Zobrazeno 1 - 10
of 3 724
pro vyhledávání: '"To, Wai Ming"'
We show that deep neural networks achieve dimension-independent rates of convergence for learning structured densities such as those arising in image, audio, video, and text applications. More precisely, we demonstrate that neural networks with a sim
Externí odkaz:
http://arxiv.org/abs/2411.15095
We mimic the conventional explicit Total Variation Diminishing Runge-Kutta (TVDRK) schemes and propose a class of numerical integrators to solve differential equations on a unit sphere. Our approach utilizes the exponential map inherent to the sphere
Externí odkaz:
http://arxiv.org/abs/2410.10420
We consider the problem of estimating a structured multivariate density, subject to Markov conditions implied by an undirected graph. In the worst case, without Markovian assumptions, this problem suffers from the curse of dimensionality. Our main re
Externí odkaz:
http://arxiv.org/abs/2410.07685
We study active learning methods for single index models of the form $F({\mathbf x}) = f(\langle {\mathbf w}, {\mathbf x}\rangle)$, where $f:\mathbb{R} \to \mathbb{R}$ and ${\mathbf x,\mathbf w} \in \mathbb{R}^d$. In addition to their theoretical int
Externí odkaz:
http://arxiv.org/abs/2405.09312
We develop optimal algorithms for learning undirected Gaussian trees and directed Gaussian polytrees from data. We consider both problems of distribution learning (i.e. in KL distance) and structure learning (i.e. exact recovery). The first approach
Externí odkaz:
http://arxiv.org/abs/2402.06380
Despite numerous years of research into the merits and trade-offs of various model selection criteria, obtaining robust results that elucidate the behavior of cross-validation remains a challenging endeavor. In this paper, we highlight the inherent l
Externí odkaz:
http://arxiv.org/abs/2312.17047
Autor:
To, Wai Ming, Lam, King Hang
Publikováno v:
International Journal of Energy Sector Management, 2023, Vol. 18, Issue 6, pp. 1572-1591.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/IJESM-06-2023-0018
We show that a constant-size constant-error coreset for polytope distance is simple to maintain under merges of coresets. However, increasing the size cannot improve the error bound significantly beyond that constant.
Comment: Presented in SoCG'
Comment: Presented in SoCG'
Externí odkaz:
http://arxiv.org/abs/2311.05651
Autor:
Liang, Xuanwen, Lee, Eric Wai Ming
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems
Crowd simulations play a pivotal role in building design, influencing both user experience and public safety. While traditional knowledge-driven models have their merits, data-driven crowd simulation models promise to bring a new dimension of realism
Externí odkaz:
http://arxiv.org/abs/2311.02996
We study the optimal sample complexity of neighbourhood selection in linear structural equation models, and compare this to best subset selection (BSS) for linear models under general design. We show by example that -- even when the structure is \emp
Externí odkaz:
http://arxiv.org/abs/2306.02244