1. [Thiry et al. 2021] The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods, Louis THIRY and Michael Arbel and Eugene Belilovsky and Edouard Oyallon, International Conference on Learning Representations, Mai 2021. (PDF)
  2. [Kerdreux et al. 2021] Neural wild guess, Louis Thiry Thomas Kerdreux, CVPR workshop Ethical Considerations in Creative applications of Computer Vision, June 2021. (PDF)
  3. 2020

  4. [Lapointe et al. 2020] Machine learning surrogate models for prediction of point defect vibrational entropy, Lapointe, Clovis and Swinburne, Thomas D and Thiry, Louis and Mallat, St{'e}phane and Proville, Laurent and Becquart, Charlotte S and Marinica, Mihai-Cosmin, Phys. Rev. Materials, March 2020. (PDF)
  5. [Kerdreux et al., 2020] Interactive Neural style transfer with artists, Kerdreux, T. and Thiry, L. and Kerdreux, E., International conference of computational creativity 2020, Coimbre, Portugal, September 2020. (PDF)
  6. [Zarka et al., 2020] Deep Network Classification by Scattering and Homotopy Dictionary Learning, Zarka J., Thiry L., Angles T., and Mallat S., Eighth International Conference on Learning Representations (ICLR 2020), April 2020. (PDF)
  7. [Kymatio] Kymatio: Scattering Transforms in Python, Andreux, M. and Angles, T. and Exarchakis, G. and Leonarduzzi, R. and Rochette, G. and Thiry, L. and Zarka, J. and Mallat, S. and Anden, J. and Belilovsky, E. and Bruna, J. and Lostanlen, V. and Chaudhary, M. and Hirn, Matthew J. and Oyallon, Edouard and Zhang, S. and Cella, C. and Eickenberg, Michael, Journal of Machine Learning Research 21 (2020) 1-6, January 2020. (PDF)
  8. 2019

  9. [Cabannes et al., 2019] Dialog on a Canvas with a Machine, Cabannes, V. and Kerdreux, T. and Thiry, L. and Campana, T. and Ferrandes, C., Machine Learning for Creativity and Design, NeurIPS 2019 Workshop, Vancouver, Canada, December 2019. (PDF)
  10. [Brochard et al., 2019] Statistical learning of geometric characteristics of wireless networks, Brochard, A., Błaszczyszyn, B., Mallat, S., and Zhang, S., Proc. of IEEE INFOCOM 2019: 2224-2232, 2019. (PDF)
  11. [Leonarduzzi et al., 2019] Maximum-entropy Scattering Models for Financial Time Series, Leonarduzzi, R., Rochette, G., Bouchaud, J-P., and Mallat, S., Proc. of IEEE ICASSP 2019: 5496-5500, 2019. (PDF)
  12. [Mallat et al., 2019] Phase Harmonic Correlations and Convolutional Neural Networks, Mallat, S., Zhang, S., and Rochette, G., IMA Journal of Information and Inference, November 2019. (PDF)
  13. [Zhang et Mallat, 2019] Maximum Entropy Models from Phase Harmonic Covariances, Zhang, S., and Mallat, S., arXiv:1911.10017, November 2019. (PDF)
  14. [Anden et al., 2019] Classification with joint time-frequency scattering, Anden, J., Lostanlen, V., and Mallat, S., IEEE Trans. on Signal Processing, vol 17, no. 4, May 2019. (PDF)
  15. 2018

  16. [Bruna et Mallat, 2018] Multiscale Sparse Microcanonical Models, Bruna, J. and Mallat, S., Jour. of Math. Stat. and Learning, vol. 1, no. 3, p. 257-315, November 2018. (PDF)
  17. [Andreux et Mallat, 2018] Music generation and transformation with moment matching scattering inverse networks, Andreux, M. and Mallat, S., 19th International Society for Music Information Retrieval Conference (ISMIR 2018), September 2018. (PDF)
  18. [Angles et Mallat, 2018] Generative Networks as Inverse Problems with Scattering Transforms, Angles, T. and Mallat, S., Sixth International Conference on Learning Representations (ICLR 2018), May 2018. (PDF)
  19. [Eickenberg et al., 2018] Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties, Eickenberg, M., Exarchakis, G., Hirn, M., Mallat, S., and Thiry, L., Jour. of Chemical Physics, vol 148, no. 24, May 2018. (PDF)
  20. 2017

  21. [Eickenberg et al., 2017] Solid Harmonic Wavelet Scattering: Predicting Quantum Molecular Energy from Invariant Descriptors of 3D Electronic Densities, Eickenberg, M., Exarchakis, G., Hirn, M., and Mallat, S., Advances in Neural Information Processing Systems 30 (NIPS 2017), 2017. (PDF)
  22. [Oyallon, 2017b] Analyzing and Introducing Structures in Deep Convolutional Neural Networks, Oyallon, E., Ph.D. thesis, École normale supérieure - PSL Research University, Paris, France, Oct. 2017. (PDF)
  23. [Oyallon et al., 2017] Scaling the Scattering Transform: Deep Hybrid Networks, Oyallon, E., Belilovsky, E., and Zagoruyko, S., ICCV, 2017. (PDF - v1) (PDF - v2)
  24. [Jacobsen et al., 2017] Hierarchical Attribute CNNs, Jacobsen, J.-H., Oyallon, E., Mallat, S. and Smeulders, A.W.M., ICML PADL, 2017. (PDF)
  25. [Oyallon, 2017a] Building a Regular Decision Boundary with Deep Networks, Oyallon, E., CVPR, 2017. (PDF)
  26. [Lostanlen, 2017] Convolutional Operators in the Time-frequency Domain, Lostanlen V., Ph.D. thesis, École normale supérieure - PSL Research University, Paris, France, Feb. 2017. (PDF)
  27. 2016

  28. [Lostanlen and Cella, 2016] Deep convolutional networks on the pitch spiral for music instrument recognition, Lostanlen V., Cella C.-E., Proc. ISMIR, New York, USA, August 2016. (PDF) (Code)
  29. [Dong et al., 2016] Reservoir Computing with light scattering, Dong J., Gigan S., Krzakala F., Wainrib G., Submitted, 2016.
  30. [Wainrib and Amar, 2016] Iterative random autoencoders and the ping-pong algorithm, Wainrib G., Amar G., Submitted, 2016.
  31. [Morilla et al., 2016] Colonic microRNA-based composite algorithm predicting drug responses in acute severe ulcerative colitis, Morilla I., Uzzan M., Laharie D., Cazals-Hatem D., Daniel F., Bouhnik Y., Ogier-Denis E., Wainrib G., Treton X., Submitted, 2016.
  32. [Ding et al., 2016] Ulcerative Colitis and smoking: an integrative network-based analysis of detoxification gene expression data, Ding Y.-P., Ladeiro Y., Bouhnik Y., Marah A., Zaag H., Cazals-Hatem D., Seksik P., Daniel F., Hugot J.-P., Morilla I., Wainrib G., Tréton X., Ogier-Denis E., Submitted, 2016.
  33. [Victor et al., 2016] Network modeling of Crohn's disease, Victor J.-M., Debret G., Lesne A., Pascoe L., Carrivain P., Wainrib G., Hugot J.-P., PLoS One (to appear), 2016.
  34. [Couillet et al., 2016c] Training performance of echo state neural networks, Couillet R., Wainrib G., Sevi H., Ali H.T., IEEE Statistical Signal Processing Workshop (SSP), Palma de Majorca, Spain, 2016. (PDF)
  35. [Wainrib, 16] Context-dependent representation in recurrent neural networks, Wainrib G., arXiv preprint arXiv:1506.06602, 2016. (PDF)
  36. [Couillet et al., 2016b] The asymptotic performance of linear echo state neural networks, Couillet R., Wainrib G., Sevi H., Ali H.T., Submitted, 2016.
  37. [Couillet et al., 2016a] A random matrix approach to echo-state neural networks, Couillet R., Wainrib G., Sevi H., Ali H.T., International Conference on Machine Learning (ICML), New York, June 2016. (PDF)
  38. [Milišić and Wainrib, 2016] Mathematical modeling of lymphocytes selection in the germinal center, Milišić V., Wainrib G., Journal of Mathematical Biology, 2016. (PDF)
  39. [Wainrib and Galtier, 2016] A local Echo State Property through the largest Lyapunov exponent, Wainrib G., Galtier M., Neural Networks, Apr. 2016. (PDF)
  40. [del Molino et al., 2016] The real Ginibre ensemble with k=O(n) real eigenvalues, del Molino LCG., Pakdaman K., Touboul J., Wainrib G., Journal of Statistical Physics, Mar. 2016. (PDF)
  41. 2015

  42. [Waldspurger, 2015b] Phase retrieval for wavelet transforms, Waldspurger I., arXiv preprint arXiv:1512.07024, 2015. (PDF)
  43. [Lostanlen and Mallat, 2015b] Wavelet Scattering on the Pitch Spiral, Lostanlen V. and Mallat S., Proceedings of DAFx-15, 2015. (PDF) (Code)
  44. [Waldspurger, 2015a] Wavelet transform modulus: phase retrieval and scattering, Waldspurger I., Ph.D. thesis, ED386, Paris, France, Nov. 2015. (PDF)
  45. [Andén et al., 2014] Joint Time-Frequency Scattering for Audio Classification, Andén J., Lostanlen V., Mallat S., Proceedings of 2015 IEEE MLSP Workshop, Sept. 2015. (PDF) (Code)
  46. [Lostanlen and Mallat, 2015a] Transformée en scattering sur la spirale temps-chroma-octave, Lostanlen V. and Mallat S., Proceedings of GRETSI 2015, 2015. (PDF) (Code)
  47. [Wainrib and Galtier, 2015] Regular graphs maximize the variability of random neural networks, Wainrib G. and Galtier M., Physical Review E, Sep. 2015. (PDF)
  48. [Touboul and Wainrib, 2015] Dynamics and absorption properties of stochastic equations with Hölder diffusion coefficients, Touboul J. and Wainrib G., Physica D: Nonlinear Phenomena, Jul. 2015. (PDF)
  49. [Oyallon and Mallat, 2015] Deep Roto-Translation Scattering for Object Classification, Oyallon E. and Mallat S., Proceedings in IEEE CVPR 2015 conference, 2015. (PDF) (Code)
  50. [Mallat and Waldspurger, 2015] Phase retrieval for the Cauchy wavelet transform, Mallat S. and Waldspurger I., Journal of Fourier Analysis and Applications, 2014. (PDF)
  51. [d'Aspremont et al., 2015] Phase Recovery, MaxCut and Complex Semidefinite Programming, d'Aspremont A., Mallat S., Waldspurger I., Mathematical Programming, 2015. (PDF)
  52. [Hirn et al., 2015] Quantum Energy Regression using Scattering Transforms, Hirn M., Poilvert N., Mallat S., arXiv preprint arXiv:1502.02077, 2015. (PDF)
  53. [Balelli et al., 2015] Branching random walks on binary strings and application to adaptative immunity, Balelli I., Milišić V., Wainrib G., arXiv preprint arXiv:1501.07806, 2015. (PDF)
  54. 2014

  55. [Oyallon et al., 2014] Generic Deep Networks with wavelet Scattering, Oyallon, E., Mallat, S. and Sifre, L., ICLR workshop, 2014. (PDF)
  56. [Chen et al., 2014] Unsupervised Deep Haar Scattering on Graphs, Chen X., Cheng X., Mallat S., Conference on Neural Information Processing Systems (NIPS), Montreal, Quebec, Canada, Dec. 2014. (PDF) (Code)
  57. [Sifre, 2014] Rigid-Motion Scattering for Image Classification, Sifre L., Ph.D. thesis, École polytechnique, Palaiseau, France, Oct. 2014. (PDF)
  58. [Wolf et al., 2014] Audio Source Separation with Time-Frequency Velocities, Wolf G., Mallat S., Shamma S., Proceedings of 2014 IEEE MLSP Workshop, Sept. 2014. (PDF)
  59. [Marini et al., 2014] Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes, Galtier M., Marini C., Wainrib G., Jaeger H., Neural Networks, Aug. 2014. (PDF)
  60. [Sifre and Mallat, 2014] Rigid-Motion Scattering for Texture Classification, Sifre L. and Mallat S., submitted to International Journal of Computer Vision, 2014. (PDF)
  61. [Talmon et al., 2014] Manifold Learning for Latent Variable Inference in Dynamical Systems, Talmon R., Mallat S., Zaveri H., Coifman R. R., Technical Report, 2014. (PDF)
  62. [Chudacek et al., 2014] Low Dimensional Manifold Embedding For Scattering Coefficients Of Intrapartum Fetale Heart Rate Variability, Chudacek V., Talmon R., Anden J., Mallat S., Coifman R. R., Abry P., Doret M., 2014 Internat. IEEE Conf. in Medicine and Biology , EMBC'14, 2014. (PDF)
  63. [Allez et al., 2014] Index Distribution of the Ginibre Ensemble, Allez R., Touboul J., Wainrib G., Journal of Physics A: Mathematical and Theoretical, Jan. 2014. (PDF)
  64. 2013

  65. [Bruna and Mallat, 2013a] Scattering transform for image classification:
    Invariant Scattering Convolution Network, Bruna J. and Mallat S., IEEE Trans. on PAMI, vol. 35, no. 8, pp. 1872-1886, Aug. 2013. (PDF)
  66. [Sifre and Mallat, 2013] Affine invariant scattering for texture classification (8 pages):
    Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination, Sifre L. and Mallat S., Proceedings in IEEE CVPR 2013 conference, 2013. (PDF) (Code)
  67. [Bruna et al., 2013] Intermittent Process Analysis with Scattering Moments, Bruna J., Mallat S., Bacry E. and Muzy J.-F., arXiv preprint arXiv:1311.4104, 2013. (PDF)
  68. [Bruna and Mallat, 2013b] Audio texture synthesis with scattering moments, Bruna J. and Mallat S., arXiv preprint arXiv:1311.0407, 2013. (PDF)
  69. [Hammari et al., 2013] Wavelet methods for shape perception in electro-sensing, Hammari H., Mallat S., Waldspurger I., Wang H., arXiv preprint arXiv:1310.2842, 2013. (PDF)
  70. [Fogel et al., 2013] Phase retrieval for imaging problems, Fogel F., Waldspurger I., d'Aspremont A., arXiv preprint arXiv:1304.7735, 2013. (PDF)
  71. 2012

  72. [Andén and Mallat, 2011b] Audio scattering transform, scattering of parametrized models, transposition invariance, and classification results on musical genre identification and phone classification (31 pages):
    Deep Scattering Spectrum, Andén J. and Mallat. S., Submitted to IEEE Transactions on Signal Processing, 2011. (PDF)
  73. [Mallat, 2012] Mathematical introduction of scattering operators for translation and rotation invariant representations:
    Group Invariant Scattering, Mallat S., Communications in Pure and Applied Mathematics, vol. 65, no. 10, pp. 1331-1398, Oct. 2012. (PDF)
  74. [Sifre and Mallat, 2012] Scattering along spatial and angular variable for rotation invariance (6 pages):
    Combined Scattering for Rotation Invariant Texture Analysis, Sifre L. and Mallat S., Proceedings of the ESANN 2012 conference, Apr. 2012. (PDF)
  75. [Andén and Mallat, 2012] Modulated source-filter models and their representation in the scattering transform (6 pages):
    Scattering Representation of Modulated Sounds, Andén J. and Mallat S., Proceedings of the DAFx 2012 conference, 2012. (PDF)
  76. [Bruna, 2012] PhD thesis with extensive scattering review, new mathematical properties, applications on pattern and texture classification, and multifractal scattering (200 pages):
    Scattering Representations for Recognition, Bruna J., Ph.D. thesis, École Polytechnique, Palaiseau, France, Nov. 2012. (PDF)
  77. 2011

  78. [Bruna and Mallat, 2011] Classification with Scattering Operators, Bruna J. and Mallat S., Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pp. 1561-1566, 2011.
  79. [Andén and Mallat, 2011a] Scattering transform applied to audio signals and musical classification (6 pages):
    Multiscale Scattering for Audio Classification, Andén J. and Mallat S., Proceedings of the ISMIR 2011 conference, pp. 657-662, 2011. (PDF)
  80. 2010

  81. [Mallat, 2010] Recursive interferometric Representations, Mallat S., 18th European Signal Processing Conference (EUSIPCO-2010) Aalborg, Denmark, August 23-27, 2010. (PDF)