Europe
A Probabilistic U-Net for Segmentation of Ambiguous Images
Simon Kohl, Bernardino Romera-Paredes, Clemens Meyer, Jeffrey De Fauw, Joseph R. Ledsam, Klaus Maier-Hein, S. M. Ali Eslami, Danilo Jimenez Rezende, Olaf Ronneberger
Many real-world vision problems suffer from inherent ambiguities. In clinical applications for example, itmight not be clear from aCT scan alone which particular region is cancer tissue. Therefore a group of graders typically produces a set of diverse but plausible segmentations.
AiluRus: A Scalable ViT Framework for Dense Prediction
As a result, our method significantly accelerates ViTs for dense prediction tasks.
List-decodable Linear Regression
Sushrut Karmalkar, Adam Klivans, Pravesh Kothari
We give the first polynomial-time algorithm for robust regression in the listdecodable setting where an adversary can corrupt a greater than1/2 fraction ofexamples.
the Ground up--Hierarchical Representation Learning by Chunking Shuchen Wu
Of course, the count function should be fixed.
But How Does It Work in Theory? Linear SVM with Random Features
Yitong Sun, Anna Gilbert, Ambuj Tewari
The random features method, proposed by Rahimi and Recht [2008], maps the data to a finite dimensional feature space as a random approximation to the feature space of RBF kernels. With explicit finite dimensional feature vectors available, the original KSVM is converted to a linear support vector machine (LSVM), that can be trained by faster algorithms (Shalev-Shwartz et al.
Coresets for Archetypal Analysis
Several approaches have been proposed to remedy the edacious nature of archetypal analysis, proposing, e.g.,efficient active-set quadratic programming (Chen etal.,2014),
