Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Gouic, Thibaut Le"'
We define a metric in the space of positive finite positive measures that extends the 2-Wasserstein metric, i.e. its restriction to the set of probability measures is the 2-Wasserstein metric. We prove a dual and a dynamic formulation and extend the
Externí odkaz:
http://arxiv.org/abs/2303.02183
We revisit the problem of recovering a low-rank positive semidefinite matrix from rank-one projections using tools from optimal transport. More specifically, we show that a variational formulation of this problem is equivalent to computing a Wasserst
Externí odkaz:
http://arxiv.org/abs/2210.14671
We describe an efficient algorithm to compute solutions for the general two-player Blotto game on n battlefields with heterogeneous values. While explicit constructions for such solutions have been limited to specific, largely symmetric or homogeneou
Externí odkaz:
http://arxiv.org/abs/2202.07318
Autor:
Pele, Kathleen, Baccou, Jean, Daridon, Loïc, Liandrat, Jacques, Gouic, Thibaut Le, Monerie, Yann, Péralès, Frédéric
This paper is devoted to the construction of a new fast-to-evaluate model for the prediction of 2D crack paths in concrete-like microstructures. The model generates piecewise linear cracks paths with segmentation points selected using a Markov chain
Externí odkaz:
http://arxiv.org/abs/2112.13578
We consider the task of generating exact samples from a target distribution, known up to normalization, over a finite alphabet. The classical algorithm for this task is rejection sampling, and although it has been used in practice for decades, there
Externí odkaz:
http://arxiv.org/abs/2105.14166
We establish the first tight lower bound of $\Omega(\log\log\kappa)$ on the query complexity of sampling from the class of strongly log-concave and log-smooth distributions with condition number $\kappa$ in one dimension. Whereas existing guarantees
Externí odkaz:
http://arxiv.org/abs/2105.14163
This work presents an algorithm to sample from the Wasserstein barycenter of absolutely continuous measures. Our method is based on the gradient flow of the multimarginal formulation of the Wasserstein barycenter, with an additive penalization to acc
Externí odkaz:
http://arxiv.org/abs/2105.01706
Conventional wisdom in the sampling literature, backed by a popular diffusion scaling limit, suggests that the mixing time of the Metropolis-Adjusted Langevin Algorithm (MALA) scales as $O(d^{1/3})$, where $d$ is the dimension. However, the diffusion
Externí odkaz:
http://arxiv.org/abs/2012.12810
Autor:
Chewi, Sinho, Clancy, Julien, Gouic, Thibaut Le, Rigollet, Philippe, Stepaniants, George, Stromme, Austin J.
We propose a new method for smoothly interpolating probability measures using the geometry of optimal transport. To that end, we reduce this problem to the classical Euclidean setting, allowing us to directly leverage the extensive toolbox of spline
Externí odkaz:
http://arxiv.org/abs/2010.12101
Stein Variational Gradient Descent (SVGD), a popular sampling algorithm, is often described as the kernelized gradient flow for the Kullback-Leibler divergence in the geometry of optimal transport. We introduce a new perspective on SVGD that instead
Externí odkaz:
http://arxiv.org/abs/2006.02509