Zobrazeno 1 - 10
of 227
pro vyhledávání: '"Heejune So"'
Autor:
Heejune So, Hyunjong Lee, Seung Hyup Hyun, Young Seok Cho, Seung Hwan Moon, Joon Young Choi, Kyung-Han Lee
Publikováno v:
Frontiers in Oncology, Vol 13 (2023)
BackgroundTotal metabolic tumor volume (TMTV) in 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) predicts patient outcome in follicular lymphoma (FL); however, it requires laborious segmentation of all lesions. We investigated the pro
Externí odkaz:
https://doaj.org/article/3e2a3c8641d041f3bbc93a034f82f611
In-context learning (ICL) is a cornerstone of large language model (LLM) functionality, yet its theoretical foundations remain elusive due to the complexity of transformer architectures. In particular, most existing work only theoretically explains h
Externí odkaz:
http://arxiv.org/abs/2409.10559
In a recent breakthrough [arXiv:2301.04112], Chatterjee proved site disorder chaos in the Edwards-Anderson (EA) short-range spin glass model utilizing the Hermite spectral method. In this paper, we demonstrate the further usefulness of this Hermite s
Externí odkaz:
http://arxiv.org/abs/2404.09409
We study gradient flow on the exponential loss for a classification problem with a one-layer softmax attention model, where the key and query weight matrices are trained separately. Under a separability assumption on the data, we show that when gradi
Externí odkaz:
http://arxiv.org/abs/2403.08699
We study the dynamics of gradient flow for training a multi-head softmax attention model for in-context learning of multi-task linear regression. We establish the global convergence of gradient flow under suitable choices of initialization. In additi
Externí odkaz:
http://arxiv.org/abs/2402.19442
With the growth of online services, the need for advanced text classification algorithms, such as sentiment analysis and biased text detection, has become increasingly evident. The anonymous nature of online services often leads to the presence of bi
Externí odkaz:
http://arxiv.org/abs/2310.04313
We study the L\'evy spin glass model, a fully connected model on $N$ vertices with heavy-tailed interactions governed by a power law distribution of order $0<\alpha<2.$ Our investigation is divided into three cases $0<\alpha<1$, $\alpha=1$, and $1<\a
Externí odkaz:
http://arxiv.org/abs/2303.06084
Autor:
Kim, Heejune
Publikováno v:
Markov Processes and Related Fields, v.28, Issue 1, 113-148 (2022)
In this paper, the Glauber dynamics for the Ising model on the complete multipartite graph $K_{np_1,\dots,np_m}$ is investigated where $0
Externí odkaz:
http://arxiv.org/abs/2102.05279
We estimate the general influence functions for spatio-temporal Hawkes processes using a tensor recovery approach by formulating the location dependent influence function that captures the influence of historical events as a tensor kernel. We assume
Externí odkaz:
http://arxiv.org/abs/2011.12151
Autor:
Sheen, Heejune, Mei, Yajun
We present an elementary mathematical method to find the minimax estimator of the Bernoulli proportion $\theta$ under the squared error loss when $\theta$ belongs to the restricted parameter space of the form $\Omega = [0, \eta]$ for some pre-specifi
Externí odkaz:
http://arxiv.org/abs/2009.11413