
Unsupervised Image Matching and Object Discovery as Optimization
Learning with complete or partial supervision is powerful but relies on ...
04/05/2019 ∙ by Huy V. Vo, et al. ∙ 40 ∙ shareread it

Partially Encrypted Machine Learning using Functional Encryption
Machine learning on encrypted data has received a lot of attention thank...
05/24/2019 ∙ by Theo Ryffel, et al. ∙ 12 ∙ shareread it

On the Global Convergence of Gradient Descent for Overparameterized Models using Optimal Transport
Many tasks in machine learning and signal processing can be solved by mi...
05/24/2018 ∙ by Lenaïc Chizat, et al. ∙ 8 ∙ shareread it

Globally Convergent Newton Methods for Illconditioned Generalized Selfconcordant Losses
In this paper, we study largescale convex optimization algorithms based...
07/03/2019 ∙ by Ulysse MarteauFerey, et al. ∙ 7 ∙ shareread it

Localized Structured Prediction
Key to structured prediction is exploiting the problem structure to simp...
06/06/2018 ∙ by Carlo Ciliberto, et al. ∙ 6 ∙ shareread it

Marginal Weighted Maximum Loglikelihood for Efficient Learning of PerturbandMap models
We consider the structuredoutput prediction problem through probabilist...
11/21/2018 ∙ by Tatiana Shpakova, et al. ∙ 6 ∙ shareread it

Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed
We study the problem of source separation for music using deep learning ...
09/03/2019 ∙ by Alexandre Défossez, et al. ∙ 5 ∙ shareread it

A General Theory for Structured Prediction with Smooth Convex Surrogates
In this work we provide a theoretical framework for structured predictio...
02/05/2019 ∙ by Alex NowakVila, et al. ∙ 4 ∙ shareread it

A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise
We consider variational inequalities coming from monotone operators, a s...
02/05/2019 ∙ by Francis Bach, et al. ∙ 4 ∙ shareread it

Massively scalable Sinkhorn distances via the Nyström method
The Sinkhorn distance, a variant of the Wasserstein distance with entrop...
12/12/2018 ∙ by Jason Altschuler, et al. ∙ 4 ∙ shareread it

Nonlinear Acceleration of Deep Neural Networks
Regularized nonlinear acceleration (RNA) is a generic extrapolation sche...
05/24/2018 ∙ by Damien Scieur, et al. ∙ 2 ∙ shareread it

Nonlinear Acceleration of CNNs
The Regularized Nonlinear Acceleration (RNA) algorithm is an acceleratio...
06/01/2018 ∙ by Damien Scieur, et al. ∙ 2 ∙ shareread it

Overcomplete Independent Component Analysis via SDP
We present a novel algorithm for overcomplete independent components ana...
01/24/2019 ∙ by Anastasia Podosinnikova, et al. ∙ 2 ∙ shareread it

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks
When optimizing overparameterized models, such as deep neural networks,...
04/30/2019 ∙ by Gauthier Gidel, et al. ∙ 2 ∙ shareread it

Fast Decomposable Submodular Function Minimization using Constrained Total Variation
We consider the problem of minimizing the sum of submodular set function...
05/27/2019 ∙ by K. S. Sesh Kumar, et al. ∙ 1 ∙ shareread it

MaxPlus Matching Pursuit for Deterministic Markov Decision Processes
We consider deterministic Markov decision processes (MDPs) and apply max...
06/20/2019 ∙ by Francis Bach, et al. ∙ 1 ∙ shareread it

AdaBatch: Efficient Gradient Aggregation Rules for Sequential and Parallel Stochastic Gradient Methods
We study a new aggregation operator for gradients coming from a minibat...
11/06/2017 ∙ by Alexandre Défossez, et al. ∙ 0 ∙ shareread it

A Generic Approach for Escaping Saddle points
A central challenge to using firstorder methods for optimizing nonconve...
09/05/2017 ∙ by Sashank J Reddi, et al. ∙ 0 ∙ shareread it

Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods
Our goal is to improve variance reducing stochastic methods through bett...
10/20/2017 ∙ by Robert M. Gower, et al. ∙ 0 ∙ shareread it

Combinatorial Penalties: Which structures are preserved by convex relaxations?
We consider the homogeneous and the nonhomogeneous convex relaxations f...
10/17/2017 ∙ by Marwa El Halabi, et al. ∙ 0 ∙ shareread it

Efficient Algorithms for Nonconvex Isotonic Regression through Submodular Optimization
We consider the minimization of submodular functions subject to ordering...
07/28/2017 ∙ by Francis Bach, et al. ∙ 0 ∙ shareread it

Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains
We consider the minimization of an objective function given access to un...
07/20/2017 ∙ by Aymeric Dieuleveut, et al. ∙ 0 ∙ shareread it

On Structured Prediction Theory with Calibrated Convex Surrogate Losses
We provide novel theoretical insights on structured prediction in the co...
03/07/2017 ∙ by Anton Osokin, et al. ∙ 0 ∙ shareread it

Optimal algorithms for smooth and strongly convex distributed optimization in networks
In this paper, we determine the optimal convergence rates for strongly c...
02/28/2017 ∙ by Kevin Scaman, et al. ∙ 0 ∙ shareread it

Stochastic Composite LeastSquares Regression with convergence rate O(1/n)
We consider the minimization of composite objective functions composed o...
02/21/2017 ∙ by Nicolas Flammarion, et al. ∙ 0 ∙ shareread it

Learning Determinantal Point Processes in Sublinear Time
We propose a new class of determinantal point processes (DPPs) which can...
10/19/2016 ∙ by Christophe Dupuy, et al. ∙ 0 ∙ shareread it

Robust Discriminative Clustering with Sparse Regularizers
Clustering highdimensional data often requires some form of dimensional...
08/29/2016 ∙ by Nicolas Flammarion, et al. ∙ 0 ∙ shareread it

Parameter Learning for Logsupermodular Distributions
We consider logsupermodular models on binary variables, which are proba...
08/18/2016 ∙ by Tatiana Shpakova, et al. ∙ 0 ∙ shareread it

PACBayesian Theory Meets Bayesian Inference
We exhibit a strong link between frequentist PACBayesian risk bounds an...
05/27/2016 ∙ by Pascal Germain, et al. ∙ 0 ∙ shareread it

Online but Accurate Inference for Latent Variable Models with Local Gibbs Sampling
We study parameter inference in largescale latent variable models. We f...
03/08/2016 ∙ by Christophe Dupuy, et al. ∙ 0 ∙ shareread it

Beyond CCA: Moment Matching for MultiView Models
We introduce three novel semiparametric extensions of probabilistic can...
02/29/2016 ∙ by Anastasia Podosinnikova, et al. ∙ 0 ∙ shareread it

Harder, Better, Faster, Stronger Convergence Rates for LeastSquares Regression
We consider the optimization of a quadratic objective function whose gra...
02/17/2016 ∙ by Aymeric Dieuleveut, et al. ∙ 0 ∙ shareread it

Rethinking LDA: moment matching for discrete ICA
We consider moment matching techniques for estimation in Latent Dirichle...
07/07/2015 ∙ by Anastasia Podosinnikova, et al. ∙ 0 ∙ shareread it

From Averaging to Acceleration, There is Only a Stepsize
We show that accelerated gradient descent, averaged gradient descent and...
04/07/2015 ∙ by Nicolas Flammarion, et al. ∙ 0 ∙ shareread it

Learning the Structure for Structured Sparsity
Structured sparsity has recently emerged in statistics, machine learning...
03/10/2015 ∙ by Nino Shervashidze, et al. ∙ 0 ∙ shareread it

On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions
We show that kernelbased quadrature rules for computing integrals can b...
02/24/2015 ∙ by Francis Bach, et al. ∙ 0 ∙ shareread it

Sequential Kernel Herding: FrankWolfe Optimization for Particle Filtering
Recently, the FrankWolfe optimization algorithm was suggested as a proc...
01/09/2015 ∙ by Simon LacosteJulien, et al. ∙ 0 ∙ shareread it

Constant Step Size LeastMeanSquare: BiasVariance Tradeoffs and Optimal Sampling Distributions
We consider the leastsquares regression problem and provide a detailed ...
11/29/2014 ∙ by Alexandre Défossez, et al. ∙ 0 ∙ shareread it

Sparse and spurious: dictionary learning with noise and outliers
A popular approach within the signal processing and machine learning com...
07/19/2014 ∙ by Rémi Gribonval, et al. ∙ 0 ∙ shareread it

SAGA: A Fast Incremental Gradient Method With Support for NonStrongly Convex Composite Objectives
In this work we introduce a new optimisation method called SAGA in the s...
07/01/2014 ∙ by Aaron Defazio, et al. ∙ 0 ∙ shareread it

On The Sample Complexity of Sparse Dictionary Learning
In the synthesis model signals are represented as a sparse combinations ...
03/20/2014 ∙ by Matthias Seibert, et al. ∙ 0 ∙ shareread it

Sample Complexity of Dictionary Learning and other Matrix Factorizations
Many modern tools in machine learning and signal processing, such as spa...
12/13/2013 ∙ by Rémi Gribonval, et al. ∙ 0 ∙ shareread it

Minimizing Finite Sums with the Stochastic Average Gradient
We propose the stochastic average gradient (SAG) method for optimizing t...
09/10/2013 ∙ by Mark Schmidt, et al. ∙ 0 ∙ shareread it

Nonstronglyconvex smooth stochastic approximation with convergence rate O(1/n)
We consider the stochastic approximation problem where a convex function...
06/10/2013 ∙ by Francis Bach, et al. ∙ 0 ∙ shareread it

LargeMargin Metric Learning for Partitioning Problems
In this paper, we consider unsupervised partitioning problems, such as c...
03/06/2013 ∙ by Rémi Lajugie, et al. ∙ 0 ∙ shareread it

Convex Relaxations for Learning Bounded Treewidth Decomposable Graphs
We consider the problem of learning the structure of undirected graphica...
12/11/2012 ∙ by K. S. Sesh Kumar, et al. ∙ 0 ∙ shareread it

A simpler approach to obtaining an O(1/t) convergence rate for the projected stochastic subgradient method
In this note, we present a new averaging technique for the projected sto...
12/10/2012 ∙ by Simon LacosteJulien, et al. ∙ 0 ∙ shareread it

Duality between subgradient and conditional gradient methods
Given a convex optimization problem and its dual, there are many possibl...
11/27/2012 ∙ by Francis Bach, et al. ∙ 0 ∙ shareread it

Convex Optimization for Parallel Energy Minimization
Energy minimization has been an intensely studied core problem in comput...
03/05/2015 ∙ by K. S. Sesh Kumar, et al. ∙ 0 ∙ shareread it

Local stability and robustness of sparse dictionary learning in the presence of noise
A popular approach within the signal processing and machine learning com...
10/02/2012 ∙ by Rodolphe Jenatton, et al. ∙ 0 ∙ shareread it