Research

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

2020

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.

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. 

2020-02-14

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.

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

2019

Mask Combination of Multi-layer Graphs for Global Structure Inference

E. Bayram; D. Thanou; E. Vural; P. Frossard 

2019-10-22. 

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.

On the convergence of stochastic primal-dual hybrid gradient

A. Alacaoglu; O. Fercoq; V. Cevher 

2019

An adaptive primal-dual framework for nonsmooth convex minimization

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

Mathematical Programming Computation. 2019. DOI : 10.1007/s12532-019-00173-3.

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. NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, 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. 

Crowdsourcing with Fairness, Diversity and Budget Constraints

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

Training DNNs with Hybrid Block Floating Point

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

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

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.

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

 

2018. NIPS’18 Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal – Canada, December 3-8, 2018.

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.

Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage

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

2017. 20th International Conference on Artificial Intelligence and Statistics (AISTATS2017), Fort Lauderdale, Florida, USA, April 20-22, 2017.

Lower Bounds on Active Learning for Graphical Model Selection

J. Scarlett; V. Cevher 

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

2016

Primal-Dual Rates and Certificates

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

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

Distribution-Matching Embedding for Visual Domain Adaptation

M. Baktashmotlagh; M. Harandi; M. Salzmann 

Journal Of Machine Learning Research. 2016. Vol. 17, p. 108.

An Efficient Streaming Algorithm for the Submodular Cover Problem

A. Norouzi Fard; A. Bazzi; M. El Halabi; I. Bogunovic; Y-P. Hsieh et al. 

2016. The Thirtieth Annual Conference on Neural Information Processing Systems (NIPS).

Learning the Number of Neurons in Deep Networks

J. M. Alvarez; M. Salzmann 

2016. Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain,

Stochastic Three-Composite Convex Minimization

A. Yurtsever; C. B. Vu; V. Cevher 

2016. 30th Conference on Neural Information Processing Systems (NIPS2016), Barcelona, Spain, December 5-10, 2016.

Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation

I. Bogunovic; J. Scarlett; A. Krause; V. Cevher 

2016. Conference on Neural Information Processing Systems (NIPS), Barcelona, December 5-10, 2016.

Convex block-sparse linear regression with expanders – provably

A. Kyrillidis; B. Bah; R. Hasheminezhad; Q. Tran Dinh; L. Baldassarre et al. 

2016. The 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016), Cadiz, Spain, May 7-11, 2016.

Time-Varying Gaussian Process Bandit Optimization

I. Bogunovic; J. Scarlett; V. Cevher 

2016. International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, May 9 – 11, 2016.

Limits on Sparse Support Recovery via Linear Sketching with Random Expander Matrices

J. Scarlett; V. Cevher 

2016. International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, May 9-11, 2016.

2015

Personalizing Product Rankings Using Collaborative Filtering on Opinion-Derived Topic Profiles

C. C. Musat; B. Faltings 

2015. Twenty-Fourth International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina, July 25–31, 2015. p. 830-836.

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

Incentives for Subjective Evaluations with Private Beliefs

G. Radanovic; B. Faltings 

2015. The 29th AAAI Conference on Artificial Intelligence (AAAI’15). p. 1014-1020.

Fast and Accurate Inference of Plackett-Luce Models

L. Maystre; M. Grossglauser 

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

Preconditioned Spectral Descent for Deep Learning

D. Carlson; E. Collins; Y-P. Hsieh; L. Carin; V. Cevher 

2015. 29-th Neural Information Processing Systems (NIPS), 2015.

A Universal Primal-Dual Convex Optimization Framework

A. Yurtsever; Q. Tran Dinh; V. Cevher 

2015. 29th Annual Conference on Neural Information Processing Systems (NIPS2015), Montreal, Canada, December 7-12, 2015.

Stochastic Spectral Descent for Restricted Boltzmann Machines.

D. Carlson; V. Cevher; L. Carin 

2015. The 18th International Conference on Artificial Intelligence and Statistics, San Diego, USA, May 9-12, 2015.

Sparsistency of $\ell_1$-Regularized $M$-Estimators

Y-H. Li; J. Scarlett; P. Ravikumar; V. Cevher 

2015. The 18th International Conference on Artificial Intelligence and Statistics, San Diego, California, USA, May 9-12, 2015.

A totally unimodular view of structured sparsity

M. El Halabi; V. Cevher 

2015. The 18th International Conference on Artificial Intelligence and Statistics, San Diego, California, USA, May 9 – 12, 2015.