Joakim Andén

I am an associate professor at the Division of Probability, Mathematical Physics and Statistics at the Department of Mathematics in KTH Royal Institute of Technology. My research focuses on signal processing, statistical data analysis, and machine learning. More generally, I'm interested in how to identify and extract discriminative information from signals while remaining invariant to less relevant sources of variability such as translation, frequency-shifting and additive noise. Specific applications include classifying heterogenous molecular structure in cryo-electron microscopy, audio classification and for speech and music, as well as classification of biomedical signals more generally.

Publications

cuFINUFFT: a load-balanced GPU library for general-purpose nonuniform FFTs
Y. Shih, G. Wright, J. Andén, J. Blaschke, A. H. Barnett. Accepted at IPDPS. (Best Paper Award) (arxiv)

Time–frequency scattering accurately models auditory similarities between instrumental playing techniques
V. Lostanlen, C. El-Hajj, M. Rossignol, G. Lafay, J. Andén, M. Lagrange. EURASIP Journal on Audio, Speech, and Music Processing, vol. 2021, no. 1, January, 2021. (doi) (pdf)

Arrhythmia classification of 12-lead electrocardiograms by hybrid scattering-LSTM networks P. A. Warrick, V. Lostanlen, M. Eickenberg, J. Andén, M. N. Homsi. 2020 Computing in Cardiology. pp. 1–4, 2020. (doi)

Multitaper estimation on arbitrary domains
J. Andén, J. L. Romero. SIAM Journal on Imaging Sciences, vol. 13, no. 3, pp. 1565–1594, September, 2020. (doi) (pdf)

Reducing bias and variance for CTF estimation in single-particle cryo-EM
A. Heimowitz, J. Andén, and A. Singer. Ultramicroscopy, vol. 212, May 2020. (doi) (pdf)

Hyper-molecules: On the representation and recovery of dynamical structures for applications in flexible macro-molecules in cryo-EM
R. R. Lederman, J. Andén, and A. Singer. Inverse Problems, vol. 36, no. 4, 4 Mar. 2020. (doi) (pdf)

Cryo-EM reconstruction of continuous heterogeneity by Laplacian spectral volumes
A. Moscovich, A. Halevi, J. Andén, and A. Singer. Inverse Problems, vol. 36, no. 2, 28 Jan. 2020. (doi) (pdf)

Factorization of the translation kernel for fast rigid image alignment
A. Rangan, M. Spivak, J. Andén, and A. Barnett. Inverse Problems, vol. 36, no. 2, 28 Jan. 2020. (doi) (pdf)

Kymatio: Scattering transforms in Python
M. Andreux, T. Angles, G. Exarchakis, R. Leonarduzzi, G. Rochette, L. Thiry, J. Zarka, S. Mallat, J. Andén, E. Belilovsky, J. Bruna, V. Lostanlen, M. Chaudhary, M. J. Hirn, E. Oyallon, S. Zhang, C. Cella, and M. Eickenberg. Journal of Machine Learning Research, vol. 21, pp. 1–6, January 2020. (abstract) (pdf)

Joint time–frequency scattering
J. Andén, V. Lostanlen, and S. Mallat. IEEE Transactions on Signal Processing, vol. 67, no. 14, pp. 3704–3718, July 16 2019. (doi) (pdf)

Fourier at the heart of computer music: From harmonic sounds to texture
V. Lostanlen, J. Andén, and M. Lagrange. Comptes Rendus Physique, vol. 20, no. 5, pp. 461–473, July 1 2019. (doi)

Relevance-based quantization of scattering features for unsupervised mining of environmental audio
V. Lostanlen, G. Lafay, J. Andén, and M. Lagrange. EURASIP Journal on Audio, Speech, and Music Processing, vol. 1, no. 15, 29 Sept. 2018. (doi)

APPLE picker: Automatic particle picking, a low-effort cryo-EM framework
A. Heimowitz, J. Andén, and A. Singer. Journal of Structural Biology, vol. 204, no. 2, pp. 215–227, November, 2018. (doi)

Extended playing techniques: The next milestone in musical instrument recognition
V. Lostanlen, J. Andén, and M. Lagrange. International Conference on Digital Libraries for Musicology, pp. 1–10, September 2018. (doi)

Structural variability from noisy tomographic projections
J. Andén and A. Singer. SIAM Journal on Imaging Sciences, vol. 11, no. 2, pp. 1441–1492, 31 May 2018. (doi)

Synthesizing developmental trajectories
P. Villoutreix, J. Andén, B. Lim, H. Lu, I. G. Kevrekidis, A. Singer, and S. Y. Shvartsman. PLOS Computational Biology, vol. 13, no. 9, e1005742. 2017. (doi) (pdf)

Factor analysis for spectral estimation
J. Andén and A. Singer. International Conference on Sampling Theory and Applications (SampTA), 3–7 July 2017. (doi)

Joint Time–Frequency Scattering for Audio Classification
J. Andén, V. Lostanlen, and S. Mallat. IEEE International Workshop on Machine Learning for Signal Processing, 17–20 Sept. 2015. (Best Paper Award, 2nd Place) (doi) (pdf)

Covariance Estimation Using Conjugate Gradient for 3D Classification in Cryo-EM
J. Andén, E. Katsevich, and A. Singer. IEEE International Symposium on Biomedical Imaging (ISBI), pp. 200–204, 2015. (doi) (pdf)

Low dimensional manifold embedding for scattering coefficients of intrapartum fetal heart rate variability
V. Chudáček, R. Talmon, J. Andén, S. Mallat, R. R. Coifman, P. Abry, and M. Doret. International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 6374–6376. 26–30 August 2014. (doi)

Deep Scattering Spectrum
J. Andén and S. Mallat. IEEE Transactions on Signal Processing, vol. 62, no. 16, pp. 4114–4128, Aug. 15 2014. (doi) (pdf)

Scattering transform for intrapartum fetal heart rate variability fractal analysis: A case-control study
V. Chudáček, J. Andén, S. Mallat, P. Abry, and M. Doret. IEEE Transactions on Biomedical Engineering, vol. 61, no. 4, pp. 1100–1108. 2014. (doi)

Scattering transform for intrapartum fetal heart rate characterization and acidosis detection
V. Chudáček, J. Andén, S. Mallat, P. Abry, and M. Doret. International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 2898–2901, 3–7 July, 2013. (doi) (pdf)

Representing environmental sounds using the separable scattering transform
C. Baugé, M. Lagrange, J. Andén, and S. Mallat. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 866–8671, 26–31 May 2013. (doi) (pdf)

Scattering representation of modulated sounds
J. Andén and S. Mallat. International Conference on Digital Audio Effects. 2012. (Best Paper Award, 1st Place) (pdf)

Multiscale scattering for audio classification
J. Andén and S. Mallat. International Symposium on Music Information Retrieval (ISMIR), pp. 657–662. 24–28 Oct. 2011. (pdf)

Software

ASPIRE

ASPIRE is a framework for developing computational algorithms for cryo-electron microscopy (cryo-EM) tasks, such as particle picking, CTF estimation, Wiener filter denoising, class averaging, ab initio reconstruction, and 3D covariance analysis, among other things. (website) (github)

Kymatio

The Kymatio toolbox implements 1D, 2D, and 3D wavelet scattering transforms in Python. It supports a variety of frontends, including TensorFlow/Keras, PyTorch, and NumPy. (website) (github)

Finufft

The Flatiron Institute Non-Uniform Fast Fourier Transform (FINUFFT) package provides an efficient implementation of the non-uniform fast Fourier transform on the CPU. C, C++, Fortran, Python, and Matlab interfaces allow users to incorporate the package in a variety of target applications. (docs) (github)

cuFinufft

cuFinufft provides a GPU implementation of the non-uniform fast Fourier transform through CUDA. It currently supports interfaces in C, C++, and Python. (github)

ScatNet

Together with Laurent Sifre, I have developed the ScatNet toolbox for calculating scattering transforms in MATLAB, complete with visualization and classification pipelines (affine space models and support vector classifiers) for duplicating the results of the above papers. Older MATLAB toolboxes scattering computation and affine space classifiers are available, but are no longer supported.

libsvm-compact

To speed up computation and reduce memory size, I have introduced some changes to the popular LIBSVM library for support vector machine (SVM) training. The libsvm-compact package extends the library to handle precomputed Gaussian kernels, 32-bit precision, triangular kernels, and multi-core training as well as in-place routines for MATLAB.