Amin Karbasi

Latest news

Hello all !

I am now an assistant professor at Yale School of Engineering. You can contact me through the following link:

http://seas.yale.edu/faculty-research/faculty-directory/amin-karbasi

 

 

I have recently defended my PhD thesis, entitle “Graph-Based Information Processing: Scaling Laws and Applications”, in the School of Computer and Communication Sciences at EPFL, where I have studied under the direction of Professor Rudiger Urbanke and Professor Martin Vetterli.

I have been working on problems in the intersection of information theory, machine learning, and high-dimensional Statistics. My work on the analysis of graphical models and their applications in biomedical systems and large scale networks has received wide recognition. In particular, for my work on Calibration in Circular Ultrasound Tomography Devices, I won the best student paper award in the 36th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011). I was also the recipient of the best student paper award from ACM/SIGMETRICS 2010 for my work on Distributed Sensor Localization From Local Connectivity. Prior to this, my work on network tomography, entitled Graph-Constrained Group Testing, was nominated for the best student paper award in the IEEE International Symposium on Information Theory (ISIT 2010).

I have enormously benefited from conducting research in cooperation with research facilities. More specifically, I did internships at various industrial research labs, including MSR-INRIA Joint Center (Paris, France), Nokia Research Center (Lausanne, Switzerland), Microsoft Research Center (Cambridge, UK), Technicolor Research Lab (Paris, France), Logitech Research Center (Lausanne, Switzerland), NEC Media and Information Research Labs (Tokyo, Japan), and IBM Research Center (Zurich, Switzerland). I worked on problems related to active learning, reliable crowdsourcing,  job  scheduling for cloud computing, interactive content search, video compression over wireless channels, array signal processing, and coding for large storage systems. One of the things I enjoy most is teamwork. I was the team leader of the World Champion Team in the International RoboCup Competition in the field of rescue robots, held in Fukuoka-Japan in 2002. Our team was comprised of 14 undergraduate students from different backgrounds, ranging from electrical engineering and computer science to mechanical engineering.

For any further information, you can look at my resume , and research statement.

Main Publications

[38]

Learning Neural Connectivity from Firing Activity: Scalable Algorithms with Provable Guarantees

A. Karbasi; A. H. Salavati; M. Vetterli

Journal of computational neuroscience. 2018.

DOI : 10.1007/s10827-018-0678-8.

[37]

Learning Network Structures from Firing Patterns

A. Karbasi; A. H. Salavati; M. Vetterli

2016. International Conference on Acoustics, Speech and Signal Processing , Shanghai, China , March 20-25, 2016. p. 699-703.

[36]

Asynchronous Decoding of LDPC Codes over BEC

S. Haghighatshoar; A. Karbasi; A. H. Salavati

2015. IEEE International Symposium on Information Theory (ISIT) , Hong Kong , June 14-19, 2015.

[35]

Near-Optimally Teaching the Crowd to Classify 

A. Singla; I. Bogunovic; G. Bartok; A. Karbasi; A. Krause

2014. The 31st International Conference on Machine Learning (ICML) , Beijing , June 21-26, 2014. p. 154–162.

[34]

Noise facilitation in associative memories of exponential capacity

A. Karbasi; A. H. Salavati; L. R. Varshney; A. Shokrollahi

Journal of Neural Computation. 2014.

DOI : 10.1162/NECO_a_00655.

[33]

On Actively Teaching the Crowd to Classify

A. Singla; I. Bogunovic; G. Bartok; A. Karbasi; A. Krause

NIPS Workshop on Data Driven Education.

[32]

Coupled neural associative memories

A. Karbasi; A. H. Salavati; A. Shokrollahi

2013. IEEE Information Theory Workshop (ITW) , Seville, Spain , September 9-13, 2013. p. 1-5.

[31]

Noise-enhanced associative memories

A. Karbasi; A. H. Salavati; L. R. Varshney; A. Shokrollahi

2013. Advances in Neural Information Processing Systems , Lake Tahoe, Nevada, United States , December 5-10,2013. p. 1682-1690.

[30]

Iterative Learning and Denoising in Convolutional Neural Associative Memories

A. Karbasi; A. H. Salavati; A. Shokrollahi

2013. 30th International Conference on Machine Learning (ICML) , Atlanta, USA , June 16-21, 2013. p. 445-453.

[29]

Constrained Binary Identification Problem

A. Karbasi; M. Zadimoghaddam

2013. 30th Symposium on Theoretical Aspects of Computer Science , Kiel, Germany .

[28]

Robust Localization from Incomplete Local Information

A. Karbasi; S. Oh

IEEE/ACM Transaction on Networking. 2013.

DOI : 10.1109/Tnet.2012.2220378.

[27]

Calibration Using Matrix Completion with Application to Ultrasound Tomography

R. Parhizkar; A. Karbasi; S. Oh; M. Vetterli

IEEE Transactions on Signal Processing. 2013.

DOI : 10.1109/Tsp.2013.2272925.

[26]

Hot or Not: Interactive Content Search Using Comparisons

A. Karbasi; S. Ioannidis; L. Massoulie

2012. Information Theory and Applications Workshop (ITA) , San Diego, USA .

[25]

Comparison-Based Learning with Rank Nets

A. Karbasi; S. ioannidis

2012. 29th International Conference on Machine Learning (ICML) , Edinburgh, Scotland , June 26- July 1.

[24]

Sequential Group Testing with Graph Constraints

A. Karbasi; M. Zadimoghaddam

2012. IEEE Information Theory Workshop (ITW) , Lausanne, Switzerland , 2-7, 2012.

[23]

Graph-Based Information Processing

A. Karbasi / R. Urbanke; M. Vetterli (Dir.)

Lausanne, EPFL, 2012.

DOI : 10.5075/epfl-thesis-5524.

[22]

Multi-Level Error-Resilient Neural Networks

A. H. Salavati; A. Karbasi

2012. IEEE International Symposium on Information Theory (ISIT 2012) , Boston, Massachusetts, USA , July 1-6, 2012. p. 1064-1068.

[21]

Low-rank Matrix Approximation Using Point-wise Operators

A. Amini; A. Karbasi; F. Marvasti

IEEE Transactions on Information Theory. 2012.

DOI : 10.1109/TIT.2011.2167714.

[20]

Graph-Constrained Group Testing

M. Cheraghchi; A. Karbasi; S. Mohajerzefreh; V. Saligrama

IEEE Transactions on Information Theory. 2012.

DOI : 10.1109/TIT.2011.2169535.

[19]

Content Search Through Comparisons

A. Karbasi; S. Ioannidis; L. Massoulie

2011.

Patent number(s) :
Technicolor
[18]

Greedy Scheduling for Distributed Computing Clusters

A. Karbasi; M. Vojnovic

2011.

Patent number(s) :
Microsoft
[17]

Adaptive Content Search Through Comparisons

A. Karbasi; S. Ioannidis; L. Massoulie

Journal of Machine Learning Research. 2011.

[16]

Compression with Graphical Constraints: An Interactive Browser

A. Karbasi; M. Zadimoghaddam

2011. IEEE International Symposium on Information Theory , Saint-Petersburg, Russia , July 31 - August 5, 2011.

[15]

Content Search Through Comparisons

A. Karbasi; S. Ioannidis; L. Massoulie

2011.

[14]

Content Search Through Comparisons

A. Karbasi; S. Ioannidis; L. Massoulie

2011. 38th International Colloquium on Automata, Languages and Programming (ICALP) , Zurich, Switzerland , July 4-8.

[13]

Calibration in Circular Ultrasound Tomography Devices

R. Parhizkar; A. Karbasi; M. Vetterli

2011. The 36th International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Prague, Czech Republic , May 22-27.

[12]

Group Testing with Probabilistic Tests: Theory, Design and Application

M. Cheraghchi; A. Hormati; A. Karbasi; M. Vetterli

IEEE Transactions on Information Theory. 2011.

DOI : 10.1109/TIT.2011.2148691.

[11]

From Centralized to Distributed Sensor Localization

A. Karbasi

2010. ACM MobiHoc-S3 , Chicago, Illinois, USA , september 20-24, 2010.

[10]

Ultrasound Tomography Calibration Using Structured Matrix Completion

A. Karbasi; S. Oh; R. Parhizkar; M. Vetterli

2010. The 20th International Congress on Acoustics , Sydney, Australia , August 23-28, 2010.

[9]

Graph-Constrained Group Testing

M. Cheraghchi; A. Karbasi; S. Mohajerzefreh; V. Saligrama

2010. IEEE International Symposium on Information Theory (ISIT 2010) , Austin, Texas, USA , June 13-18, 2010.

[8]

Distributed Sensor Network Localization from Local Connectivity: Performance Analysis for the HOP-TERRAIN Algorithm

A. Karbasi; S. Oh

2010. ACM SIGMETRICS 2010 , NEW YORK , JUNE 14-18.

[7]

Sensor Network Localization from Local Connectivity : Performance Analysis for the MDS-MAP Algorithm

S. Oh; A. Karbasi; A. Montanari

2010. 2010 IEEE Information Theory Workshop (ITW 2010) , Cairo , January 6-8.

[6]

Compressed Sensing with Probabilistic Measurements: A Group Testing Solution

M. Cheraghchi; A. Hormati; A. Karbasi; M. Vetterli

2009. 47th Annual Allerton Conference on Communication, Control, and Computing , University of Illinois at Urbana-Champaign , September 30 – October 2.

[5]

Sensor Network Localization from Local Connectivity : Performance Analysis for the MDS-MAP Algorithm

S. Oh; A. Karbasi; A. Montanari

2009.

[4]

Support Recovery in Compressed Sensing: An Estimation Theoretic Approach

A. Karbasi; A. Hormati; S. Mohajer; M. Vetterli

2009. 2009 IEEE International Symposium on Information Theory , Seoul, Korea , June 28-July 3. p. 679-683.

[3]

Support Recovery in Compressed Sensing: An Estimation Theoretic Approach

A. Karbasi; A. Hormati; S. Mohajer; M. Vetterli

2009.

[2]

A New DOA Estimation Method Using a Circular Microphone Array

A. Karbasi; A. Sugiyama

2007. European Signal Processing Conference 2007 , Poznań, Poland , September 3-7.

[1]

A DOA Estimation Method For an Arbitrary Triangular Microphone Arrangement

A. Karbasi; A. Sugiyama

2006. European Signal Processing Conference 2006 , Florence , September 4-8.