint on ArXiv: math.OC/0302243, source code). Mathematical Programming, Series A 106(3), pp. 467-489, July 2006.

• A. d'Aspremont, Risk-Management Methods for the Libor Market Model Using Semidefinite Programming.
  Preprint on ArXiv: cs.CE/0302035. Journal of Computational Finance 8(4), pp. 77-99, Summer 2005.

• A. d'Aspremont, Interest Rate Model Calibration Using Semidefinite Programming.
  Preprint on ArXiv: cs.CE/0302034. Applied Mathematical Finance 10(3), pp. 183-213, September 2003.

Notes, Conference Papers, Discussion Papers, Surveys, etc…

• M. Romain, A. d'Aspremont, A Bregman Method for Structure Learning on Sparse Directed Acyclic Graphs.
  Preprint on ArXiv: 2011.02764.

• M. Barré, C. Giron, M. Mazzolini, A. d'Aspremont, Averaging Atmospheric Gas Concentration Data using Wasserstein Barycenters.
  Preprint on ArXiv: 2010.02762.

• A. d'Aspremont, M. Pilanci, Global Convergence of Frank Wolfe on One Hidden Layer Networks.
  Preprint on ArXiv: 2002.02208.

• M. Barré, A. d'Aspremont, M*-Regularized Dictionary Learning.
  Preprint on ArXiv: 1810.02748.

• M. Barré, A. d'Aspremont, Polyak Steps for Adaptive Fast Gradient Methods.
  Preprint on ArXiv: 1906.03056.

• D. Scieur, E. Oyallon, A. d'Aspremont and F. Bach, Nonlinear Acceleration of Deep Neural Networks.
  Preprint on ArXiv: 1805.09639.

• A. Recanati, T. Kerdreux, A. d'Aspremont, Reconstructing Latent Orderings by Spectral Clustering.
  Preprint on ArXiv: 1807.07122, (local pdf file).

• A. Recanati, N. Servant, J.P. Vert, A. d'Aspremont, Robust Seriation and Applications to Cancer Genomics.
  Preprint on ArXiv: 1806.00664, (local pdf file).

• V. Roulet, F. Fogel, A. d'Aspremont, F. Bach, Learning with Clustering Structure.
  Preprint on ArXiv: 1506.04908, (local pdf file).

• K. Vervier, P. Mahé, A. d’Aspremont, JB. Veyrieras, JP. Vert On Learning Matrices with Orthogonal Columns
  Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science Volume 8726, 2014, pp 274-289.

• M. Cuturi, A. d'Aspremont, Mean Reversion with a Variance Threshold.
  Local pdf file. Proceedings ICML 2013, pp 271-279.

• A. d'Aspremont, Quelques applications de la programmation semidéfinie.
  MATAPLI, June 2013.

• A. d'Aspremont, Sparse Recovery, Kashin Decomposition and Conic Programming.
  Preprint on ArXiv: 1101.3027, January 2011.

• F. Bach, S. D. Ahipasaoglu, A. d'Aspremont Convex Relaxations for Subset Selection.
  Preprint on ArXiv: 1006.3601.

• A. d'Aspremont, Smooth Semidefinite Optimization.
  Optima 78, pp. 9-11, November 2008.

• V. Krishnamurthy, A. d'Aspremont, Convex Algorithms for Nonnegative Matrix Factorization.
  Preprint on ArXiv: 1207.0318, May 2007.

• A. d'Aspremont, S. Boyd, Relaxations and Randomized Methods for Nonconvex QCQPs., Fall 2003.
  

Dissertations

• Thèse (École Polytechnique): Interest Rate Model Calibration Using Semidefinite Programming.
  Advisor: Nicole El Karoui. (Local pdf file and slides).

• PhD Thesis (Stanford University): Shape Constrained Optimization, with Applications in Finance and Engineering.
  Advisor: Stephen Boyd. (Local pdf file and slides).