BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration

M. El Helou; S. Süsstrunk 

Local plasticity rules can learn deep representations using self-supervised contrastive predictions

B. A. Illing; J. Ventura; G. Bellec; W. Gerstner 

Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)

E. M. El Mhamdi; S. Farhadkhani; R. Guerraoui; A. H. A. Guirguis; L. N. Hoang et al. 

What can linearized neural networks actually say about generalization?

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

Machine Learning Uncovers Aerosol Size Information From Chemistry and Meteorology to Quantify Potential Cloud-Forming Particles

A. A. Nair; F. Yu; P. Campuzano-Jost; P. J. DeMott; E. J. T. Levin et al. 

GARFIELD: System Support for Byzantine Machine Learning (Regular Paper)

R. Guerraoui; A. Guirguis; J. Plassmann; A. Ragot; S. Rouault 

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

B. Şimşek; F. Ged; A. Jacot; F. Spadaro; C. Hongler et al. 

Fitting summary statistics of neural data with a differentiable spiking network simulator

G. Bellec; S. Wang; A. Modirshanechi; J. M. Brea; W. Gerstner 

Mixed Nash Equilibria in the Adversarial Examples Game

L. Meunier; M. Scetbon; R. Pinot; J. Atif; Y. Chevaleyre 

A Plug-and-Play Deep Image Prior

Z. Sun; F. Latorre; T. Sanchez; V. Cevher 

Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities

K. Antonakopoulos; T. M. Pethick; A. Kavis; P. Mertikopoulos; V. Cevher 

Convergence of adaptive algorithms for constrained weakly convex optimization

A. Alacaoglu; Y. Malitskyi; V. Cevher 

STORM+: Fully Adaptive SGD with Momentum for Nonconvex Optimization

K. Levy; A. Kavis; V. Cevher 

A first-order primal-dual method with adaptivity to local smoothness

M-L. Vladarean; Y. Malitsky; V. Cevher 

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

L. Viano; Y-T. Huang; K. Parameswaran; A. Weller; V. Cevher 

The Effect of the Intrinsic Dimension on the Generalization of Quadratic Classifiers

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

Subquadratic Overparameterization for Shallow Neural Networks

C. Song; A. Ramezani-Kebrya; T. Pethick; A. Eftekhari; V. Cevher 

Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach

N. Hallak; P. Mertikopoulos; V. Cevher 

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

S. U. Stich; A. Mohtashami; M. Jaggi 

Lifelong Machine Learning with Data Efficiency and Knowledge Retention

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

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

FeGAN: Scaling Distributed GANs

R. Guerraoui; A. Guirguis; A-M. Kermarrec; E. L. Merrer 

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. 

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

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

Genuinely Distributed Byzantine Machine Learning

E. M. El Mhamdi; R. Guerraoui; A. H. A. Guirguis; L. N. Hoang; S. L. A. Rouault 

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

T. Trébaol 

Lipschitz constant estimation for Neural Networks via sparse polynomial optimization

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

Collaborative Sampling in Generative Adversarial Networks

Y. Liu; P. A. Kothari; A. Alahi 

On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems

P. Mertikopoulos; N. Hallak; A. Kavis; V. Cevher 

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

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

Practical Low-Rank Communication Compression in Decentralized Deep Learning

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

Ensemble Distillation for Robust Model Fusion in Federated Learning

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

Model Fusion via Optimal Transport

S. P. Singh; M. Jaggi 

Extrapolation for Large-batch Training in Deep Learning

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

A Unified Theory of Decentralized SGD with Changing Topology and Local Updates

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

Detection of Similar Languages and Dialects Using Deep Supervised Autoencoders

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

BertAA: BERT fine-tuning for Authorship Attribution

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

Vulnerability Analysis of Face Morphing Attacks from Landmarks and Generative Adversarial Networks

E. Sarkar; P. Korshunov; L. Colbois; S. Marcel 

UCLID-Net: Single View Reconstruction in Object Space

B. Guillard; E. Remelli; P. Fua 

Neural Anisotropy Directions

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

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

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

Conditional gradient methods for stochastically constrained convex minimization

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

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

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

A new regret analysis for Adam-type algorithms

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

Adaptive Gradient Descent without Descent

Y. Malitsky; K. Mishchenko 

Double-Loop Unadjusted Langevin Algorithm

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

What graph neural networks cannot learn: depth vs width

A. Loukas 

On the Relationship between Self-Attention and Convolutional Layers

J-B. Cordonnier; A. Loukas; M. Jaggi 

Domain-Adaptive Multibranch Networks

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

An adaptive primal-dual framework for nonsmooth convex minimization

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

Personalized Peer Truth Serum for Eliciting Multi-Attribute Personal Data

N. Goel; B. Faltings 

Extrapolating Paths with Graph Neural Networks

J-B. Cordonnier; A. Loukas 

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

A. Koloskova; S. U. Stich; M. Jaggi 

Memory Efficient Max Flow for Multi-Label Submodular MRFs

T. Ajanthan; R. Hartley; M. Salzmann 

AGGREGATHOR: Byzantine Machine Learning via Robust Gradient Aggregation

G. Damaskinos; E. M. El Mhamdi; R. Guerraoui; A. H. A. Guirguis; S. L. A. Rouault 

Decentralized deep learning with arbitrary communication compression

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

Don’t Use Large Mini-Batches, Use Local SGD

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

On the convergence of stochastic primal-dual hybrid gradient

A. Alacaoglu; O. Fercoq; V. Cevher 

Stochastic Frank-Wolfe for Composite Convex Minimization

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

An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints

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

Fast and Provable ADMM for Learning with Generative Priors

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

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

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

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

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

Overcoming Multi-model Forgetting

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

Graph Reduction with Spectral and Cut Guarantees

A. Loukas 

Walrasian Dynamics in Multi-unit Markets

S. Branzei; A. Filos-Ratsikas 

Generating Artificial Data for Private Deep Learning

A. Triastcyn; B. Faltings 

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

N. Goel; B. Faltings 

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

S. Martin; B. Faltings; V. Schickel 

Anytime Heuristic for Weighted Matching Through Altruism-Inspired Behavior

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

Applications of Artificial Intelligence to Computational Chemistry

On Certifying Non-Uniform Bounds against Adversarial Attacks

C. Liu; R. Tomioka; V. Cevher 

[Re] Meta learning with differentiable closed-form solvers

A. Devos; S. Chatel; M. Grossglauser 

Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator

A. Yurtsever; S. Sra; V. Cevher 

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

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

A Conditional Gradient-Based Augmented Lagrangian Framework

A. Yurtsever; O. Fercoq; V. Cevher 

Almost surely constrained convex optimization

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

Iterative Classroom Teaching

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

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 

Sparsified SGD with Memory

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

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

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

Spectrally approximating large graphs with smaller graphs

A. Loukas; P. Vandergheynst 

Online Adaptive Methods, Universality and Acceleration

K. Y. Levy; A. Yurtsever; V. Cevher 

Decoupling Backpropagation using Constrained Optimization Methods

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

Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods

J. Lin; V. Cevher 

On Matching Pursuit and Coordinate Descent

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

Personalized and Private Peer-to-Peer Machine Learning

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

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

J. Lin; V. Cevher 

A Distributed Second-Order Algorithm You Can Trust

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

Asynchronous Byzantine Machine Learning (the case of SGD)

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

Non-Discriminatory Machine Learning through Convex Fairness Criteria

N. Goel; M. Yaghini; B. Faltings 

Neural Tanget Kernel: Convergence and Generalization in Neural Networks

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

Online Adaptive Methods, Universality and Acceleration

K. Y. Levy; A. Yurtsever; V. Cevher 

Mirrored Langevin Dynamics

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

Training DNNs with Hybrid Block Floating Point

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

Adversarially Robust Optimization with Gaussian Processes

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

Finding Mixed Nash Equilibria of Generative Adversarial Networks

Y-P. Hsieh; C. Liu; V. Cevher 

The Hidden Vulnerability of Distributed Learning in Byzantium

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

Fast Approximate Spectral Clustering for Dynamic Networks

L. Martin; A. Loukas; P. Vandergheynst 

Beyond Sharing Weights for Deep Domain Adaptation

A. Rozantsev; M. Salzmann; P. Fua