Zobrazeno 1 - 10
of 155
pro vyhledávání: '"Tao, Molei"'
We study the convergence rate of first-order methods for rectangular matrix factorization, which is a canonical nonconvex optimization problem. Specifically, given a rank-$r$ matrix $\mathbf{A}\in\mathbb{R}^{m\times n}$, we prove that gradient descen
Externí odkaz:
http://arxiv.org/abs/2410.09640
This article makes discrete masked models for the generative modeling of discrete data controllable. The goal is to generate samples of a discrete random variable that adheres to a posterior distribution, satisfies specific constraints, or optimizes
Externí odkaz:
http://arxiv.org/abs/2410.02143
Transit timing variation (TTV) provides rich information about the mass and orbital properties of exoplanets, which are often obtained by solving an inverse problem via Markov Chain Monte Carlo (MCMC). In this paper, we design a new data-driven appro
Externí odkaz:
http://arxiv.org/abs/2409.04557
We address the outstanding problem of sampling from an unnormalized density that may be non-log-concave and multimodal. To enhance the performance of simple Markov chain Monte Carlo (MCMC) methods, techniques of annealing type have been widely used.
Externí odkaz:
http://arxiv.org/abs/2407.16936
Applications such as unbalanced and fully shuffled regression can be approached by optimizing regularized optimal transport (OT) distances, such as the entropic OT and Sinkhorn distances. A common approach for this optimization is to use a first-orde
Externí odkaz:
http://arxiv.org/abs/2407.02015
Most existing theoretical investigations of the accuracy of diffusion models, albeit significant, assume the score function has been approximated to a certain accuracy, and then use this a priori bound to control the error of generation. This article
Externí odkaz:
http://arxiv.org/abs/2406.12839
Autor:
Zhang, Xinxi, Wen, Song, Han, Ligong, Juefei-Xu, Felix, Srivastava, Akash, Huang, Junzhou, Wang, Hao, Tao, Molei, Metaxas, Dimitris N.
Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks requiring high
Externí odkaz:
http://arxiv.org/abs/2405.21050
Autor:
Kong, Lingkai, Tao, Molei
Explicit, momentum-based dynamics that optimize functions defined on Lie groups can be constructed via variational optimization and momentum trivialization. Structure preserving time discretizations can then turn this dynamics into optimization algor
Externí odkaz:
http://arxiv.org/abs/2405.20390
The generative modeling of data on manifold is an important task, for which diffusion models in flat spaces typically need nontrivial adaptations. This article demonstrates how a technique called `trivialization' can transfer the effectiveness of dif
Externí odkaz:
http://arxiv.org/abs/2405.16381
This article considers the generative modeling of the (mixed) states of quantum systems, and an approach based on denoising diffusion model is proposed. The key contribution is an algorithmic innovation that respects the physical nature of quantum st
Externí odkaz:
http://arxiv.org/abs/2404.06336