We’re interested in machine learning, optimization algorithms and text understanding, as well as several application domains.


Stochastic Zeroth-Order Optimisation Algorithms with Variance Reduction

A. Ajalloeian / S. U. Stich; M. Jaggi (Dir.)  

EPFL, 2019-06-21. 

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

A. Koloskova; S. U. Stich; M. Jaggi 

2019-06-09. International Conference on Machine Learning, Long Beach, California, USA, 9-15 June 2019.

Local SGD Converges Fast and Communicates Little

S. U. Stich 

2019-05-06. International Conference on Learning Representations, New Orleans, USA, May 6-9, 2019.

Crosslingual Document Embedding as Reduced-Rank Ridge Regression

M. Josifoski; I. S. Paskov; H. S. Paskov; M. Jaggi; R. West 

2019-02-13. WSDM '19 - ACM International Conference on Web Search and Data Mining, Melbourne, Australia, February 11 - 15, 2019 . p. 744-752. DOI : 10.1145/3289600.3291023.

Open-Vocabulary Keyword Spotting with Audio and Text Embeddings

N. Sacchi; A. Nanchen; M. Jaggi; M. Cernak 

2019. INTERSPEECH 2019 - IEEE International Conference on Acoustics, Speech, and Signal Processing, Graz, Austria,

Better Word Embeddings by Disentangling Contextual n-Gram Information

P. Gupta; M. Pagliardini; M. Jaggi 

2019. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota, USA, June 2-7. 2019.


Training DNNs with Hybrid Block Floating Point

M. P. Drumond Lages De Oliveira; T. Lin; M. Jaggi; B. Falsafi 

2018-12-04. Neural Information Processing Systems, Montréal Canada, December 2-8, 2018.

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization

R. M. Gower; F. Hanzely; P. Richtárik; S. U. Stich 

2018-12-02. 32nd Annual Conference on Neural Information Processing Systems (NIPS), Montréal, Canada, December 2-8, 2018.

Sparsified SGD with Memory

S. U. Stich; J-B. Cordonnier; M. Jaggi 

2018-12-02. 32nd Annual Conference on Neural Information Processing Systems (NIPS), Montréal, Canada, December 2-8, 2018.

Optimal Affine-Invariant Smooth Minimization Algorithms

A. d'Aspremont; C. Guzmán; M. Jaggi 

SIAM Journal on Optimization. 2018-09-19. Vol. 28, num. 3, p. 2384-2405. DOI : 10.1137/17M1116842.

Unsupervised Learning of Representations for Lexical Entailment Detection

A. Hug 


Convex Optimization using Sparsified Stochastic Gradient Descent with Memory

J-B. Cordonnier 


Unsupervised learning of sentence embeddings using compositional n-gram features

M. Pagliardini; P. Gupta; M. Jaggi 

2018-05-01. NAACL 2018 - Conference of the North American Chapter of the Association for Computational Linguistics.

Simple Unsupervised Keyphrase Extraction using Sentence Embeddings

K. Bennani-Smires; C-C. Musat; A. Hossmann; M. Baeriswyl; M. Jaggi 

2018-05-01. CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning.

On Matching Pursuit and Coordinate Descent

F. Locatello; A. Raj; S. P. R. Karimireddy; G. Rätsch; B. Schölkopf et al. 


Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems

S. P. R. Karimireddy; M. Jaggi; S. Stich 


Learning Word Vectors for 157 Languages

E. Grave; P. Bojanowski; P. Gupta; A. Joulin; T. Mikolov 

2018-02-19. Language Resources and Evaluation Conference, Miyazaki, Japan, May 7-12, 2018.

CoCoA: A General Framework for Communication-Efficient Distributed Optimization

V. Smith; S. Forte; C. Ma; M. Takac; M. I. Jordan et al. 

Journal Of Machine Learning Research. 2018-01-01. Vol. 18.

Some results on a class of mixed van der Waerden numbers

K. Maran; S. Reddy; D. Sharma; A. Tripathi 

Rocky Mountain Journal of Mathematics. 2018. Vol. 48, num. 3, p. 885-904. DOI : 10.1216/RMJ-2018-48-3-885.

Gene locations may contribute to predicting gene regulatory relationships

J. Meng; W. Xu; X. Chen; T. Lin; X. Deng 

JOURNAL OF ZHEJIANG UNIVERSITY-SCIENCE B. 2018. Vol. 19, num. 1, p. 25-37. DOI : 10.1631/jzus.B1700303.

Prediction of patient-reported physical activity scores from wearable accelerometer data: a feasibility study

I. Bahej; I. Clay; M. Jaggi; V. De Luca 

2018. ICNR2018 - International Conference on NeuroRehabilitation, Pisa, Italy, October 16 - 20, 2018.


Asynchronous updates for stochastic gradient descent

A. S. Chiappa 


Fully Quantized Distributed Gradient Descent

F. Künstner 


Safe Adaptive Importance Sampling

S. U. Stich; A. Raj; M. Jaggi 

2017. Neural Information Processing Systems (NIPS), Long Beach, USA, December 4-9, 2017.

On the existence of ordinary triangles

R. Fulek; H. N. Mojarrad; M. Naszódi; J. Solymosi; S. U. Stich et al. 

Computational Geometry. 2017. Vol. 66, p. 28-31. DOI : 10.1016/j.comgeo.2017.07.002.

Learning Aerial Image Segmentation from Online Maps

P. Kaiser; J. D. Wegner; A. Lucchi; M. Jaggi; T. Hofmann et al. 

IEEE Transactions on Geoscience and Remote Sensing. 2017. Vol. 55, num. 11, p. 6054-6068. DOI : 10.1109/TGRS.2017.2719738.

Approximate Steepest Coordinate Descent

S. U. Stich; A. Raj; M. Jaggi 

2017. International Conference on Machine Learning (ICML 2017), Sydney, Australia, Aug 6-11, 2017.

Generating Steganographic Text with LSTMs

T. Tina Fang; M. Jaggi; K. Argyraki 

2017. ACL Student Research Workshop 2017, Vancouver, Canada, July 30-August 4, 2017. p. 100-106. DOI : 10.18653/v1/P17-3017.

Distributed Optimization with Arbitrary Local Solvers

C. Ma; J. Konecný; M. Jaggi; V. Smith; M. I. Jordan et al. 

Journal of Optimization Methods and Software. 2017. Vol. 32. DOI : 10.1080/10556788.2016.1278445.

Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features

M. Pagliardini; P. Gupta; M. Jaggi 


A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe

F. Locatello; R. Khanna; M. Tschannen; M. Jaggi 

2017. 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017, Fort Lauderdale, California, United States, April 20-22, 2017.

Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification

J. Deriu; A. Lucchi; V. D. Luca; A. Severyn; S. Müller et al. 

2017. International World Wide Web Conference (WWW) 2017, Perth, Australia, April 3-7, 2017. p. 1045-1052. DOI : 10.1145/3038912.3052611.

Faster Coordinate Descent via Adaptive Importance Sampling

D. Perekrestenko; V. Cevher; M. Jaggi 

2017. 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017, Fort Lauderdale, Florida, USA, April 20-22, 2017.


CoCoA: A General Framework for Communication-Efficient Distributed Optimization

V. Smith; S. Forte; C. Ma; M. Takác; M. I. Jordan et al. 


Screening Rules for Convex Problems

A. Raj; J. Olbrich; B. Gärtner; B. Schölkopf; M. Jaggi 


Pursuits in Structured Non-Convex Matrix Factorizations

R. Khanna; M. Tschannen; M. Jaggi 


SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision

J. Deriu; M. Gonzenbach; F. Uzdilli; A. Lucchi; V. D. Luca et al. 

2016. [email protected] 2016, San Diego, CA, USA, June 16-17, 2016. p. 1124-1128.

Primal-Dual Rates and Certificates

C. Dünner; S. Forte; M. Takác; M. Jaggi 

2016. International Conference on Machine Learning (ICML) 2016, USA, NY, New York City, June 19-24, 2016. p. 783-792.

Audio Based Bird Species Identification using Deep Learning Techniques

E. Sprengel; M. Jaggi; Y. Kilcher; T. Hofmann 

2016. Conference and Labs of the Evaluation Forum (CLEF) 2016, Évora, Portugal, 5-8 September, 2016. p. 547-559.


L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework

V. Smith; S. Forte; M. I. Jordan; M. Jaggi 


Swiss-Chocolate: Combining Flipout Regularization and Random Forests with Artificially Built Subsystems to Boost Text-Classification for Sentiment.

F. Uzdilli; M. Jaggi; D. Egger; P. Julmy; L. Derczynski et al. 

2015. [email protected] 2015, Denver, Colorado, USA, June 4-5, 2015. p. 608-612.

On the Global Linear Convergence of Frank-Wolfe Optimization Variants.

S. Lacoste-Julien; M. Jaggi 

2015. Neural Information Processing Systems (NIPS) 2015, Montreal, Quebec, Canada, December 7-12, 2015. p. 496-504.

Adding vs. Averaging in Distributed Primal-Dual Optimization.

C. Ma; V. Smith; M. Jaggi; M. I. Jordan; P. Richtárik et al. 

2015. International Conference on Machine Learning (ICML) 2015, Lille, France, 6-11 July 2015. p. 1973-1982.


An Equivalence between the Lasso and Support Vector Machines

M. Jaggi 

Regularization, Optimization, Kernels, and Support Vector Machines; Chapman and Hall/CRC, 2014. p. 1-26.

Swiss-Chocolate: Sentiment Detection using Sparse SVMs and Part-Of-Speech n-Grams.

M. Jaggi; F. Uzdilli; M. Cieliebak 

2014. [email protected] 2014, Dublin, Ireland, August 23-24, 2014. p. 601-604.

Communication-Efficient Distributed Dual Coordinate Ascent.

M. Jaggi; V. Smith; M. Takác; J. Terhorst; S. Krishnan et al. 

2014. Neural Information Processing Systems (NIPS) 2014, Montreal, Quebec, Canada, December 8-13 2014. p. 3068-3076.


Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization.

M. Jaggi 

2013. International Conference on Machine Learning (ICML) 2013, Atlanta, GA, USA, 16-21 June 2013. p. 427-435.

Block-Coordinate Frank-Wolfe Optimization for Structural SVMs

S. Lacoste-Julien; M. Jaggi; M. W. Schmidt; P. Pletscher 

2013. International Conference on Machine Learning (ICML) 2013, Atlanta, GA, USA, 16-21 June 2013. p. 53-61.


Regularization Paths with Guarantees for Convex Semidefinite Optimization.

J. Giesen; M. Jaggi; S. Laue 

2012. International Conference on Artificial Intelligence and Statistics (AISTATS) 2012, La Palma, Canary Islands, April 21-23, 2012. p. 432-439.

Optimizing over the Growing Spectrahedron

J. Giesen; M. Jaggi; S. Laue 

2012. European Symposia on Algorithms (ESA) 2012, Ljubljana, Slovenia, September 10-12, 2012. p. 503-514. DOI : 10.1007/978-3-642-33090-2_44.

Approximating parameterized convex optimization problems

J. Giesen; M. Jaggi; S. Laue 

ACM Trans. Algorithms. 2012. Vol. 9, num. 1, p. 10:1-10:17. DOI : 10.1145/2390176.2390186.

An Exponential Lower Bound on the Complexity of Regularization Paths

B. Gärtner; M. Jaggi; C. Maria 

JoCG - Journal of Computational Geometry. 2012. Vol. 3, num. 1, p. 168-195. DOI : 10.20382/jocg.v3i1a9.

Optimizing over the Growing Spectrahedron

J. Giesen; M. Jaggi; S. Laue 

Algorithms – ESA 2012; Berlin Heidelberg: Springer, 2012. p. 503-514.


Sparse convex optimization methods for machine learning

M. Jaggi 

ETH Zürich, 2011. 

Convex Optimization without Projection Steps

M. Jaggi 



A Simple Algorithm for Nuclear Norm Regularized Problems.

M. Jaggi; M. Sulovský 

2010. International Conference on Machine Learning (ICML) 2010, Haifa, Israel, June 21-24, 2010. p. 471-478.

Approximating Parameterized Convex Optimization Problems.

J. Giesen; M. Jaggi; S. Laue 

2010. European Symposia on Algorithms (ESA) 2010, Liverpool, UK, September 6-8, 2010. p. 524-535. DOI : 10.1007/978-3-642-15775-2_45.

Approximating Parameterized Convex Optimization Problems

J. Giesen; M. Jaggi; S. Laue 

European Symposia on Algorithms (ESA) 2010; Springer Berlin Heidelberg, 2010. p. 524-535.


A Combinatorial Algorithm to Compute Regularization Paths

B. Gärtner; J. Giesen; M. Jaggi; T. Welsch 


Coresets for polytope distance

B. Gärtner; M. Jaggi 

2009. Symposium on Computational Geometry 2009, Aarhus, Denmark, June 8-10, 2009. p. 33-42. DOI : 10.1145/1542362.1542370.