Zobrazeno 1 - 10
of 1 389
pro vyhledávání: '"Sun, Yuxin"'
We study the complexity of Non-Gaussian Component Analysis (NGCA) in the Statistical Query (SQ) model. Prior work developed a general methodology to prove SQ lower bounds for this task that have been applicable to a wide range of contexts. In particu
Externí odkaz:
http://arxiv.org/abs/2403.04744
We study the problem of learning mixtures of linear classifiers under Gaussian covariates. Given sample access to a mixture of $r$ distributions on $\mathbb{R}^n$ of the form $(\mathbf{x},y_{\ell})$, $\ell\in [r]$, where $\mathbf{x}\sim\mathcal{N}(0,
Externí odkaz:
http://arxiv.org/abs/2310.11876
Autor:
Sun, Yuxin
Since many log tracing application and diagnostic commands are now available on nodes at base station, event log can easily be collected, parsed and structured for network performance analysis. In order to improve In Service Performance of customer n
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-343358
We present new insights and a novel paradigm (StEik) for learning implicit neural representations (INR) of shapes. In particular, we shed light on the popular eikonal loss used for imposing a signed distance function constraint in INR. We show analyt
Externí odkaz:
http://arxiv.org/abs/2305.18414
We study the problem of PAC learning a single neuron in the presence of Massart noise. Specifically, for a known activation function $f: \mathbb{R} \to \mathbb{R}$, the learner is given access to labeled examples $(\mathbf{x}, y) \in \mathbb{R}^d \ti
Externí odkaz:
http://arxiv.org/abs/2210.09949
Publikováno v:
Hangkong bingqi, Vol 31, Iss 1, Pp 97-102 (2024)
Oriented object detection in remote sensing images is a current research hotspot. Due to the varying heights and equipment used in capturing remote sensing images, the ground sampling distance (GSD) of each image also varies, causing many small objec
Externí odkaz:
https://doaj.org/article/6ed40112b66e4634b898261fb4ef3378
Publikováno v:
Zhongguo quanke yixue, Vol 27, Iss 06, Pp 656-662 (2024)
Background The development of maternal and child health requires reducing urban-rural, regional and group disparities in the health of women and children. Focusing on the quality of life of maternal women in rural areas and other low-income areas is
Externí odkaz:
https://doaj.org/article/0059330f42754ccc93c498544d988acd
We establish optimal Statistical Query (SQ) lower bounds for robustly learning certain families of discrete high-dimensional distributions. In particular, we show that no efficient SQ algorithm with access to an $\epsilon$-corrupted binary product di
Externí odkaz:
http://arxiv.org/abs/2206.04589
We discover restrained numerical instabilities in current training practices of deep networks with stochastic gradient descent (SGD), and its variants. We show numerical error (on the order of the smallest floating point bit and thus the most extreme
Externí odkaz:
http://arxiv.org/abs/2206.02001
Publikováno v:
In Composite Structures 15 October 2024 346