We’re interested in machine learning, optimization algorithms and text understanding, as well as several application domains.
2019
An accelerated communication-efficient primal-dual optimization framework for structured machine learning
Optimization Methods & Software. 2019-08-06. DOI : 10.1080/10556788.2019.1650361.Stochastic Zeroth-Order Optimisation Algorithms with Variance Reduction
EPFL, 2019-06-21.A comparison of model-parallel training methods for deep learning
2019-06-18.Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
2019-06-09. ICML 2019 – International Conference on Machine Learning, Long Beach, California, USA, 9-15 June 2019.Local SGD Converges Fast and Communicates Little
2019-05-06. ICLR 2019 – International Conference on Learning Representations, New Orleans, USA, May 6-9, 2019.Unsupervised Robust Nonparametric Learning Of Hidden Community Properties
Mathematical Foundations Of Computing. 2019-05-01. Vol. 2, num. 2, p. 127-147. DOI : 10.3934/mfc.2019010.Crosslingual Document Embedding as Reduced-Rank Ridge Regression
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.Error Feedback Fixes SignSGD and other Gradient Compression Schemes
2019. 36th International Conference on Machine Learning (ICML) 2019, Long Beach, USA, June 9-15, 2019. p. 3252-3261.Overcoming Multi-model Forgetting
2019. ICML 2019 – 36th International Conference on Machine Learning, Long Beach, California, USA, June 09-15, 2019. p. 594-603.Open-Vocabulary Keyword Spotting with Audio and Text Embeddings
2019. INTERSPEECH 2019 – IEEE International Conference on Acoustics, Speech, and Signal Processing, Graz, Austria,Better Word Embeddings by Disentangling Contextual n-Gram Information
2019. NAACL 2019 – Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota, USA, June 2-7. 2019.2018
Training DNNs with Hybrid Block Floating Point
2018-12-04. NeurIPS 2018 – 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
2018-12-02. 32nd Annual Conference on Neural Information Processing Systems (NIPS), Montréal, Canada, December 2-8, 2018.Sparsified SGD with Memory
2018-12-02. NeurIPS 2018 – 32nd Annual Conference on Neural Information Processing Systems, Montréal, Canada, December 2-8, 2018.Optimal Affine-Invariant Smooth Minimization Algorithms
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
2018-09-04.Convex Optimization using Sparsified Stochastic Gradient Descent with Memory
2018-06-27.Unsupervised learning of sentence embeddings using compositional n-gram features
2018-05-01. NAACL 2018 – Conference of the North American Chapter of the Association for Computational Linguistics.Simple Unsupervised Keyphrase Extraction using Sentence Embeddings
2018-05-01. CoNLL 2018 – SIGNLL Conference on Computational Natural Language Learning.On Matching Pursuit and Coordinate Descent
2018-05-01. ICML 2018 – 35th International Conference on Machine Learning.Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems
2018-05-01.Learning Word Vectors for 157 Languages
2018-02-19. Language Resources and Evaluation Conference, Miyazaki, Japan, May 7-12, 2018.A Distributed Second-Order Algorithm You Can Trust
2018. 35th International Conference on Machine Learning (ICML 2018), Stockholm, Sweden, 10-15 July 2018. p. 1358-1366.Training DNNs with Hybrid Block Floating Point
2018-01-01. NeurIPS 2018 – 32nd Conference on Neural Information Processing Systems, Montreal, CANADA, Dec 02-08, 2018.CoCoA: A General Framework for Communication-Efficient Distributed Optimization
Journal Of Machine Learning Research. 2018-01-01. Vol. 18.Some results on a class of mixed van der Waerden numbers
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
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
2018. ICNR2018 – International Conference on NeuroRehabilitation, Pisa, Italy, October 16 – 20, 2018.2017
Asynchronous updates for stochastic gradient descent
2017-06-09.Fully Quantized Distributed Gradient Descent
2017.Safe Adaptive Importance Sampling
2017. Neural Information Processing Systems (NIPS), Long Beach, USA, December 4-9, 2017.On the existence of ordinary triangles
Computational Geometry. 2017. Vol. 66, p. 28-31. DOI : 10.1016/j.comgeo.2017.07.002.Learning Aerial Image Segmentation from Online Maps
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
2017. ICML 2017 – International Conference on Machine Learning, Sydney, Australia, Aug 6-11, 2017.Generating Steganographic Text with LSTMs
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
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
2017
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe
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
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
2017. 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017, Fort Lauderdale, Florida, USA, April 20-22, 2017.2016
CoCoA: A General Framework for Communication-Efficient Distributed Optimization
2016.Screening Rules for Convex Problems
2016
Pursuits in Structured Non-Convex Matrix Factorizations
2016
SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision
2016. [email protected] 2016, San Diego, CA, USA, June 16-17, 2016. p. 1124-1128.Primal-Dual Rates and Certificates
2016. ICML 2016 – International Conference on Machine Learning, USA, NY, New York City, June 19-24, 2016. p. 783-792.Audio Based Bird Species Identification using Deep Learning Techniques
2016. Conference and Labs of the Evaluation Forum (CLEF) 2016, Évora, Portugal, 5-8 September, 2016. p. 547-559.2015
L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework
2015
Swiss-Chocolate: Combining Flipout Regularization and Random Forests with Artificially Built Subsystems to Boost Text-Classification for Sentiment.
2015. [email protected] 2015, Denver, Colorado, USA, June 4-5, 2015. p. 608-612.On the Global Linear Convergence of Frank-Wolfe Optimization Variants
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
2015. ICML 2015 – International Conference on Machine Learning, Lille, France, 6-11 July 2015. p. 1973-1982.2014
An Equivalence between the Lasso and Support Vector Machines
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.
2014. [email protected] 2014, Dublin, Ireland, August 23-24, 2014. p. 601-604.Communication-Efficient Distributed Dual Coordinate Ascent.
2014. Neural Information Processing Systems (NIPS) 2014, Montreal, Quebec, Canada, December 8-13 2014. p. 3068-3076.2013
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization
2013. ICML 2013 – International Conference on Machine Learning, Atlanta, GA, USA, 16-21 June 2013. p. 427-435.Block-Coordinate Frank-Wolfe Optimization for Structural SVMs
2013. ICML 2013 – International Conference on Machine Learning, Atlanta, GA, USA, 16-21 June 2013. p. 53-61.2012
Regularization Paths with Guarantees for Convex Semidefinite Optimization.
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
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
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
JoCG – Journal of Computational Geometry. 2012. Vol. 3, num. 1, p. 168-195. DOI : 10.20382/jocg.v3i1a9.Optimizing over the Growing Spectrahedron
Algorithms – ESA 2012; Berlin Heidelberg: Springer, 2012. p. 503-514.2011
Sparse convex optimization methods for machine learning
ETH Zürich, 2011.Convex Optimization without Projection Steps
2011
2010
A Simple Algorithm for Nuclear Norm Regularized Problems.
2010. International Conference on Machine Learning (ICML) 2010, Haifa, Israel, June 21-24, 2010. p. 471-478.Approximating Parameterized Convex Optimization Problems.
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
European Symposia on Algorithms (ESA) 2010; Springer Berlin Heidelberg, 2010. p. 524-535.2009
A Combinatorial Algorithm to Compute Regularization Paths
2009