Publication
Detection over diffusion networks: Asymptotic tools for performance prediction and simulation
Publications associées (32)
Mirrored Langevin Dynamics
Volkan Cevher, Paul Thierry Yves Rolland, Ya-Ping Hsieh, Ali Kavis
We consider the problem of sampling from constrained distributions, which has posed significant challenges to both non-asymptotic analysis and algorithmic design. We propose a unified framework, which is inspired by the classical mirror descent, to derive ...
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2018Mirrored Langevin Dynamics
Volkan Cevher, Paul Thierry Yves Rolland, Ya-Ping Hsieh, Ali Kavis
We consider the problem of sampling from constrained distributions, which has posed significant challenges to both non-asymptotic analysis and algorithmic design. We propose a unified framework, which is inspired by the classical mirror descent, to derive ...
2018SIPS: Unsupervised Succinct Interest Points
Davide Scaramuzza, Titus Cieslewski
Detecting interest points is a key component of vision-based estimation algorithms, such as visual odometry or visual SLAM. Classically, interest point detection has been done with methods such as Harris, FAST, or DoG. Recently, better detectors have been ...
2018Driven-dissipative quantum Monte Carlo method for open quantum systems
Vincenzo Savona, Alexandra Nagy
We develop a real-time full configuration-interaction quantum Monte Carlo approach to model driven-dissipative open quantum systems with Markovian system-bath coupling. The method enables stochastic sampling of the Liouville–von Neumann time evolution of t ...
2018Importance Sampling Tree for Large-scale Empirical Expectation
François Fleuret, Olivier Canévet, Cijo Jose
We propose a tree-based procedure inspired by the Monte-Carlo Tree Search that dynamically modulates an importance-based sampling to prioritize computation, while getting unbiased estimates of weighted sums. We apply this generic method to learning on very ...
2016On the sensitivity of buildings to climate
Building simulation requires a large number of uncertain inputs and parameters. These include quantities that may be known with reasonable confidence, like the thermal properties of materials and building dimensions, but also inputs whose correct values ca ...
EPFL2016Sampling-Based Nuclear Data Uncertainty Quantification for Continuous Energy Monte Carlo Codes
The goal of the present PhD research is to establish a methodology of nuclear data uncertainty quantification (NDUQ) for MCNPX, the continuous-energy Monte-Carlo (M-C) code. The high fidelity (continuous-energy treatment and flexible geometry modelling) of ...
EPFL2015Wavelet-variance-based estimation for composite stochastic processes
Jan Skaloud, Stéphane Guerrier, Yannick Stebler
This article presents a new estimation method for the parameters of a time series model. We consider here composite Gaussian processes that are the sum of independent Gaussian processes which, in turn, explain an important aspect of the time series, as is ...
Amer Statistical Assoc2013Dispersion operators and resistant second-order functional data analysis
Inferences related to the second-order properties of functional data, as expressed by covariance structure, can become unreliable when the data are non-Gaussian or contain unusual observations. In the functional setting, it is often difficult to identify a ...
Oxford University Press2012Rotational Features Extraction for Ridge Detection
Michaël Unser, Pascal Fua, François Fleuret, François Aguet, Germán González Serrano, Fethallah Benmansour
State-of-the-art approaches to detecting ridge-like structures in images rely on filters designed to respond to locally linear intensity features. While these approaches may be optimal for ridges whose appearance is close to being ideal, their performance ...
Institute of Electrical and Electronics Engineers2011