Biomedical Imaging Group

École polytechnique fédérale de Lausanne

EPFL STI IMT LIB

BM 4138

Station 17

CH-1015, Lausanne

Switzerland

22 June 2013: Our papers "Consistent Discretization of Linear Inverse Problems using Sparse Stochastic Processes" and "Sparse Image Deconvolution with Message Passing" will be presented at SPARS 2013 on July 8 and 11, respectively.

26 May 2013: Unfortunately, I won't be able to attend ICASSP 2013 due to delays in issuance of the Canadian visa.

15 April 2013: The paper "MAP Estimators for Self-Similar Sparse Stochastic Models" was accepted to SAMPTA 2013. It was co-authored with Emrah Bostan, Julien Fageot, and Prof. Michael Unser.

I am a PhD student in Biomedical Imaging Group (BIG) at EPFL. My supervisor is Prof. Michael Unser. I am working on development of models and algorithms for solving inverse problems.

Currently, I am visiting Information Systems Laboratory (ISL) at Stanford University, where my supervisor is Prof. Andrea Montanari. I am working on statistical inference on random graphs.

Before starting my PhD, I was a visiting student with the Research Lab of Electronics at MIT. I received my MSc and BSc degrees in 2011 and 2008, respectively, from the communication systems department of EPFL. In 2009, I worked as an intern Microsoft in the Unified Communication Group, where I worked on real-time communication platform Microsoft Lync. In 2008, I worked as a research intern in the Signal and Information processing unit of the Telecommunication Research Center in Vienna, Austria.

My full CV can be found [here]. For my LinkedIn go here . For my Google Scholar profile go [here].

I develop statistical models and algorithms for the reconstruction of biomedical images from highly undersampled or distorted measurements. Such problems are common in various image acquisition modalities such as magnitic resonance imaging (MRI), bio-microscopy, astronomy, etc.

I am interested in the development of iterative algorithms that allow to perform inference on large dimensional data in an efficient way. In particular, message-passing algorithms on graphical models are of particularly high interest to me.

The full list of my publications is available on the right.

- U. S. Kamilov, S. Rangan, A. K. Fletcher, and M. Unser, "Approximate Message Passing with Consistent Parameter Estimation and Applications to Sparse Learning," available as arXiv:1207.3859 [cs.IT]. [arXiv] [gamp]
- E. Bostan, U. S. Kamilov, M. Nilchian, and M. Unser, "Sparse Stochastic Processes and Discretization of Linear Inverse Problems," IEEE Trans. Image Process., vol. 22, no. 7, July 2013. [link] [arXiv]
- A. Kazerouni, U. S. Kamilov, E. Bostan, and M. Unser, "Bayesian Denoising: From MAP to MMSE Using Consistent Cycle Spinning," IEEE Signal Process. Letters, vol. 20, no. 3, March 2013. [link] [supplement] [code]
- A. Amini, U. S. Kamilov, E. Bostan, and M. Unser, "Bayesian Estimation for Continuous-Time Sparse Stochastic Processes," IEEE Trans. Signal Process., vol. 61, no. 4, pp. 907-920, February 2013. [link] [code]
- U. S. Kamilov, P. Pad, A. Amini, and M. Unser, "MMSE Estimation of Sparse Lévy Processes," IEEE Trans. Signal Process., vol. 61, no. 1, pp. 137-147, January 2013. [link] [code]
- U. S. Kamilov, V. K. Goyal, and S. Rangan, "Message-Passing De-Quantization with Applications to Compressed Sensing," IEEE Trans. Signal Process., vol. 60, no. 12, pp. 6270-6281, December 2012. [link] [arXiv] [gamp]
- U. S. Kamilov, A. Bourquard, A. Amini, and M. Unser, "One-Bit Measurements with Adaptive Thresholds," IEEE Signal Process. Letters, vol. 19, no. 10, pp. 607-610, October 2012. [link] [gamp]
- U. S. Kamilov, E. Bostan, and M. Unser, "Wavelet Shrinkage with Consistent Cycle Spinning Generalizes Total Variation Denoising," IEEE Signal Process. Letters, vol. 19, no. 4, pp. 187-190, April 2012. [link] [supplement] [code]

- U. S. Kamilov, A. Bourquard, and M. Unser, "Sparse Image Deconvolution with Message Passing," Proc. 5th Workshop on Signal Process. with Adaptive Sparse Structured Representations (SPARS 2013) (Lausanne, Switzerland, July 8-11), accepted. [link]
- E. Bostan, U. S. Kamilov, M. Nilchian, and M. Unser, "Consistent Discretization of Linear Inverse Problems using Sparse Stochastic Processes," Proc. 5th Workshop on Signal Process. with Adaptive Sparse Structured Representations (SPARS 2013) (Lausanne, Switzerland, July 8-11), accepted. [link]
- E. Bostan, J. Fageot, U. S. Kamilov, and M. Unser, "MAP Estimators for Self-Similar Sparse Stochastic Models," Proc. 10th International Conference on Sampling Theory and Applications (SAMPTA 2013) (Bremen, Germany, July 1-5), accepted.
- U. S. Kamilov, A. Bourquard, E. Bostan, and M. Unser, "Autocalibrated Signal Reconstruction from Linear Measurements using Adaptive GAMP," Proc. IEEE. Int. Conf. Acoustics, Speech and Signal Process. 2013 (Vancouver, Canada, May 26-31), pp. 5925-5928. [link]
- B. Tekin, U. S. Kamilov, E. Bostan, and M. Unser, "Benefits of Consistency in Image Denoising with Steerable Wavelets," Proc. IEEE Int. Conf. Acoustics, Speech and Signal Process. 2013 (Vancouver, Canada, May 26-31), pp. 1355-1358. [link]
- U. S. Kamilov, S. Rangan, A. K. Fletcher, and M. Unser, "Approximate Message Passing with Consistent Parameter Estimation and Applications to Sparse Learning," Proc. 23rd Ann. Conf. Neural Information Processing Systems (NIPS 2012) (Lake Tahoe, Nevada, December 3-6), pp. 2447-2455.
[link]
- Acceptance rate: 370/1467 = 25%.

- A. Amini, U. S. Kamilov, and M. Unser, "The Analog Formulation of Sparsity Implies Infinite Divisibility and Rules Out Bernoulli-Gaussian Priors," Proc. IEEE Information Theory Workshop 2012 (Lausanne, Switzerland, September 3-7), pp. 687-691. [link]
- E. Bostan, U. S. Kamilov, and M. Unser, "Reconstruction of Biomedical Images and Sparse Stochastic Modeling," Proc. Int. Symp. Biomedical Imaging 2012 (Barcelona, Spain, May 2-5), pp. 880-883. [link]
- U. S. Kamilov, A. Amini, and M. Unser, "MMSE Denoising of Sparse Lévy Processes via Message Passing," Proc. IEEE Int. Conf. Acoustics, Speech and Signal Process. 2012 (Kyoto, Japan, March 25-30), pp. 3637-3640. [link]
- U. S. Kamilov, E. Bostan, and M. Unser, "Generalized Total Variation Denoising via Augmented Lagrangian Cycle Spinning with Haar Wavelets," Proc. IEEE Int. Conf. Acoustics, Speech and Signal Process. 2012 (Kyoto, Japan, March 25-30), pp. 909-912. [link]
- A. Amini, U. S. Kamilov, and M. Unser, "Bayesian Denoising of Generalized Poisson Processes with Finite Rate of Innovation," Proc. IEEE Int. Conf. Acoustics, Speech and Signal Process. 2012 (Kyoto, Japan, March 25-30), pp. 3629-3632. [link]
- U. S. Kamilov, V. K. Goyal, and S. Rangan, "Generalized Approximate Message Passing Estimation from Quantized Samples," Proc. 4th Int. Workshop on Computational Advances in Multi-Sensor Adaptive Process. (CAMSAP 2011) (San Juan, Puerto Rico, December 13-16), pp. 401-404.
[link]
- Student paper award finalist.

- U. S. Kamilov, V. K. Goyal, and S. Rangan, "Message-Passing Estimation from Quantized Samples," Proc. 4th Workshop on Signal Process. with Adaptive Sparse Structured Representations (SPARS 2011) (Edinburgh, United Kingdom, June 27-June 30), p. 58. [link]
- U. S. Kamilov, V. K. Goyal, and S. Rangan, "Optimal Quantization for Compressive Sensing under Message Passing Reconstruction," Proc. 2011 IEEE Int. Symp. Inform. Theory (Saint-Petersburg, Russia, July 31-August 5), pp. 390-394. [link]

- U. S. Kamilov, "Optimal Quantization for Compressive Sensing with Relaxed Belief Propagation," Master's Thesis EPFL/MIT, April 2011. [link]