Photo
NEWS:

Martin Jaggi

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

Postdoctoral researcher in the Data Analytics Lab at ETH Zürich, working with Thomas Hofmann.

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:

Refereed Journal and Conference Publications:

Communication-Efficient Distributed Dual Coordinate Ascent (with Virginia Smith, Martin Takáč, Jonathan Terhorst, Sanjay Krishnan, Thomas Hofmann, Michael I. Jordan)
NIPS 2014 [Slides]
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 Workshop Proceedings:

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:

An Optimal Affine Invariant Smooth Minimization Algorithm (with Alexandre d'Aspremont and Cristobal Guzman)
Draft on arXiv (2013)
Convex Optimization without Projection Steps
Thesis chapter. arXiv math.OC (2011) (now subsumed by newer ICML 2013 version)
A Combinatorial Algorithm to Compute Regularization Paths (with Bernd Gärtner, Joachim Giesen and Torsten Welsch)
Draft on arXiv cs.LG (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

Talks:

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, 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 (2014,2013,2012), SemEval 2014, SWAT 2014, ICML (2014,2013,2012), NIPS OPT and GREEDY Workshops (2013), COLT (2011), ALENEX (2010), ICALP (2010), ESA (2009,2008), SoCG (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 the currently available student projects in our group.
Supervised Theses/Projects:
Tribhuvanesh Orekondy: 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 Assistance:
Informatics for mathematics and physics students (in C++), ETH, Fall 2011
Graph Drawing (Organizing Assistant), ETH, Spring 2011
Algorithms, Probability, and Computing (Organizing Assistant), ETH, Fall 2010
Algorithms, Probability, and Computing, ETH, Fall 2009
Informatics II for civil engineering students (in Java), ETH, Spring 2009
Informatics for mathematics and physics students (in C++), ETH, Fall 2008
Discrete Mathematics for electrical engineering students, ETH, Fall 2007
Analysis I for computer science students, 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, Aug 2014