We’re interested in machine learning, optimization algorithms and text understanding, as well as several application domains.
The list below is NOT up to date. Please refer to the Google Scholar pages of our team members instead.
2022
Stochastic distributed learning with gradient quantization and double-variance reduction
Optimization Methods & Software. 2022-09-24. DOI : 10.1080/10556788.2022.2117355.Genomic Diversity of Torque Teno Virus in Blood Samples from Febrile Paediatric Outpatients in Tanzania: A Descriptive Cohort Study
Viruses-Basel. 2022-08-01. Vol. 14, num. 8, p. 1612. DOI : 10.3390/v14081612.MoDN-Flip: Optimizing Modular Clinical Decision Support Networks with Decision Flippability Score
2022-07-29.Point-of-care lung ultrasonography for early identification of mild COVID-19: a prospective cohort of outpatients in a Swiss screening center
Bmj Open. 2022-06-01. Vol. 12, num. 6, p. e060181. DOI : 10.1136/bmjopen-2021-060181.Is Artificial intelligence as accurate as spirometry in early diagnosis of asthma exacerbation in children ? A prospective study.
2022-05-27. p. 35S-35S.SKILL: Structured Knowledge Infusion for Large Language Models
2022-01-01. Conference of the North-American-Chapter-of-the-Association-for-Computational-Linguistics (NAAACL) – Human Language Technologies, Seattle, WA, Jul 10-15, 2022. p. 1581-1588.Masked Training of Neural Networks with Partial Gradients
2022-01-01. International Conference on Artificial Intelligence and Statistics, ELECTR NETWORK, Mar 28-30, 2022. p. 5876-5890.Algorithms for Efficient and Robust Distributed Deep Learning
Lausanne, EPFL, 2022.2021
Interpreting Language Models Through Knowledge Graph Extraction
2021-12-14. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online, December 6-14, 2021.Lung Ultrasonography for Risk Stratification in Patients with Coronavirus Disease 2019 (COVID-19): A Prospective Observational Cohort Study
Clinical Infectious Diseases. 2021-12-01. Vol. 73, num. 11, p. E4189-E4196. DOI : 10.1093/cid/ciaa1408.Equinox: Training (for Free) on a Custom Inference Accelerator
2021-10-18. 54th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO’21), Virtual Event, Greece, October 18–22, 2021. DOI : 10.1145/3466752.3480057.Bayesian inference with Expectation Maximisation for the characterisation of antibiotic treatment recovery in Cystic Fibrosis
2021-08-27.Extracellular vesicle- and particle-mediated communication shapes innate and adaptive immune responses
Journal Of Experimental Medicine. 2021-08-02. Vol. 218, num. 8, p. e20202579. DOI : 10.1084/jem.20202579.Deep Compositional Denoising for High-quality Monte Carlo Rendering
Computer Graphics Forum. 2021-07-01. Vol. 40, num. 4, p. 1-13. DOI : 10.1111/cgf.14337.Understanding Catastrophic Overfitting in Adversarial Training
2021-05-21.Deep learning diagnostic and risk-stratification pattern detection for COVID-19 in digital lung auscultations: clinical protocol for a case-control and prospective cohort study
Bmc Pulmonary Medicine. 2021-03-24. Vol. 21, num. 1, p. 103. DOI : 10.1186/s12890-021-01467-w.Measuring the Impact of Model and Input Heterogeneity in Personalized Federated Learning
2021-02-19.Semantic Perturbations with Normalizing Flows for Improved Generalization
2021-01-01. 18th IEEE/CVF International Conference on Computer Vision (ICCV), ELECTR NETWORK, Oct 11-17, 2021. p. 6599-6609. DOI : 10.1109/ICCV48922.2021.00655.Faster Parallel Training of Word Embeddings
2021-01-01. 28th Annual IEEE International Conference on High Performance Computing, Data, and Analytics (HiPC), ELECTR NETWORK, Dec 17-18, 2021. p. 31-41. DOI : 10.1109/HiPC53243.2021.00017.Differentiable Patch Selection for Image Recognition
2021-01-01. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), ELECTR NETWORK, Jun 19-25, 2021. p. 2351-2360. DOI : 10.1109/CVPR46437.2021.00238.Lightweight Cross-Lingual Sentence Representation Learning
2021-01-01. Joint Conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th International Joint Conference on Natural Language Processing (IJCNLP) / 6th Workshop on Representation Learning for NLP (RepL4NLP), ELECTR NETWORK, Aug 01-06, 2021. p. 2902-2913. DOI : 10.18653/v1/2021.acl-long.226.Learning computationally efficient static word and sentence representations
Lausanne, EPFL, 2021.Exact Optimization of Conformal Predictors via Incremental and Decremental Learning
2021-01-01. International Conference on Machine Learning (ICML), ELECTR NETWORK, Jul 18-24, 2021.Attention is not all you need: pure attention loses rank doubly exponentially with depth
2021-01-01. International Conference on Machine Learning (ICML), ELECTR NETWORK, Jul 18-24, 2021.Learning from History for Byzantine Robust Optimization
2021-01-01. International Conference on Machine Learning (ICML), ELECTR NETWORK, Jul 18-24, 2021.Consensus Control for Decentralized Deep Learning
2021-01-01. International Conference on Machine Learning (ICML), ELECTR NETWORK, Jul 18-24, 2021.Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
2021-01-01. International Conference on Machine Learning (ICML), ELECTR NETWORK, Jul 18-24, 2021.Optimization methods for collaborative learning
Lausanne, EPFL, 2021.Predicting changes in depression using person-generated health data
2021.LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads
2021-01-01. 24th International Conference on Artificial Intelligence and Statistics (AISTATS), ELECTR NETWORK, Apr 13-15, 2021.Advances and Open Problems in Federated Learning
Foundations And Trends In Machine Learning. 2021-01-01. Vol. 14, num. 1-2, p. 1-210. DOI : 10.1561/2200000083.Contribution Measures for Incentivizing Personalized Collaborative Learning
2021.HyperAggregate: A sublinear secure aggregation protocol
2021.Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates
2021. 24th International Conference on Artificial Intelligence and Statistics (AISTATS), Virtual, April 13-15, 2021.Blood virosphere in febrile Tanzanian children
Emerging Microbes & Infections. 2021-01-01. Vol. 10, num. 1, p. 982-993. DOI : 10.1080/22221751.2021.1925161.An accelerated communication-efficient primal-dual optimization framework for structured machine learning
Optimization Methods & Software. 2021. Vol. 36, num. 1, p. 20-44. DOI : 10.1080/10556788.2019.1650361.2020
Design Patterns for Resource-Constrained Automated Deep-Learning Methods
AI. 2020-10-06. Vol. 1, num. 4, p. 510-538. DOI : 10.3390/ai1040031.The Internet of Audio Things: State of the Art, Vision, and Challenges
Ieee Internet Of Things Journal. 2020-10-01. Vol. 7, num. 10, p. 10233-10249. DOI : 10.1109/JIOT.2020.2997047.Clinical relevance of low-densityPlasmodium falciparumparasitemia in untreated febrile children: A cohort study
Plos Medicine. 2020-09-01. Vol. 17, num. 9, p. e1003318. DOI : 10.1371/journal.pmed.1003318.Adaptive Mitigation: Identification of the Dynamic Drivers of Effective Policy during the COVID-19 Pandemic
2020-08-30.Speech Style Transfer
2020-08-14.Self-supervised learning for time series classification
2020-08-09.LaMBERT: Light and Multigranular BERT
2020-07-01.CUMULATOR — a tool to quantify and report the carbon footprint of machine learning computations and communication in academia and healthcare
2020-06-19.Privacy-preserving and Personalized Federated Machine Learning for Medical Data
2020-06-18.MLBench – Optional Semester Project
2020-06-15.Efficient second-order methods for model compression
2020-04-06.Automated Essay Scoring in Foreign Language Students Based on Deep Contextualised Word Representations
2020-03-23. LAK20 – 10th International Conference on Learning Analytics & Knowledge, Mars 23, 2020.SCAFFOLD Stochastic Controlled Averaging for Federated Learning
2020-01-01. International Conference on Machine Learning (ICML), ELECTR NETWORK, Jul 13-18, 2020.A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!
2020. 24th International Conference on Artificial Intelligence and Statistics (AISTATS), Virtual, April 13-15, 2021.Practical Low-Rank Communication Compression in Decentralized Deep Learning
2020. NeurIPS 2020 – Advances in Neural Information Processing Systems, Virtual, December 6-12, 2020.Ensemble Distillation for Robust Model Fusion in Federated Learning
2020. NeurIPS 2020 – Advances in Neural Information Processing Systems, Virtual, April 13-15, 2021.Model Fusion via Optimal Transport
2020. NeurIPS 2020 – Advances in Neural Information Processing Systems, Virtual, April 13-15, 2021.Extrapolation for Large-batch Training in Deep Learning
2020. ICML 2020 37th International Conference on Machine Learning, Virtual, July 13-18, 2020.A Unified Theory of Decentralized SGD with Changing Topology and Local Updates
2020. 37th International Conference on Machine Learning (ICML 2020), Virtual, July 13-18, 2020.The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Updates
Journal Of Machine Learning Research. 2020-01-01. Vol. 21, p. 237.Weight Erosion: An Update Aggregation Scheme for Personalized Collaborative Machine Learning
2020. MICCAI Workshop on Distributed and Collaborative Learning, Lima, Peru, Octobre 4-8, 2020. p. 160-169. DOI : 10.1007/978-3-030-60548-3_16.Accelerating Gradient Boosting Machines
2020-01-01. 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), ELECTR NETWORK, Aug 26-28, 2020. p. 516-525.Context Mover’s Distance & Barycenters: Optimal Transport of Contexts for Building Representations
2020-01-01. 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), ELECTR NETWORK, Aug 26-28, 2020.GA-Par: Dependable Microservice Orchestration Framework for Geo-Distributed Clouds
Ieee Transactions On Parallel And Distributed Systems. 2020-01-01. Vol. 31, num. 1, p. 129-143. DOI : 10.1109/TPDS.2019.2929389.Dynamic Model Pruning with Feedback
2020. 8th International Conference on Learning Representations (ICLR), Virtual Conference, Formerly Addis Ababa, Ethiopia, April 26-30, 2020.Forecasting intracranial hypertension using multi-scale waveform metrics
Physiological Measurement. 2020-01-01. Vol. 41, num. 1, p. 014001. DOI : 10.1088/1361-6579/ab6360.An Explicit Construction of Optimal Streaming Codes for Channels With Burst and Arbitrary Erasures
Ieee Transactions On Communications. 2020-01-01. Vol. 68, num. 1, p. 12-25. DOI : 10.1109/TCOMM.2019.2944372.On the Relationship between Self-Attention and Convolutional Layers
2020. Eighth International Conference on Learning Representations – ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020.Evaluating the search phase of neural architecture search
2020. ICRL 2020 Eighth International Conference on Learning Representations, Millennium Hall, Addis Ababa, ETHIOPIA, April 26-30, 2020.2019
Stochastic Zeroth-Order Optimisation Algorithms with Variance Reduction
2019-06-21.A comparison of model-parallel training methods for deep learning
2019-06-18.Software Tools for Handling Magnetically Collected Ultra-thin Sections for Microscopy
2019-06-10.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.Decentralized deep learning with arbitrary communication compression
2019. ICLR 2020 8th International Conference on Learning Representations, Addis Ababa, Ethiopia, April 26-30, 2020.Don’t Use Large Mini-Batches, Use Local SGD
2019. ICLR 2020 8th International Conference on Learning Representations, Addis Ababa, Ethiopia, April 26-30, 2020.On Linear Learning with Manycore Processors
2019-01-01. 26th International Conference on High Performance Computing, Data and Analytics (HiPCW), Hyderabad, INDIA, Dec 17-20, 2019. p. 184-194. DOI : 10.1109/HiPC.2019.00032.Communication trade-offs for Local-SGD with large step size
2019-01-01. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, CANADA, Dec 08-14, 2019.PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization
2019-01-01. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, Dec 08-14, 2019.Correlating Twitter Language with Community-Level Health Outcomes
2019-01-01. 4th Social Media Mining for Health Applications Workshop and Shared Task (SMM4H), Florence, ITALY, Aug 02, 2019. p. 71-78. DOI : 10.18653/v1/W19-3210.Unsupervised Scalable Representation Learning for Multivariate Time Series
2019-01-01. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, CANADA, Dec 08-14, 2019.Transformer-Based Multi-lingual Sentence Embeddings
2019.Efficient Greedy Coordinate Descent for Composite Problems
2019. The 22nd International Conference on Artificial Intelligence and Statistics – AISTATS 2019, Naha, Okinawa, Japan, April 16-18, 2019. p. 2887-2896.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, DOI : 10.21437/Interspeech.2019-1846.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. p. 933–939. DOI : 10.18653/v1/N19-1098.2018
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.CoCoA: A General Framework for Communication-Efficient Distributed Optimization
Journal of Machine Learning Research. 2018-07-01. Vol. 18, num. 230.Convex Optimization using Sparsified Stochastic Gradient Descent with Memory
2018-06-27.Detecting Steganography
2018-06-21.Decoupling Backpropagation using Constrained Optimization Methods
2018-06-18. ICML 2018 35th International Conference on Machine Learning, Stockholm, SWEDEN, July 10-15, 2018.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. p. 528–540. DOI : 10.18653/v1/N18-1049.Simple Unsupervised Keyphrase Extraction using Sentence Embeddings
2018-05-01. CoNLL 2018 – SIGNLL Conference on Computational Natural Language Learning. p. 221–229. DOI : 10.18653/v1/K18-1022.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. AISTATS 2018 – International Conference on Artificial Intelligence and Statistics. p. 1204-1213.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.COLA: Decentralized Linear Learning
2018-01-01. 32nd Conference on Neural Information Processing Systems (NeurIPS), Montreal, Canada, Dec 02-08, 2018.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.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.CoCoA: A General Framework for Communication-Efficient Distributed Optimization
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, num. 4, p. 813-848. 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
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. DOI : 10.3115/v1/S14-2105.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.Approximating parameterized convex optimization problems
ACM Transactions on 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
2012. European Symposia on Algorithms (ESA) 2012, Ljubljana, Slovenia, September 10-12, 2012. p. 503-514. DOI : 10.1007/978-3-642-33090-2_44.2011
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_45.2009
A Combinatorial Algorithm to Compute Regularization Paths
2009