Anna Choromanska

Anna Choromanska

Assistant Professor

Electrical and Computer Engineering

Biography

Prof. Anna Choromanska received her Ph.D. degree from the Department of Electrical Engineering at Columbia University in the City of New York in 2014, and a MSc degree with distinctions from the Department of Electronics and Information Technology at Warsaw University of Technology. She did her Post-Doctoral studies in the Computer Science Department at Courant Institute of Mathematical Sciences in NYU. She joined the Department of Electrical and Computer Engineering at NYU Tandon School of Engineering in the Spring 2017 as an Assistant Professor.

Prof. Choromanska's research interests ​focus on machine learning both theoretical and applicable to the variety of real-life phenomena. Currently her main research projects focus on numerical optimization, deep learning, and large data analysis. She collaborates with NVIDIA (New Jersey lab) on the autonomous car driving project. She is also working on learning from datastreams, learning with expert advice, supervised and unsupervised online learning, clustering, and structured prediction. She has also been working on applying machine learning to analyze neural circuits, particularly 3D reconstruction of neurons from confocal microscopy images and classification of neurons.

Prof. Choromanska was a recipient of The Fu Foundation School of Engineering and Applied Science Presidential Fellowship at Columbia University in the City of New York. She co-authored several international conference papers (some granted best paper awards) and refereed journal publications, as well as book chapters. The results of some of her works are used in production by Facebook (training production vision systems and entry to COCO competition) and Baidu. She is also a contributor to the open source fast out-of-core learning system Vowpal Wabbit (aka VW). Prof. Choromanska gave over 50 invited and conference talks and serves as a book editor (MIT Press volume), organizer of top machine learning events (Workshop on Nonconvex Optimization for Machine Learning: Theory and Practice, International Conference on Neural Information Processing Systems, 2016), and a reviewer and area chair for several top machine learning conferences and journals.

Prof. Anna Choromanska is also a pianist who has been playing piano since the age of six and has diplomas of two music schools. She is also an avid salsa dancer performing with Ache Performance Project of Frankie Martinez.

Journal Articles

A. Choromanska, K. Choromanski, G. Jagannathan, C. Monteleoni, Differentially-Private Learning of Low Dimensional Manifolds, Theoretical Computer Science, 2015

A. Choromanska, S-F. Chang, R. Yuste, Automatic Reconstruction of 3D neural morphologies using multi-scale graph-based tracking, Frontiers in Neural Circuits, 6:25, 2012

Other Publications

Conferences:

N. Patel, A. Choromanska, P. Krishnamurthy, F. Khorrami, Sensor Modality Fusion with CNNs for UGV Autonomous Driving in Indoor Environments, in the International Conference on Intelligent Robots and Systems (IROS), 2017

Y. Jernite, A. Choromanska, D. Sontag, Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation, in the International Conference on Machine Learning (ICML), 2017

P. Chaudhari, A. Choromanska, S. Soatto, Y. LeCun, C. Baldassi, C. Borgs, J. Chayes, L. Sagun, R. Zecchina, Entropy-SGD: Biasing Gradient Descent Into Wide Valleys, in the International Conference on Learning Representations (ICLR), 2017. Acceptance Rate [36%]

M. Bojarski, A. Choromanska, K. Choromanski, F. Fagan, C. Gouy-Pailler, A. Morvan, N. Sakr, T. Sarlos, J. Atif, Structured adaptive and random spinners for fast machine learning computations, in the International Conference on Artificial Intelligence and Statistics (AISTATS), 2017

A. Choromanska, K. Choromanski, M. Bojarski, T. Jebara, S. Kumar, Y. LeCun, Binary embeddings with structured hashed projections, in the International Conference on Machine Learning (ICML), 2016. Oral presentation: Acceptance Rate [24.27%]

A. Choromanska, J. Langford, Logarithmic Time Online Multiclass prediction, in the Neural Information Processing Systems Conference (NIPS), 2015. Spotlight talk: Acceptance Rate [3.65%]

S. Zhang, A. Choromanska, Y. LeCun, Deep learning with Elastic Averaging SGD, in the Neural Information Processing Systems Conference (NIPS), 2015. Spotlight talk: Acceptance Rate [3.65%]

A. Choromanska, Y. LeCun, G. Ben Arous, Open Problem: The landscape of the loss surfaces of multilayer networks, in the Conference on Learning Theory (COLT), Open Problems, 2015

A. Choromanska, M. B. Henaff, M. Mathieu, G. Ben Arous, Y. LeCun, The Loss Surfaces of Multilayer Networks, in the International Conference on Artificial Intelligence and Statistics (AISTATS), 2015

A. Choromanska, T. Jebara, H. Kim, M. Mohan, C. Monteleoni, Fast spectral clustering via the Nystrom method, in the International Conference on Algorithmic Learning Theory (ALT), 2013

A. Choromanska, K. Choromanski, G. Jagannathan, C. Monteleoni, Differentially-Private Learning of Low Dimensional Manifolds, in the International Conference on Algorithmic Learning Theory (ALT), 2013

T. Jebara, A. Choromanska, Majorization for CRFs and Latent Likelihoods, in the Neural Information Processing Systems Conference (NIPS), 2012. Spotlight talk: Acceptance Rate [3.58%]. Student Best Paper Award, First Place, on the 7th Annual Machine Learning Symposium, New York Academy of Science, 2012

A. Choromanska, C. Monteleoni, Online clustering with experts, in the International Conference on Artificial Intelligence and Statistics (AISTATS), 2012. Oral presentation: Acceptance Rate [5.97%]. Student Best Paper Award, Third Place, on the 6th Annual Machine Learning Symposium, New York Academy of Science, 2011

 

PhD Thesis:

A. Choromanska, Selected machine learning reductions, PhD Thesis, 2014

 

Workshops:

S. Zhang, A. Choromanska, Y. LeCun, Deep learning with Elastic Averaging SGD (initial results), in the International Conference on Learning Representations (ICLR) Workshop, CoRR, abs/1412.6651v5, 2015

A. Y. Aravkin, A. Choromanska, T. Jebara, D. Kanevsky, Semistochastic quadratic bound methods (initial results), in the International Conference on Learning Representations (ICLR) Workshop, CoRR, abs/1309.1369, 2014

A. Choromanska, A. Agarwal, J. Langford, Extreme Multi Class Classification, in the Neural Information Processing Systems Conference (NIPS) Workshop: eXtreme Classification, 2013

A. Choromanska, D. Kanevsky, T. Jebara, Majorization for Deep Belief Networks, in the Neural Information Processing Systems Conference (NIPS) Workshop: Log-linear models, 2012

A. Choromanska and C. Monteleoni, Online Clustering with Experts (initial results), in the International Conference on Machine Learning (ICML) Workshop: Online Trading of Exploration and Exploitation 2, Journal of Machine Learning Research (JMLR) Workshop and Conference Proceedings, 2011

 

Technical reports:

A. Agarwal, A. Choromanska, K. Choromanski, Notes on Using Determinantal Point Processes for Clustering with Applications to Text Clustering, CoRR, abs/1410.6975, 2014

A. Choromanska, T. Jebara, Stochastic Bound Majorization, CoRR, abs/1309.5605, 2013

 

Preprints:

M. Bojarski, A. Choromanska, K. Choromanski, B. Firner, L. Jackel, U. Muller, K. Zieba, VisualBackProp: visualizing CNNs for autonomous driving, CoRR, 2016 (submitted)

M. Bojarski, A. Choromanska, K. Choromanski, Y. LeCun, Differentially- and non-differentiallyprivate random decision trees, CoRR, abs/1410.6973, 2015 (submitted)

A. Choromanska, K. Choromanski, M. Bojarski, On the boosting ability of top-down decision tree learning algorithm for multiclass classification, CoRR, abs/1605.05223, 2016 (submitted) 

A. Y. Aravkin, A. Choromanska, T. Jebara, D. Kanevsky, Chapter: Semistochastic quadratic bound methods, in Log-Linear Models, Extensions and Applications, MIT Press, 2015 (submitted)

 

Education

Columbia University in the City of New York, 2014

M.Phil. and Ph.D., Department of Electrical Engineering

Warsaw University of Technology, 2009

MSc, Department of Electronics and Information Technology

Experience

NVIDIA (New Jersey lab)

Research Collaboration

From: May 2016 to present

Courant Institute of Mathematical Sciences, CSD, NYU

Post-Doctoral Associate

From: April 2014 to January 2017

Microsoft Research, New York

Research Collaboration

From: September 2013 to June 2014

Microsoft Research, New York

Summer Internship

From: June 2013 to September 2013

IBM T.J.Watson Research Center

Research Collaboration

From: May 2012 to June 2013

ATT Research Laboratories

Summer Internship

From: July 2012 to September 2012

Dept. of Electrical Eng., Univ. of Hawaii at Manoa

Visiting Summer Scholar

From: October 2008 to November 2008

Centre de Recherche du Centre Hospitalier Univ. de Montreal

Summer Internship

From: July 2008 to September 2008

Smell and Taste Center, Department of Otorhinolaryngology, UPenn

Visiting Summer Scholar

From: September 2008 to September 2008

University of North Texas Health Science Center

Visiting Summer Scholar

From: September 2008 to September 2008

Awards + Distinctions

Student Best Paper Award, First Place, for the work T. Jebara, A. Choromanska, Majorization for CRFs and Latent Likelihoods, 7th Annual Machine Learning Symposium, New York Academy of Science, 2012

Student Best Paper Award, Third Place, for the work A. Choromanska, C. Monteleoni, Online clustering with experts, 6th Annual Machine Learning Symposium, New York Academy of Science, 2011

The Fu Foundation School of Engineering and Applied Science Presidential Fellowship holder, Columbia University in the City of New York, 2009-2012

Departmental Scholarship holder for the Achievements in Science, Warsaw University of Technology, Department of Electronics and Information Technology, 2005-2009

Winner (first place) of the National Mathematics Competition held by Warsaw University of Technology, 2004

Laureate of the National Physics Competition held by Warsaw University of Technology, 2004

Affiliations

NYU Center for Data Science

Research Interests

  • machine learning both theoretical and applicable to the variety of real-life phenomena
  • numerical optimization
  • deep learning large data analysis, learning from datastreams, learning with expert advice, supervised and unsupervised online learning, clustering, and structured prediction
  • autonomous car driving