English(EN) Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport

新的HyCNNs架构提供了改进的凸函数学习和最优传输

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-29 17:52

研究人员开发了超输入凸神经网络（HyCNNs），这是一种旨在比现有的输入凸神经网络（ICNNs）更有效地学习凸函数的新架构。HyCNNs将Maxout网络与ICNN原理相结合，在深度利用和可扩展性方面提供了理论优势。实验表明，HyCNNs在凸回归和插值任务中优于ICNNs和MLPs，并且在学习合成数据和单细胞RNA测序的高维最优传输图方面是有效的。 AI

影响引入了一种更具参数效率的凸函数学习架构，有可能提高最优传输等任务的性能。

排序理由介绍新颖神经网络架构的学术论文。

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv stat.ML TIER_1 English(EN) · Shayan Hundrieser, Insung Kong, Johannes Schmidt-Hieber · 2026-04-30 04:00

Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport

arXiv:2604.26942v1 Announce Type: cross Abstract: We introduce Hyper Input Convex Neural Networks (HyCNNs), a novel neural network architecture designed for learning convex functions. HyCNNs combine the principles of Maxout networks with input convex neural networks (ICNNs) to cr…
arXiv stat.ML TIER_1 English(EN) · Johannes Schmidt-Hieber · 2026-04-29 17:52

Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport

We introduce Hyper Input Convex Neural Networks (HyCNNs), a novel neural network architecture designed for learning convex functions. HyCNNs combine the principles of Maxout networks with input convex neural networks (ICNNs) to create a neural network that is always convex in the…

报道来源 [2]

Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport

Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport

相关实体

相关话题