Publications associées à Convergence without Convexity: Sampling, Optimization, and Games

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

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

Fast K-Means with Accurate Bounds

François Fleuret, James Peter Newling

We propose a novel accelerated exact

k

-means algorithm, which outperforms the current state-of-the-art low-dimensional algorithm in 18 of 22 experiments, running up to 3

\times

faster. We also propose a general improvement of existing state-of-the-art a ...

Idiap2016

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

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 Gamma-convergence of discrete L-1-Potts functionals toward their continuous counterpart and obtain a convergence statement for the corresponding minimi ...

Siam Publications2015

Source Localization and Tracking in Non-Convex Rooms

Martin Vetterli, Ivan Dokmanic, Orhan Öçal

We consider the estimation of the acoustic source position in a known room from recordings by a microphone array. We propose an algorithm that does not require the room to be convex, nor a line-of-sight path between the microphone array and the source to b ...

Ieee2014

Rigorous optimization recipes for sparse and low rank inverse problems with applications in data sciences

Anastasios Kyrillidis

Many natural and man-made signals can be described as having a few degrees of freedom relative to their size due to natural parameterizations or constraints; examples include bandlimited signals, collections of signals observed from multiple viewpoints in ...

EPFL2014

A Branch-and-Price Algorithm to Solve the Integrated Berth Allocation and Yard Assignment Problem in Bulk Ports

Michel Bierlaire, Tomas Robenek, Nitish Umang

In this research, two crucial optimization problems of berth allocation and yard assignment in the context of bulk ports are studied. We discuss how these problems are interrelated and can be combined and solved as a single large scale optimization problem ...

Elsevier Science Bv2014

Learning with tensors: a framework based on convex optimization and spectral regularization

Quoc Tran Dinh

We present a framework based on convex optimization and spectral regularization to perform learning when feature observations are multidimensional arrays (tensors). We give a mathematical characterization of spectral penalties for tensors and analyze a uni ...

Springer2014

Right-Protected Data Publishing with Provable Distance-Based Mining

Michail Vlachos, Nikolaos Freris

Protection of one's intellectual property is a topic with important technological and legal facets. We provide mechanisms for establishing the ownership of a dataset consisting of multiple objects. The algorithms also preserve important properties of the d ...

Ieee Computer Soc2014

Probabilistic inverse reinforcement learning in unknown environments

Christos Dimitrakakis

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents are trying to sol ...

2013

Convergence without Convexity: Sampling, Optimization, and Games

Graph Chatbot

Chattez avec Graph Search

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

Fast K-Means with Accurate Bounds

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

The L-1-Potts Functional For Robust Jump-Sparse Reconstruction

Source Localization and Tracking in Non-Convex Rooms

Rigorous optimization recipes for sparse and low rank inverse problems with applications in data sciences

A Branch-and-Price Algorithm to Solve the Integrated Berth Allocation and Yard Assignment Problem in Bulk Ports

Learning with tensors: a framework based on convex optimization and spectral regularization

Right-Protected Data Publishing with Provable Distance-Based Mining

Probabilistic inverse reinforcement learning in unknown environments

Fast K-Means with Accurate Bounds

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

Right-Protected Data Publishing with Provable Distance-Based Mining

A Branch-and-Price Algorithm to Solve the Integrated Berth Allocation and Yard Assignment Problem in Bulk Ports

Learning with tensors: a framework based on convex optimization and spectral regularization

Source Localization and Tracking in Non-Convex Rooms

Rigorous optimization recipes for sparse and low rank inverse problems with applications in data sciences

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

Probabilistic inverse reinforcement learning in unknown environments

The L-1-Potts Functional For Robust Jump-Sparse Reconstruction