Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL Divergences
通过Wasserstein和Kalman-Wasserstein KL散度的适定KL正则化控制
Viktor Stein, Adwait Datar, Nihat Ay
机构
*
Department of Mathematics, Technical University of Munich \& Munich Center for Machine Learning, Germany. The majority of the work was conducted while at the Institute of Mathematics at the Technical University of Berlin, Germany \& the Berlin Mathematical School.
;
Institute for Data Science Foundations, Hamburg University of Technology, Germany
;
Santa Fe Institute, USA
Approximating $f$-Divergences with Rank Statistics
用秩统计量近似 $f$-散度
Viktor Stein, José Manuel de Frutos
机构
*
Department of Mathematics, Technical University of Munich \& Munich Center for Machine Learning, Germany. The majority of the work was conducted while at the Institute of Mathematics at the Technical University of Berlin, Germany \& the Berlin Mathematical School.
;
Department of Signal Theory
机构
*
University of Tokyo(东京大学)
;
Toyota Central Research Laboratory(丰田中央研究所)
;
University of California, Berkeley(加州大学伯克利分校)
;
Massachusetts Institute of Technology(麻省理工学院)
;
National Institute of Advanced Industrial Science and Technology(国家工业科学与技术研究院)
Degradation-Aware Metric Prompting for Hyperspectral Image Restoration
退化感知度量提示用于高光谱图像恢复
Binfeng Wang, Di Wang, Haonan Guo, Ying Fu, Jing Zhang
机构
*
School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China(北京理工大学计算机科学与技术学院)
;
School of Computer Science, Wuhan University, Wuhan, Hubei, China(武汉大学计算机学院)
;
Zhongguancun Academy, Beijing, China(中关村学院)
Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
非光滑优化的保护性随机Polyak步长:无需小(次)梯度的鲁棒性能
Dimitris Oikonomou, Nicolas Loizou
机构
*
Mathematical Institute for Data Science (MINDS), Johns Hopkins University, Baltimore, MD, USA(数据科学数学研究所(MINDS),约翰霍普金斯大学,巴尔的摩,MD,美国)
;
Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA(计算机科学系,约翰霍普金斯大学,巴尔的摩,MD,美国)
;
Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA(应用数学与统计学系,约翰霍普金斯大学,巴尔的摩,MD,美国)
On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering
生成路径的崩溃:扩散引导的准则与修正
Ziseok Lee, Minyeong Hwang, Wooyeol Lee, Sanghyun Jo, Jihyung Ko, Young Bin Park, Jae-Mun Choi, Eunho Yang, Kyungsu Kim
机构
*
Department of Biomedical Sciences, Seoul National University, Seoul, South Korea(首尔国立大学生物医学科学系)
;
School of Transdisciplinary Innovations, Seoul National University, Seoul, South Korea(首尔国立大学跨学科创新学院)
;
Interdisciplinary Program in AI, Seoul National University, Seoul, South Korea(首尔国立大学人工智能交叉学科项目)
;
Kim Jaechul Graduate School of AI, Seoul, South Korea(金 Jaechul人工智能研究生院)