Photo
NEWS:

Martin Jaggi

mail: jaggi@inf.ethz.ch
office: CAB F 42.1
personal website: www.m8j.net

I've accepted a position as a tenure-track assistent professor at EPFL, starting this fall. I'm looking for talented PhD students! See EDIC program website, and please also get in touch via email if you plan to apply. For undegraduate summer internships, please see the Summer@EPFL program.

Postdoctoral researcher (Oberassistent) in the Data Analytics Lab at ETH Zürich, in the group of Thomas Hofmann. I'm also an associated fellow at the new Max-Planck-ETH Center for Learning Systems.
In fall 2013, I was a research fellow in big data analysis at Simons Institute for the Theory of Computing, Berkeley, US.
2012/2013, I was a postdoctoral researcher with Alexandre d'Aspremont at CMAP at Ecole Polytechnique, Paris.
I obtained my PhD from ETH Zürich in fall 2011, supervised by Bernd Gärtner and Emo Welzl.

Research: Scientific interests:

Publications: (See also google scholar)

Refereed Journal and Conference Publications:

Primal-Dual Rates and Certificates (with Celestine Dünner, Simone Forte and Martin Takáč)
ICML 2016: International Conference on Machine Learning (2016)
On the Global Linear Convergence of Frank-Wolfe Optimization Variants (with Simon Lacoste-Julien)
NIPS 2015 [Poster, Code]
Adding vs. Averaging in Distributed Primal-Dual Optimization (with Chenxin Ma, Virginia Smith, Michael I. Jordan, Peter Richtárik, Martin Takáč)
ICML 2015: International Conference on Machine Learning (2015) [Poster, Slides, Code]
Communication-Efficient Distributed Dual Coordinate Ascent (with Virginia Smith, Martin Takáč, Jonathan Terhorst, Sanjay Krishnan, Thomas Hofmann, Michael I. Jordan)
NIPS 2014 [Slides, Poster, Code]
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization
ICML 2013: International Conference on Machine Learning (2013) [Poster, Slides, Short Slides, Workshop Version, Video]
Block-Coordinate Frank-Wolfe Optimization for Structural SVMs (with Simon Lacoste-Julien, Mark Schmidt and Patrick Pletscher)
ICML 2013: International Conference on Machine Learning (2013) [Poster, Slides, Workshop Version, Code]
Approximating Parameterized Convex Optimization Problems (with Joachim Giesen and Sören Laue)
ACM Transactions on Algorithms (2012) [Slides etc., DOI]
An Exponential Lower Bound on the Complexity of Regularization Paths (with Bernd Gärtner and Clément Maria)
Journal of Computational Geometry (2012)
Optimizing over the Growing Spectrahedron (with Joachim Giesen and Sören Laue)
ESA 2012: 20th Annual European Symposium on Algorithms (2012)
Regularization Paths with Guarantees for Convex Semidefinite Optimization (with Joachim Giesen and Sören Laue)
AISTATS 2012: 15th International Conference on Artificial Intelligence and Statistics (2012) [Poster, Slides etc.]
Approximating Parameterized Convex Optimization Problems (with Joachim Giesen and Sören Laue)
ESA 2010: 18th Annual European Symposium on Algorithms (2010) [Slides etc., DOI]
A Simple Algorithm for Nuclear Norm Regularized Problems (with Marek Sulovský)
ICML 2010: International Conference on Machine Learning (2010) [Slides etc.]
Coresets for Polytope Distance (with Bernd Gärtner)
SCG '09: 25th Annual Symposium on Computational Geometry (2009) [Slides etc., DOI]

Book Chapter:

An Equivalence between the Lasso and Support Vector Machines
Regularization, Optimization, Kernels, and Support Vector Machines, Chapman and Hall/CRC.
Edited by Johan A.K. Suykens, Marco Signoretto, Andreas Argyriou, (2014) [Slides, Shorter Version, Video]

Refereed Workshops:

SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision (with Jan Deriu, Maurice Gonzenbach, Fatih Uzdilli, Aurelien Lucchi and Valeria De Luca)
SemEval 2016: Proceedings of the 10th International Workshop on Semantic Evaluation. San Diego (2016)
Swiss-Chocolate: Combining Flipout Regularization and Random Forests with Artificially Built Subsystems to Boost Text-Classification for Sentiment (with Fatih Uzdilli, Dominic Egger, Pascal Julmy, Leon Derczynski and Mark Cieliebak)
SemEval 2015: Proceedings of the 9th International Workshop on Semantic Evaluation. Denver, Colorado (2015)
Swiss-Chocolate: Sentiment Detection using Sparse SVMs and Part-Of-Speech n-Grams (with Fatih Uzdilli and Mark Cieliebak)
SemEval 2014: Proceedings of the 8th International Workshop on Semantic Evaluation, p 601–604. Dublin, Ireland (2014)
An Affine Invariant Linear Convergence Analysis for Frank-Wolfe Algorithms (with Simon Lacoste-Julien)
NIPS Workshop on Greedy Algorithms, Frank-Wolfe and Friends (2013)
An Equivalence between the Lasso and Support Vector Machines
ROKS - International Workshop on Advances in Regularization, Optimization, Kernel Methods and Support Vector Machines: Theory and Applications (2013) [Slides, Longer Version, Video]
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization
SPARS 2013: International Workshop on Signal Processing with Adaptive Sparse Structured Representations (2013) [Poster, Slides, Short Slides, Longer Version, Video]
Block-Coordinate Frank-Wolfe Optimization for Structural SVMs (with Simon Lacoste-Julien, Mark Schmidt and Patrick Pletscher
NIPS Workshop on Optimization for Machine Learning (2012) [Poster, Slides, Longer Version, Code]

Drafts / Submitted / Various:

Pursuits in Structured Non-Convex Matrix Factorizations (with Rajiv Khanna and Michael Tschannen)
arXiv (2016)
L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework (with Virginia Smith, Simone Forte and Michael I. Jordan)
arXiv (2015)
Distributed Optimization with Arbitrary Local Solvers (with Chenxin Ma, Jakub Konečný, Virginia Smith, Michael I. Jordan, Peter Richtárik, Martin Takáč)
arXiv (2015)
An Optimal Affine Invariant Smooth Minimization Algorithm (with Alexandre d'Aspremont and Cristobal Guzman)
arXiv (2013)
Convex Optimization without Projection Steps
Thesis chapter. arXiv (2011) (now subsumed by newer ICML 2013 version)
A Combinatorial Algorithm to Compute Regularization Paths (with Bernd Gärtner, Joachim Giesen and Torsten Welsch)
arXiv (2009)
New Results in Tropical Discrete Geometry (with Gabriel Katz and Uli Wagner)
Manuscript (2008)

Theses:

Sparse Convex Optimization Methods for Machine Learning,
PhD thesis in Theoretical Computer Science, ETH Zurich, October 2011
(Advisors: Bernd Gärtner and Emo Welzl, Co-Examinors: Elad Hazan, Joachim Giesen, Joachim M. Buhmann)
Linear and Quadratic Programming by Unique Sink Orientations,
Diploma thesis in Mathematics, ETH Zurich, September 2006
Implementations of the Schreier-Sims Algorithm,
Semester thesis, University of London, March 2005

Open Source Software:

proxCoCoA+ Distributed L1-Regularized Optimization
(with Virginia Smith and Simone Forte)
Apache Spark code for large scale sparse regression and classification
   [ github ]
Linearly Convergent Frank-Wolfe Optimization Algorithms
(with Simon Lacoste-Julien)
A reference implementation of the Frank-Wolfe algorithm variants with away-steps as well as pair-wise steps, demonstrating the linear convergence rates. Code for Matlab & Octave.
   [ github ]
dissolvestruct - Distributed Solver for Large Scale Structured Prediction
(with Tribhuvanesh Orekondy and Aurelien Lucchi)
Apache Spark library for distributed training, with several use-cases of structured prediction. Providing the same interface as standard SVMstruct.
   [ github ]
CoCoA - Communication-Efficient Distributed Coordinate Ascent
(with Virginia Smith)
Apache Spark code for large scale binary classification and (soon) regression
   [ github ]
Frank-Wolfe Demo Code
Matlab & Octave code illustrating the Frank-Wolfe algorithm for Lasso (l1-regularized least squares regression), and nuclear norm regularized matrix completion
   [ tutorial website ]
BCFW - Fast Structured Prediction Solver
(with Patrick Pletscher, Mark Schmidt and Simon Lacoste-Julien)
Fast Matlab implementation of the block-coordinate Frank-Wolfe algorithm for Structural SVMs
   [ github ]

Selected Talks:

Optimization, Learning and Systems
15 February 2016, IC Colloquium, EPFL, Switzerland
L1-Regularized Distributed Optimization - A Communication-Efficient Primal-Dual Framework
6 October 2015, Workshop on Optimization in Machine Learning, Vision and Image Processing, Toulouse, France
Frank-Wolfe Optimization Algorithms: A Brief Tutorial
24 July 2015, Simons Center for Data Analysis, New York, USA
Communication Efficient Distributed Training of Machine Learning Models
16 July 2015, ISMP - International Symposium on Mathematical Programming, Pittsburgh, USA
Distributed Machine Learning: Algorithms and Open Source Implementations
12 June 2015, 2nd Swiss Workshop on Data Science (SDS|2015), ZHAW Winterthur
Verteiltes Machine Learning: Klassifikation und Regression auf grossen Datenmengen
11 June 2015, Big Data Workshop: Squeezing more out of Data, FFHS Switzerland
Communication Efficient Distributed Training of Machine Learning Models
2 June 2015, PASC 2015 - Platform for Advanced Scientific Computing Conference, ETH Zurich
Frank-Wolfe Optimization Algorithms: A Brief Tutorial
6 May 2015, Optimization and Big Data 2015 - International Workshop, Trek and Colloquium, Edinburgh, UK
CoCoA and Frank-Wolfe: Topics in [Distributed] Convex Optimization
13 March 2015, swissQuant - Scientific Advisory Board Meeting, Zurich
Machine Learning and AI in Neurointensive Care
17 February 2015, ICU Cockpit Day, University Hospital Zurich, Zurich
Communication Efficient Distributed Optimization for Machine Learning
16 December 2014, Big Data Reunion Workshop, Berkeley, USA
Communication-Efficient Distributed Optimization for Machine Learning
21 November 2014, International Workshop on Online Algorithms and Learning, Lorentz Center, Leiden, NED
Communication-Efficient Distributed Dual Coordinate Ascent
5 September 2014, IMA Conference on Numerical Linear Algebra and Optimisation, Birmingham, UK
Communication-Efficient Distributed Dual Coordinate Ascent
11 July 2014, Stochastic and Distributed Optimization Workshop - Mastodons Display-Gargantua, Nice, France
ICML Tutorial on Frank-Wolfe and Greedy Optimization for Learning with Big Data
21 June 2014, ICML, Beijing, China
Frank-Wolfe and Greedy Algorithms in Optimization and Signal Processing
21 Mai 2014, SIAM Conference on Optimization, San Diego, USA
Frank-Wolfe Optimization with Applications to Structured Prediction
15 November 2013, Machine Learning Reading Group, Stanford, USA
A Fresh Look at the Frank-Wolfe Algorithm, with Applications to Sparse Convex Optimization
1 August 2013, ICCOPT Conference, Lisbon, Portugal
Connections between the Lasso and Support Vector Machines (invited plenary talk)
8 July 2013, ROKS 2013 International Workshop on Advances in Regularization, Optimization, Kernel Methods and Support Vector Machines: Theory and Applications, Leuven, Belgium
Block-Coordinate Frank-Wolfe Optimization with Applications to Structured Prediction (invited plenary talk)
2 May 2013, Optimization and Big Data International Workshop, Edinburgh, UK
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization
24 January 2013, SMILE (Statistical Machine Learning in Paris) Seminar, Paris, France
Block-Coordinate Frank-Wolfe Optimization with Applications to Structured Prediction
13 November 2012, Xerox Research Europe Seminar, Grenoble, France
Block-Coordinate Frank-Wolfe for Structural SVMs
12 November 2012, INRIA LEAR Seminar, Grenoble, France
Cheaper Block Coordinate Descent by Frank-Wolfe Steps
22 May 2012, UCL-INMA / CORE Optimization Research Retreat, Knokke, Belgium
Structured Sparsity
10 November 2011, Mittagsseminar, ETH, [abstract]
Convex Optimization without Projection Steps
20 October 2011, INRIA / ENS Machine Learning Seminar, Paris, France
Sparse Convex Optimization Methods for Machine Learning
22 August 2011, Machine Learning Seminar, ETH
Convex Optimization with a Parameter, and Regularization Paths for Matrix Factorizations
3 March 2011, Mittagsseminar, ETH, [abstract]
A typical day in the life of the optimization problem max xT A x
14 October 2010, Mittagsseminar, ETH, [abstract]
A Simple Algorithm for Nuclear Norm Regularized Problems
22 June 2010, ICML 2010, Haifa, Israel
Matrix Factorizations of Incomplete Matrices
15 February 2010, Google Research Talk, Google Zürich
Maximum Margin Matrix Factorization and Simon Funk's Algorithm
18 January 2010, Machine Learning Seminar, ETH
Approximate SDP Solvers, Matrix Factorizations, the Netflix Prize, and PageRank
6 October 2009, Mittagsseminar, ETH, [abstract]
Coresets for Polytope Distance
8 June 2009, 25th Annual Symposium on Computational Geometry (SCG '09), Aarhus, Denmark
Kernels, Margins, Coresets and The Fight of High- vs. Low-Dimensional Spaces
26 March 2009, Mittagsseminar, ETH, [abstract]
Coresets for Polytope Distance
9 October 2008, Mittagsseminar, ETH, [abstract]
Approximating the cut norm using Grothendieck's inequality, by Noga Alon and Assaf Naor
11 April 2008, Reading Seminar, ETH, [DOI]
Geometry of Support Vector Machines
28 February 2008, Mittagsseminar, ETH, [abstract]
Evolution of Curvature and Other Quantities under Mean Curvature Flow
24 November & 1 December 2005, Seminar on Geometric Heat Flows, ETH
Extremal Combinatorics - Density and Universality
14 June 2004, Extremal Combinatorics Seminar, ETH

Reviewing:

Journals: Mathematical Programming, SIAM Journal on Optimization, Journal of Machine Learning Research (JMLR), Mathematics of Operations Research, IEEE Transactions on Signal Processing, IEEE Transactions on Pattern Analysis and Machine Intelligence, Constructive Approximation, Optimization Methods & Software, Information Sciences, J. of Universal Computer Science, Algorithmica
Conferences: NIPS (2016,2015,2014,2013,2012), ICML (2016,2015,2014,2013,2012), SemEval (2015,2014), SWAT 2014, NIPS OPT and GREEDY Workshops (2013), COLT (2011), ALENEX (2010), ICALP (2010), ESA (2009,2008), SoCG (2016,2008)

Organizing:

NIPS 2014 Workshop on Optimization for Machine Learning, jointly with Alekh Agarwal, Miro Dudik, Zaid Harchaoui, Aaditya Ramdas, and Suvrit Sra.
ICML 2014 Tutorial on Frank-Wolfe and Greedy Optimization for Learning with Big Data, jointly with Zaid Harchaoui.
Presentation slides, demo code and bibliography are available on the website.
Zurich Machine Learning and Data Science Meetup. Join us for one of our monthly open events, and also the linkedin group.
NIPS 2013 Workshop on Greedy Algorithms, Frank-Wolfe and Friends, jointly with Zaid Harchaoui and Federico Pierucci.
All papers, presentation slides and videos are available from the website.

Teaching:

Check out the currently available student projects in our group.
Supervised Theses/Projects:
Maurice Gonzenbach: Sentiment Classification and Medical Health Record Analysis using Convolutional Neural Networks,
Master thesis (jointly supervised with Valeria De Luca), ETH, May 2016
Jan Deriu: Sentiment Analysis using Deep Convolutional Neural Networks with Distant Supervision,
Master thesis (jointly supervised with Aurelien Lucchi), ETH, April 2016
Pascal Kaiser: Learning city structures from online maps,
Master thesis (jointly supervised with Aurelien Lucchi and Jan Dirk Wegner), ETH, March 2016
Adrian Kündig: Prediction of Cerebral Autoregulation in Intensive Care Patients,
Master thesis (jointly supervised with Valeria De Luca), ETH, January 2016
Bettina Messmer: Automatic Analysis of Large Text Corpora,
Master thesis (jointly supervised with Aurelien Lucchi), ETH, January 2016
Tribhuvanesh Orekondy: HADES: Hierarchical Approximate Decoding for Structured Prediction,
Master thesis (jointly supervised with Aurelien Lucchi), ETH, September 2015
Jakob Olbrich: Screening Rules for Convex Problems,
Master thesis (jointly supervised with Bernd Gärtner), ETH, September 2015
Sandro Felicioni: Latent Multi-Cause Model for User Profile Inference,
Master thesis (jointly supervised with Thomas Hofmann, and 1plusX), ETH, September 2015
Ruben Wolff: Distributed Structured Prediction for 3D Image Segmentation,
Master thesis (jointly supervised with Aurelien Lucchi), ETH, September 2015
Simone Forte: Distributed Optimization for Non-Strongly Convex Regularizers,
Master thesis (jointly supervised with Matthias Seeger, Amazon Berlin, and Virginia Smith, UC Berkeley), ETH, September 2015
Xiaoran Chen: Classification of stroke types with SNP and phenotype datasets,
Semester project (jointly supervised with Roqueiro Damian and Xiao He), ETH, June 2015
Yannic Kilcher: Towards efficient second-order optimization for big data,
Master thesis (jointly supervised with Aurelien Lucchi and Brian McWilliams), ETH, May 2015
Matthias Hüser: Forecasting intracranial hypertension using time series and waveform features,
Master thesis (jointly supervised with Valeria De Luca), ETH, April 2015
Lei Zhong: Adaptive Probabilities in Stochastic Optimization Algorithms,
Master thesis, ETH, April 2015
Maurice Gonzenbach: Prediction of Epileptic Seizures using EEG Data,
Semester project (jointly supervised with Valeria De Luca), ETH, Feb 2015
Julia Wysling: Screening Rules for the Support Vector Machine and the Minimum Enclosing Ball,
Bachelor's thesis (jointly supervised with Bernd Gärtner), ETH, Feb 2015
Tribhuvanesh Orekondy: dissolvestruct - A distributed implementation of Structured SVMs using Spark,
Semester project, ETH, August 2014
Michel Verlinden: Sublinear time algorithms for Support Vector Machines,
Semester project, ETH, July 2011
Clément Maria: An Exponential Lower Bound on the Complexity of Regularization Paths,
Internship project (jointly supervised with Bernd Gärtner), ETH, August 2010
Dave Meyer: Implementierung von geometrischen Algorithmen für Support-Vektor-Maschinen,
Diploma thesis, ETH, August 2009
Gabriel Katz: Tropical Convexity, Halfspace Arrangements and Optimization,
Master's thesis (jointly supervised with Uli Wagner), ETH, September 2008
Teaching:
Computational Intelligence Lab (Organizing Assistant), ETH, Spring 2016
Advanced Topics in Machine Learning Seminar (Organizing Assistant), ETH, Fall 2015
Computational Intelligence Lab (Organizing Assistant), ETH, Spring 2015
Big Data (Organizing Assistant), ETH, Fall 2014
Advanced Topics in Machine Learning Seminar (Organizing Assistant), ETH, Fall 2014
Informatics for mathematics and physics students (in C++) (TA), ETH, Fall 2011
Graph Drawing (Organizing Assistant), ETH, Spring 2011
Algorithms, Probability, and Computing (Organizing Assistant), ETH, Fall 2010
Algorithms, Probability, and Computing (TA), ETH, Fall 2009
Informatics II for civil engineering students (in Java) (TA), ETH, Spring 2009
Informatics for mathematics and physics students (in C++) (TA), ETH, Fall 2008
Discrete Mathematics for electrical engineering students (TA), ETH, Fall 2007
Analysis I for computer science students (TA), ETH, Winter 2003/2004

Consulting:

I'm interested to provide consulting for your machine learning, big data, prediction or data analysis project. See this separate webpage for contact details.

 

MJ, May 2016