61 citations
- Chungbuk National University HospitalKR4 papers
- Department of PublicIN3 papers
- Icon (India)IN3 papers
- Korea UniversityKR3 papers
- Yonsei UniversityKR3 papers
- Chungbuk National UniversityKR2 papers
- Istituto Universitario di Studi Superiori di PaviaIT2 papers
- Leiden UniversityNL2 papers
- Scuola Normale SuperioreIT2 papers
- Australian National UniversityAU1 paper
- Cairo UniversityEG1 paper
- Centre d'Économie de la SorbonneFR1 paper
23 papers
Reproducing the first and second moments of empirical degree distributions
Mattia Marzi, Francesca Giuffrida, Diego Garlaschelli +1
The study of probabilistic models for the analysis of complex networks represents a flourishing research field. Among the former, Exponential Random Graphs (ERGs) have gained incre…
Existence of weak solutions for fast diffusion equation with a divergence type of drift term
Sukjung Hwang, Kyungkeun Kang, Hwa Kil Kim
We construct non-negative weak solutions of fast diffusion equations with a divergence type of drift term satisfying the -energy inequality and speed estimate in Wasserstein s…
Description length of canonical and microcanonical models
Francesca Giuffrida, Tiziano Squartini, Peter Grünwald +1
The (non-)equivalence of canonical and microcanonical ensembles is a fundamental question in statistical physics, concerning whether the use of soft and hard constraints in the max…
Effective Shortcut Technique for GAN
Seung Park, Cheol-Hwan Yoo, Yong-Goo Shin
In recent years, generative adversarial network (GAN)-based image generation techniques design their generators by stacking up multiple residual blocks. The residual block generall…
Image Generation with Self Pixel-wise Normalization
Yoon-Jae Yeo, Min-Cheol Sagong, Seung Park +2
Region-adaptive normalization (RAN) methods have been widely used in the generative adversarial network (GAN)-based image-to-image translation technique. However, since these appro…
Generative Convolution Layer for Image Generation
Seung Park, Yong-Goo Shin
This paper introduces a novel convolution method, called generative convolution (GConv), which is simple yet effective for improving the generative adversarial network (GAN) perfor…