Research

Research is a major part in the Machine Learning field. With multiple publications each year, we are standing within the best.

2021

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

S. U. Stich; A. Mohtashami; M. Jaggi 

2021. 24th International Conference on Artificial Intelligence and Statistics (AISTATS), Virtual, April 13-15, 2021.

Lifelong Machine Learning with Data Efficiency and Knowledge Retention

F. Mi / B. Faltings (Dir.)  

Lausanne, EPFL, 2021. 

The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets

Y-P. Hsieh; P. Mertikopoulos; V. Cevher 

2021. 38th International Conference on Machine Learning (ICML 2021), Online, July 18-24, 2021. p. 4337-4348.

2020

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

K. Parameswaran; Y-T. Huang; Y-P. Hsieh; P. T. Y. Rolland; C. Shi et al. 

2020-11-05

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

A. Carlier; M. Danelljan; A. Alahi; R. Timofte 

2020-09-29. NeurIPS 2020 34th Conference on Neural Information Processing Systems, Vancouver, Canada, December 6-12, 2020.

CUMULATOR — a tool to quantify and report the carbon footprint of machine learning computations and communication in academia and healthcare

T. Trébaol 

2020-06-19.

Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

F. Latorre; P. T. Y. Rolland; V. Cevher 

2020-04-26. 8th International Conference on Learning Representations, Addis Ababa, ETHIOPIA, April 26-30, 2020.

Collaborative Sampling in Generative Adversarial Networks

Y. Liu; P. A. Kothari; A. Alahi 

2020-02-11. Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), New York, New York, USA, February 7-12, 2020. p. 4948-4956. DOI : 10.1609/aaai.v34i04.5933.

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!

D. Kovalev; A. Koloskova; M. Jaggi; P. Richtarik; U. S. Sitch 

2020. 24th International Conference on Artificial Intelligence and Statistics (AISTATS), Virtual, April 13-15, 2021.

Practical Low-Rank Communication Compression in Decentralized Deep Learning

T. Vogels; S. P. R. Karimireddy; M. Jaggi 

2020. NeurIPS 2020 – Advances in Neural Information Processing Systems, Virtual, December 6-12, 2020.

Ensemble Distillation for Robust Model Fusion in Federated Learning

T. Lin; L. Kong; S. U. Stich; M. Jaggi 

2020. NeurIPS 2020 – Advances in Neural Information Processing Systems, Virtual, April 13-15, 2021.

Model Fusion via Optimal Transport

S. P. Singh; M. Jaggi 

2020. NeurIPS 2020 – Advances in Neural Information Processing Systems, Virtual, April 13-15, 2021.

Extrapolation for Large-batch Training in Deep Learning

T. Lin; L. Kong; S. U. Stich; M. Jaggi 

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

A. Koloskova; N. Loizou; S. Boreiri; M. Jaggi; S. U. Stich 

2020. 37th International Conference on Machine Learning (ICML 2020), Virtual, July 13-18, 2020.

Detection of Similar Languages and Dialects Using Deep Supervised Autoencoders

S. Parida; E. VILLATORO-℡LO; S. Kumar; M. Fabien; P. Motlicek 

2020. 17th International Conference on Natural Language Processing, 1-7 December 2020.

BertAA: BERT fine-tuning for Authorship Attribution

M. Fabien; E. VILLATORO-℡LO; P. Motlicek; S. Parida 

2020. 17th International Conference on Natural Language Processing, 1-7 December 2020.

UCLID-Net: Single View Reconstruction in Object Space

B. Guillard; E. Remelli; P. Fua 

2020. 34th Conference on Neural Information Processing Systems, Virtual, December 6-12, 2020.

Neural Anisotropy Directions

G. Ortiz Jimenez; A. Modas; S. M. Moosavi Dezfooli; P. Frossard 

2020. NeurIPS 2020 34th Conference on Neural Information Processing Systems, Vancouver, Canada, December 6-12, 2020.

Hold me tight! Influence of discriminative features on deep network boundaries

G. Ortiz Jimenez; A. Modas; S. M. Moosavi Dezfooli; P. Frossard 

2020. Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020), [Virtual only], December 6-12, 2020.

Conditional gradient methods for stochastically constrained convex minimization

M-L. Vladarean; A. Alacaoglu; Y-P. Hsieh; V. Cevher 

2020. 37th International Conference on Machine Learning (ICML), virtual, July 12-18, 2020.

Efficient Proximal Mapping of the 1-path-norm of Shallow Networks

F. Latorre; P. T. Y. Rolland; S. N. Hallak; V. Cevher 

2020. 37th International Conference on Machine Learning (ICML), Virtual, July 13-18, 2020.

A new regret analysis for Adam-type algorithms

A. Alacaoglu; Y. Malitsky; P. Mertikopoulos; V. Cevher 

2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 13-18, 2020.

Adaptive Gradient Descent without Descent

Y. Malitsky; K. Mishchenko 

2020. 37th International Conference on Machine Learning (ICML 2020), Virtual, July 12-18, 2020.

Double-Loop Unadjusted Langevin Algorithm

P. Rolland; A. Eftekhari; A. Kavis; V. Cevher 

2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 12-18, 2020.

What graph neural networks cannot learn: depth vs width

A. Loukas 

2020. International Conference on Learning Representations, Addis Ababa, Ethiopia, April 26-30, 2020.

On the Relationship between Self-Attention and Convolutional Layers

J-B. Cordonnier; A. Loukas; M. Jaggi 

2020. Eighth International Conference on Learning Representations – ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020.

Domain-Adaptive Multibranch Networks

R. Bermúdez Chacón; M. Salzmann; P. Fua 

2020. International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, April 26-30, 2020.

An adaptive primal-dual framework for nonsmooth convex minimization

Q. Tran-Dinh; A. Alacaoglu; O. Fercoq; V. Cevher 

Mathematical Programming Computation. 2020. Vol. 12, p. 451–491. DOI : 10.1007/s12532-019-00173-3.

2019

Extrapolating Paths with Graph Neural Networks

J-B. Cordonnier; A. Loukas 

2019-08-10. International Joint Conference on Artificial Intelligence, Macao, China, August 10-16, 2019.

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

A. Koloskova; S. U. Stich; M. Jaggi 

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

Memory Efficient Max Flow for Multi-Label Submodular MRFs

T. Ajanthan; R. Hartley; M. Salzmann 

IEEE Transactions On Pattern Analysis And Machine Intelligence (PAMI). 2019-04-01. Vol. 41, num. 4, p. 886-900. DOI : 10.1109/TPAMI.2018.2819675.

Decentralized deep learning with arbitrary communication compression

A. Koloskova; T. Lin; S. U. Stich; M. Jaggi 

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

T. Lin; S. U. Stich; K. K. Patel; M. Jaggi 

2019. ICLR 2020 8th International Conference on Learning Representations, Addis Ababa, Ethiopia, April 26-30, 2020.

On the convergence of stochastic primal-dual hybrid gradient

A. Alacaoglu; O. Fercoq; V. Cevher 

2019

Stochastic Frank-Wolfe for Composite Convex Minimization

F. Locatello; A. Yurtsever; O. Fercoq; V. Cevher 

2019. NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, December 8-14, 2019.

An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints

M. F. Sahin; A. Eftekhari; A. Alacaoglu; F. R. Latorre Gomez; V. Cevher 

2019. NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, December 8-14, 2019.

Fast and Provable ADMM for Learning with Generative Priors

F. R. Latorre Gomez; A. Eftekhari; V. Cevher 

2019. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 8-14, 2019.

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

A. Kavis; K. Y. Levy; F. Bach; V. Cevher 

2019. NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, December 8-14, 2019.

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

S. P. R. Karimireddy; Q. Rebjock; S. U. Stich; M. Jaggi 

2019. 36th International Conference on Machine Learning (ICML) 2019, Long Beach, USA, June 9-15, 2019. p. 3252-3261.

Overcoming Multi-model Forgetting

Y. Benyahia; K. Yu; K. B. Smires; M. Jaggi; A. C. Davison et al. 

2019. ICML 2019 – 36th International Conference on Machine Learning, Long Beach, California, USA, June 09-15, 2019. p. 594-603.

Graph Reduction with Spectral and Cut Guarantees

A. Loukas 

Journal of Machine Learning Research. 2019. Vol. 20, num. 116, p. 1-42.

Walrasian Dynamics in Multi-unit Markets

S. Branzei; A. Filos-Ratsikas 

2019. 33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, HI, Jan 27-Feb 01, 2019. p. 1812-1819.

Personalized Peer Truth Serum for Eliciting Multi-Attribute Personal Data

N. Goel; B. Faltings 

2019. 

Generating Artificial Data for Private Deep Learning

A. Triastcyn; B. Faltings 

2019. 

Deep Bayesian Trust : A Dominant and Fair Incentive Mechanism for Crowd

N. Goel; B. Faltings 

2019. 

Context-Tree Recommendation vs Matrix-Factorization: Algorithm Selection and Live Users Evaluation

S. Martin; B. Faltings; V. Schickel 

2019. 33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, HI, Jan 27-Feb 01, 2019. p. 9534-9540.

Anytime Heuristic for Weighted Matching Through Altruism-Inspired Behavior

P. Danassis; A. Filos-Ratsikas; B. Faltings 

2019. 

Applications of Artificial Intelligence to Computational Chemistry

N. J. Browning / U. Röthlisberger (Dir.)  

Lausanne, EPFL, 2019. 

On Certifying Non-Uniform Bounds against Adversarial Attacks

C. Liu; R. Tomioka; V. Cevher 

2019. 36th International Conference on Machine Learning (ICML)’2019, Long Beach, USA, June 9-15, 2019.

[Re] Meta learning with differentiable closed-form solvers

A. Devos; S. Chatel; M. Grossglauser 

The ReScience journal C. 2019. 

Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator

A. Yurtsever; S. Sra; V. Cevher 

2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.

Efficient learning of smooth probability functions from Bernoulli tests with guarantees.

P. T. Y. Rolland; A. Kavis; A. Immer; A. Singla; V. Cevher 

2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.

A Conditional Gradient-Based Augmented Lagrangian Framework

A. Yurtsever; O. Fercoq; V. Cevher 

2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.

Almost surely constrained convex optimization

O. Fercoq; A. Alacaoglu; I. Necoara; V. Cevher 

2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.

Iterative Classroom Teaching

S. T. Yeo; K. Parameswaran; A. Singla; M. Arpit; T. L. C. Asselborn et al. 

2019. 33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, Hawaii, USA, January 27 – February 1, 2019. p. 5684-5692.

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. NeurIPS 2018 – 32nd Annual Conference on Neural Information Processing Systems, Montréal, Canada, December 2-8, 2018.

A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming

A. Yurtsever; O. Fercoq; F. Locatello; V. Cevher 

2018-07-11. the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, July 10-15, 2018.

Spectrally approximating large graphs with smaller graphs

A. Loukas; P. Vandergheynst 

2018-07-10. International Conference in Machine Learning (ICML), Stockholmsmässan, Sweden, July 10-15, 2018.

Online Adaptive Methods, Universality and Acceleration

K. Y. Levy; A. Yurtsever; V. Cevher 

2018-07-04. 32nd Conference on Neural Information Processing Systems conference (NIPS 2018), Montreal, Canada, December 3-8, 2018.

Decoupling Backpropagation using Constrained Optimization Methods

A. Gotmare; V. Thomas; J. M. Brea; M. Jaggi 

2018-06-18. ICML 2018 35th International Conference on Machine Learning, Stockholm, SWEDEN, July 10-15, 2018.

Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods

J. Lin; V. Cevher 

2018-06-08. 35th International Conference on Machine Learning, Stockholm, Sweden, July 10 -15, 2018.

On Matching Pursuit and Coordinate Descent

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

2018-05-01. ICML 2018 – 35th International Conference on Machine Learning.

Personalized and Private Peer-to-Peer Machine Learning

A. Bellet; R. Guerraoui; M. Taziki; M. Tommasi 

2018-04-09. AISTATS.

Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces

J. Lin; V. Cevher 

2018-03-11. 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, July 10-15, 2018.

A Distributed Second-Order Algorithm You Can Trust

C. Mendler-Dünner; A. Lucchi; M. Gargiani; Y. A. Bian; T. Hofmann et al. 

2018. 35th International Conference on Machine Learning (ICML 2018), Stockholm, Sweden, 10-15 July 2018. p. 1358-1366.

Asynchronous Byzantine Machine Learning (the case of SGD)

G. Damaskinos; E. M. El Mhamdi; R. Guerraoui; R. Patra; M. Taziki 

2018. 35th International Conference on Machine Learning, Stockholm, SWEDEN, July 10-15, 2018. p. 1145-1154.

Non-Discriminatory Machine Learning through Convex Fairness Criteria

N. Goel; M. Yaghini; B. Faltings 

2018. 32nd AAAI Conference on Artificial Intelligence / 30th Innovative Applications of Artificial Intelligence Conference / 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, LA, February 02-07, 2018. p. 3029-3036.

Neural Tanget Kernel: Convergence and Generalization in Neural Networks

A. U. Jacot-Guillarmod; F. R. Gabriel; C. Hongler 

2018. 32nd International Conference on Neural Information Processing Systems, Montréal – Canada, December 3-8, 2018. p. 8580-8589.

Online Adaptive Methods, Universality and Acceleration

K. Y. Levy; A. Yurtsever; V. Cevher 

2018-01-01. 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, CANADA, Dec 02-08, 2018.

Mirrored Langevin Dynamics

Y-P. Hsieh; A. Kavis; P. Rolland; V. Cevher 

2018-01-01. 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, CANADA, Dec 02-08, 2018.

Training DNNs with Hybrid Block Floating Point

M. Drumond; T. Lin; M. Jaggi; B. Falsafi 

2018-01-01. NeurIPS 2018 – 32nd Conference on Neural Information Processing Systems, Montreal, CANADA, Dec 02-08, 2018.

Adversarially Robust Optimization with Gaussian Processes

I. Bogunovic; J. Scarlett; S. Jegelka; V. Cevher 

2018. Conference on Neural Information Processing Systems (NIPS), Montreal, 2018.

Finding Mixed Nash Equilibria of Generative Adversarial Networks

Y-P. Hsieh; C. Liu; V. Cevher 

2018. IEEE International Conference on Machine Learning (ICML)’ 2019, Long Beach, USA, June 9-15, 2019.

The Hidden Vulnerability of Distributed Learning in Byzantium

E. M. El Mhamdi; R. Guerraoui; S. L. A. Rouault 

2018. International Conference on Machine Learning, Stockholm, Sweden, July 10-15, 2018.

Fast Approximate Spectral Clustering for Dynamic Networks

L. Martin; A. Loukas; P. Vandergheynst 

2018. International Conference in Machine Learning (ICML), Stockholmsmässan, Sweden, July 10-15, 2018.

Beyond Sharing Weights for Deep Domain Adaptation

A. Rozantsev; M. Salzmann; P. Fua 

IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018. Vol. 41, num. 4, p. 801-814. DOI : 10.1109/TPAMI.2018.2814042.

Dimension-free Information Concentration via Exp-Concavity

Y-P. Hsieh; V. Cevher 

2018. Algorithmic Learning Theory (ALT) 2018, Lanzarote, Spain, April 7-9, 2018.

Robust Maximization of Non-Submodular Objectives

I. Bogunovic; J. Zhao; V. Cevher 

2018. International Conference on Artificial Intelligence and Statistics (AISTATS), Lanzarote, Canary Islands, April, 9-11, 2018.

High Dimensional Bayesian Optimization via Additive Models with Overlapping Groups

P. T. Y. Rolland; J. Scarlett; I. Bogunovic; V. Cevher 

2018. AISTATS, Lanzarote, Spain, April, 9-11, 2018.

Stochastic Three-Composite Convex Minimization with a Linear Operator

R. Zhao; V. Cevher 

2018. 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018, Lanzarotte, Spain, April 9-11, 2018.

Let’s be honest: An optimal no-regret framework for zero-sum games

E. Asadi Kangarshahi; Y-P. Hsieh; M. F. Sahin; V. Cevher 

2018. 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, July 10-15, 2018.

2017

Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data

J. A. Tropp; A. Yurtsever; M. Udell; V. Cevher 

2017-12-04. 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, California, USA, December 4-9, 2017.

Deep Subspace Clustering Networks

P. Ji; T. Zhang; H. Li; M. Salzmann; I. Reid 

2017. Neural Information Processing Systems (NIPS).

Compression-aware Training of Deep Networks

J. Alvarez; M. Salzmann 

2017. Neural Information Processing Systems (NIPS).

Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach

S. Mitrovic; I. Bogunovic; A. Norouzi Fard; J. Tarnawski; V. Cevher 

2017. Conference on Neural Information Processing Systems (NIPS), Long Beach,

Safe Adaptive Importance Sampling

S. U. Stich; A. Raj; M. Jaggi 

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

Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization

A. Alacaoglu; Q. Tran-Dinh; O. Fercoq; V. Cevher 

2017. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, December 4-9, 2017.

Phase Transitions in the Pooled Data Problem

J. Scarlett; V. Cevher 

2017. Conference on Neural Information Processing Systems (NIPS), Long Beach, California, December 2017.

Combinatorial Penalties: Which structures are preserved by convex relaxations?

M. El Halabi; F. Bach; V. Cevher 

2017. 21st International Conference on Artificial Intelligence and Statistics (AISTATS), Lanzarotte, Spain, April 9-11, 2017.

On The Robustness of a Neural Network

E. M. El Mhamdi; R. Guerraoui; S. L. A. Rouault 

2017. 36th IEEE International Symposium on Reliable Distributed Systems, Hong Kong, September 26-29, 2017.

Approximate Steepest Coordinate Descent

S. U. Stich; A. Raj; M. Jaggi 

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

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

E. M. El Mhamdi; H. Hendrikx; R. Guerraoui; A. D. O. Maurer 

2017

Joint Dimensionality Reduction and Metric Learning: A Geometric Take

M. Harandi; M. Salzmann; R. Hartley 

2017. International Conference on Machine Learning (ICML).

ChoiceRank: Identifying Preferences from Node Traffic in Networks

L. Maystre; M. Grossglauser 

2017. International Conference on Machine Learning, Sydney, Australia, August 6-11, 2017.

Just Sort It! A Simple and Effective Approach to Active Preference Learning

L. Maystre; M. Grossglauser 

2017. International Conference on Machine Learning, Sydney, Australia, August 6-11, 2017.

Robust Submodular Maximization: A Non-Uniform Partitioning Approach

I. Bogunovic; S. Mitrovic; J. Scarlett; V. Cevher 

2017. The 34th International Conference on Machine Learning (ICML), Sydney, 2017.

Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization

J. Scarlett; I. Bogunovic; V. Cevher 

2017. Conference on Learning Theory (COLT)Conference on Learning Theory (COLT), AmsterdamAmsterdam, Netherlands, July 2017July, 7-10, 2017.

How close are the eigenvectors and eigenvalues of the sample and actual covariance matrices?

A. Loukas 

2017. International Conference on Machine Learning (ICML), Sydney, August 8-11, 2017.

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.