Publications associées à Second-order guarantees in centralized, federated and decentralized nonconvex optimization

Adaptive data augmentation for image classification

Data augmentation is the process of generating samples by transforming training data, with the target of improving the accuracy and robustness of classifiers. In this paper, we propose a new automatic and adaptive algorithm for choosing the transformations ...

IEEE2016

Theory of representation learning in cortical neural networks

Carlos Stein Naves de Brito

Our brain continuously self-organizes to construct and maintain an internal representation of the world based on the information arriving through sensory stimuli. Remarkably, cortical areas related to different sensory modalities appear to share the same f ...

EPFL2016

Exact Algorithms for $ L ^{ 1 } $ -TV Regularization of Real-Valued or Circle-Valued Signals

Michaël Unser, Martin Kurt Storath

We consider

L ^{ 1 }

-TV regularization of univariate signals with values on the real line or on the unit circle. While the real data space leads to a convex optimization problem, the problem is nonconvex for circle-valued data. In this paper, we deriv ...

SIAM2016

The $ L ^{ 1 } $ -Potts Functional for Robust Jump-Sparse Reconstruction

Martin Kurt Storath

We investigate the nonsmooth and nonconvex

L ^{ 1 }

-Potts functional in discrete and continuous time. We show Γ-convergence of discrete

L ^{ 1 }

-Potts functionals toward their continuous counterpart and obtain a convergence statement for the corr ...

SIAM2015

Efficient Subnetwork Selection in Relay Networks

Christina Fragouli, Siddhartha Brahma, Ayan Sengupta

We consider a source that would like to communicate with a destination over a layered Gaussian relay network. We present a computationally efficient method that enables to select a near-optimal (in terms of throughput) subnetwork of a given size connecting ...

2014

Efficient Subnetwork Selection in Relay Networks

Christina Fragouli, Siddhartha Brahma, Ayan Sengupta

We consider a source that would like to communicate with a destination over a layered Gaussian relay network. We present a computationally efficient method that enables to select a near-optimal (in terms of throughput) subnetwork of a given size connecting ...

Ieee2014

Path-following gradient-based decomposition algorithms for separable convex optimization

Quoc Tran Dinh

A new decomposition optimization algorithm, called path-following gradient-based decomposition, is proposed to solve separable convex optimization problems. Unlike path-following Newton methods considered in the literature, this algorithm does not require ...

Springer Verlag2014

Geometric Variational Models for Inverse Problems in Imaging

Virginia Estellers Casas

This dissertation develops geometric variational models for different inverse problems in imaging that are ill-posed, designing at the same time efficient numerical algorithms to compute their solutions. Variational methods solve inverse problems by the fo ...

EPFL2013

Definitive Consensus for Distributed Data Inference

Leonidas Georgopoulos

Inference from data is of key importance in many applications of informatics. The current trend in performing such a task of inference from data is to utilise machine learning algorithms. Moreover, in many applications that it is either required or is pref ...

EPFL2011

Design of tensegrity structures using parametric analysis and stochastic search

Ian Smith, Landolf-Giosef-Anastasios Rhode-Barbarigos, Himanshu Jain

Tensegrity structures are lightweight structures composed of cables in tension and struts in compression. Since tensegrity systems exhibit geometrically nonlinear behavior, finding optimal structural designs is difficult. This paper focuses on the use of s ...

Springer Verlag2010

Second-order guarantees in centralized, federated and decentralized nonconvex optimization

Graph Chatbot

Chattez avec Graph Search

Adaptive data augmentation for image classification

Theory of representation learning in cortical neural networks

Exact Algorithms for $ L ^{ 1 } $ -TV Regularization of Real-Valued or Circle-Valued Signals

The $ L ^{ 1 } $ -Potts Functional for Robust Jump-Sparse Reconstruction

Efficient Subnetwork Selection in Relay Networks

Efficient Subnetwork Selection in Relay Networks

Path-following gradient-based decomposition algorithms for separable convex optimization

Geometric Variational Models for Inverse Problems in Imaging

Definitive Consensus for Distributed Data Inference

Design of tensegrity structures using parametric analysis and stochastic search

Theory of representation learning in cortical neural networks

The $ L ^{ 1 } $ -Potts Functional for Robust Jump-Sparse Reconstruction

Efficient Subnetwork Selection in Relay Networks

Efficient Subnetwork Selection in Relay Networks

Design of tensegrity structures using parametric analysis and stochastic search

Path-following gradient-based decomposition algorithms for separable convex optimization

Definitive Consensus for Distributed Data Inference

Exact Algorithms for $ L ^{ 1 } $ -TV Regularization of Real-Valued or Circle-Valued Signals

Geometric Variational Models for Inverse Problems in Imaging

Adaptive data augmentation for image classification