Zobrazeno 1 - 10
of 796
pro vyhledávání: '"Stromme, P."'
Geometric tempering is a popular approach to sampling from challenging multi-modal probability distributions by instead sampling from a sequence of distributions which interpolate, using the geometric mean, between an easier proposal distribution and
Externí odkaz:
http://arxiv.org/abs/2410.09697
Autor:
Stromme, Austin J.
Motivated by the manifold hypothesis, which states that data with a high extrinsic dimension may yet have a low intrinsic dimension, we develop refined statistical bounds for entropic optimal transport that are sensitive to the intrinsic dimension of
Externí odkaz:
http://arxiv.org/abs/2306.03398
Publikováno v:
ACS Omega, Vol 9, Iss 12, Pp 13852-13859 (2024)
Externí odkaz:
https://doaj.org/article/f9f4bdfea92e424f872be6a302dfed75
Autor:
Rigollet, Philippe, Stromme, Austin J.
We study the sample complexity of entropic optimal transport in high dimensions using computationally efficient plug-in estimators. We significantly advance the state of the art by establishing dimension-free, parametric rates for estimating various
Externí odkaz:
http://arxiv.org/abs/2206.13472
Autor:
Niklasson, Gunnar A., Niklasson, Sara L., Notfors, Celina, Wang, Junxin, Stromme, Maria, Arhammar, Cecilia
Sunscreen lotions are used to protect the skin from damage due to solar ultraviolet (UV) radiation. The active UV blocking components can be organic molecules or inorganic particles, for example TiO2. While both in vivo and in vitro methods exist for
Externí odkaz:
http://arxiv.org/abs/2204.13507
Publikováno v:
SIAM Journal on Mathematical Analysis 54 (2), 1718-1741, 2022
We compute exact second-order asymptotics for the cost of an optimal solution to the entropic optimal transport problem in the continuous-to-discrete, or semi-discrete, setting. In contrast to the discrete-discrete or continuous-continuous case, we s
Externí odkaz:
http://arxiv.org/abs/2106.11862
We study first-order optimization algorithms for computing the barycenter of Gaussian distributions with respect to the optimal transport metric. Although the objective is geodesically non-convex, Riemannian GD empirically converges rapidly, in fact
Externí odkaz:
http://arxiv.org/abs/2106.08502
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
Autor:
Chewi, Sinho, Gouic, Thibaut Le, Lu, Chen, Maunu, Tyler, Rigollet, Philippe, Stromme, Austin J.
Motivated by the problem of sampling from ill-conditioned log-concave distributions, we give a clean non-asymptotic convergence analysis of mirror-Langevin diffusions as introduced in Zhang et al. (2020). As a special case of this framework, we propo
Externí odkaz:
http://arxiv.org/abs/2005.09669
We study first order methods to compute the barycenter of a probability distribution $P$ over the space of probability measures with finite second moment. We develop a framework to derive global rates of convergence for both gradient descent and stoc
Externí odkaz:
http://arxiv.org/abs/2001.01700