Publications
Pre-Prints
Selected Journal Papers
J. Teneggi, P. H. Yi, J. Sulam. Examination-level supervision for deep learning–based intracranial hemorrhage detection at head CT. Radiology: Artificial Intelligence (2023).
J. Teneggi, B. Bharti, Y. Romano, J. Sulam, SHAP-XRT: The Shapley Value Meets Conditional Independence Testing, Transactions of Machine Learning Research, 2023.
R. Muthukumar, J. Sulam, Adversarial robustness of sparse local Lipschitz predictors, SIAM Mathematics of Data Science, 2023.
Y.K.T. Xu, A. R. Graves, G.I. Coste, R.L. Huganir, D.E. Bergles, A.S. Charles, J. Sulam, Cross-modality supervised image restoration enables nanoscale tracking of synaptic plasticity in living mice, Nature Methods, 2023.
A. Pal, J. Sulam, Understanding Noise-Augmented Training for Randomized Smoothing, Transactions of Machine Learning Research (TMLR), 2023.
Z. Fang, K.W. Lai, P. van Zijl, X. Li, J. Sulam, DeepSTI: Towards Tensor Reconstruction using Fewer Orientations in Susceptibility Tensor Imaging, Medical Imaging Analysis, 2023.
S. P. Garin, V. S. Parekh, J. Sulam, P. H. Yi, Medical imaging data science competitions should report dataset demographics and evaluate for bias, Nature Medicine, 2023.
Z. Wang, C. Saoud, S. Wangsiricharoen, A. W. James, A. S. Popel, J. Sulam, Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images, in IEEE Transactions on Medical Imaging, 2022, doi: 10.1109/TMI.2022.3202759.
J. Teneggi, A. Luster and J. Sulam, Fast Hierarchical Games for Image Explanations, EEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022, doi: 10.1109/TPAMI.2022.3189849.
J. Sulam, C. You, Z. Zhu, Recovery and Generalization in Over-Realized Dictionary Learning, Journal of Machine Learning Research (JMLR), 23 (135), 2022.
J. A. R., J. Sulam, J. J. Gray, Antibody structure prediction using interpretable deep learning, Patterns 3.2:100406, 2022.
Y. K. T. Xu, C.L. Call, J. Sulam, D.E. Bergles, Automated in vivo tracking of cortical oligodendrocytes, Front. Cell. Neurosci., 2021
I. Rey Otero, J. Sulam, M. Elad, Variations on the Convolutional Sparse Coding Model, in IEEE Transactions on Signal Processing, 2020.
Y. Romano, A. Aberdam, J. Sulam, M. Elad. Adversarial Noise Attacks of Deep Learning Architectures – Stability Analysis via Sparse Modeled Signals. Journal of Mathematical Imaging and Vision, 2019.
D. Simon, J. Sulam, Y. Romano, Y. Lue, M. Elad. Improving Pursuit Algorithms Using Stochastic Resonance. IEEE Transactions on Signal Processing, 2019
J. Sulam, A. Aberdam, A. Beck, M. Elad, On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019.
A. Aberdam, J. Sulam, M. Elad. Multi Layer Sparse Coding: the Holistic Way. SIAM Journal on Mathematics of Data Science, 1:1, 46-77, 2019
J. Sulam, V. Papyan, Y. Romano, M. Elad. Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning, in IEEE Transactions on Signal Processing, vol. 66, no. 15, pp. 4090-4104, Aug.1, 1 2018.
V. Papyan, Y. Romano, J. Sulam and M. Elad, Theoretical Foundations of Deep Learning via Sparse Representations, in IEEE Signal Processing Magazine, vol. 35, no. 4, pp. 72-89, July 2018.
V. Papyan*, J. Sulam*, M. Elad. Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding. IEEE Transactions on Signal Processing, 65(21), 5687-5701, 2017. This paper was originally presented (as as pre-print) in a two-parts form. The first one focuses on the noiseless (i.e., ideal) case and it introduces the main mathematical tools employed in our work. The second part addresses the generalization of theoretical claims for approximation algorithms and noisy data. *Contributed Equally.
J. Sulam, M. Elad. Large Inpainting of Face Images with Trainlets. IEEE Signal Processing Letters, Is. 99, Oct. 2016. Supplementary Material. Code and Model
J. Sulam, Y. Romano, R. Talmon. Dynamical system classification with diffusion embedding for ECG-based person identification. Signal Processing. Vol. 130, January 2017, Pages 403–411.
J. Sulam , B. Ophir, M. Zibulevsky and M. Elad. Trainlets: Dictionary Learning in High Dimensions. IEEE Transactions on Signal Processing, 2016, V. 64, 12, pg: 3180 – 3193. CODE AVAILABLE.
Selected Conference Papers
Z Fang, S Buchanan, J Sulam, What's in a Prior? Learned Proximal Networks for Inverse Problems, ICLR (to appear) 2024.
B. Bharti, P.H. Yi, J. Sulam, Estimating and Controlling for Fairness via Sensitive Attribute Predictors, Neurips 2023.
A Pal, J Sulam, R Vidal, Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness, Neurips 2023.
Z Fang, HG Shin, P Zijl, X Li, J Sulam, WaveSep: A Flexible Wavelet-Based Approach for Source Separation in Susceptibility Imaging, International Workshop on Machine Learning in Clinical Neuroimaging, 2023.
J. Teneggi, M. Tivnan, J.W. Stayman, J. Sulam, How To Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control, ICML 2023.
R. Muthukumar, J. Sulam, Sparsity-aware generalization theory for deep neural networks, COLT 2023.
J. Agterberg and J. Sulam. Entrywise Recovery Guarantees for Sparse PCA via Sparsistent Algorithms, AISTATS, 2022
J.A. Ruffolo, J.J. Gray, J, Sulam, Deciphering antibody affinity maturation with language models and weakly supervised learning, Machine Learning for Structural Biology Workshop, NeurIPS 2021.
Z Zhu, T Ding, J Zhou, X Li, C You, J Sulam, Q Qu, A Geometric Analysis of Neural Collapse with Unconstrained Features, Neurips (Spotlight) 2021
J. Sulam, R. Muthukumar, R. Arora. Adversarial Robustness of Supervised Sparse Coding, Neurips 2020.
H Cherkaoui, J Sulam, T Moreau. Learning to solve TV regularized problems with unrolled algorithms, Neurips 2020.
G França, J Sulam, DP Robinson, R Vidal, Conformal Symplectic and Relativistic Optimization, Neurips 2020.
K.W. Lai, M. Aggarwal, P. van Zijl, X. Li, J. Sulam, Learned Proximal Networks for Quantitative Susceptibility Mapping. to appear in MICCAI 2020.
E. Zisselman, J. Sulam, M. Elad, A Local Block Coordinate Descent Algorithm for the CSC Model, CVPR 2019.
J. Sulam, V. Papyan, Y. Romano, M. Elad. Projecting onto the Multi-Layer Convolutional Sparse Coding Model. ICASSP 2018 (oral presentation @ Special Session on Learning Signal Representation using Deep Learning).
J. Sulam, R. Ben-Ari, P. Kisilev. Maximizing AUC with Deep Learning for Classification of Imbalanced Mammogram Datasets. Eurographics Workshop on Visual Computing for Biology and Medicine 2017.
V. Papyan, Y. Romano, J. Sulam, M. Elad. Convolutional Dictionary Learning via Local Processing. Accepted to ICCV 2017.
J. Sulam* , Y. Romano* and M. Elad. Gaussian Mixture Diffusion. 2016 ICSEE International Conference on the Science of Electrical Engineering. Nov. 2016.* Contributed Equally.
J. Turek, J. Sulam , I. Yavne and M. Elad. Fusion of Ultrasound Harmonic Imaging with Clutter Removal Using Sparse Signal Separation. IEEE ICASSP, Brisbane, Australia, April 19-24, 2015 (oral presentation).
J. Sulam and M. Elad. Expected Patch Log Likelihood with a Sparse Prior. EMMCVPR, Springer, January 2015 (oral presentation). CODE AVAILABLE.
J. Sulam , B. Ophir, M. Elad. Image Denoising Through Multi-Scale Learnt Dictionaries. IEEE International Conference on Image Processing (ICIP), October 27-30, 2014 (oral presentation). CODE AVAILABLE.
J. Sulam , G. Schlotthauer, M.E. Torres. Nonlinear slight parameter changes detection: a forecasting approach. 41th Argentinean Workshop on Informatics JAIIO. August, 2012. p. 168-179, ISSN 1850-2806.
Thesis
J. Sulam. From Local to Global Sparse Modeling. Computer Science Department, Technion - Israel Institute of Technology. 2018.