Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Maunu, Tyler"'
Autor:
Maunu, Tyler, Molina-Fructuoso, Martin
We study accelerated optimization methods in the Gaussian phase retrieval problem. In this setting, we prove that gradient methods with Polyak or Nesterov momentum have similar implicit regularization to gradient descent. This implicit regularization
Externí odkaz:
http://arxiv.org/abs/2311.12888
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 develop theoretically guaranteed stochastic methods for outlier-robust PCA. Outlier-robust PCA seeks an underlying low-dimensional linear subspace from a dataset that is corrupted with outliers. We are able to show that our methods, which involve
Externí odkaz:
http://arxiv.org/abs/2203.09276
Publikováno v:
Proceedings of the 2021 International Conference on 3D Vision (3DV), 2021, pp. 352-360
We develop new statistics for robustly filtering corrupted keypoint matches in the structure from motion pipeline. The statistics are based on consistency constraints that arise within the clustered structure of the graph of keypoint matches. The sta
Externí odkaz:
http://arxiv.org/abs/2201.04797
We consider the fundamental problem of sampling the optimal transport coupling between given source and target distributions. In certain cases, the optimal transport plan takes the form of a one-to-one mapping from the source support to the target su
Externí odkaz:
http://arxiv.org/abs/2110.03237
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
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
Autor:
Maunu, Tyler, Lerman, Gilad
We give robust recovery results for synchronization on the rotation group, $\mathrm{SO}(D)$. In particular, we consider an adversarial corruption setting, where a limited percentage of the observations are arbitrarily corrupted. We give a novel algor
Externí odkaz:
http://arxiv.org/abs/2002.05299
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
Autor:
Maunu, Tyler, Lerman, Gilad
We study the problem of robust subspace recovery (RSR) in the presence of adversarial outliers. That is, we seek a subspace that contains a large portion of a dataset when some fraction of the data points are arbitrarily corrupted. We first examine a
Externí odkaz:
http://arxiv.org/abs/1904.03275