Statistical Learning
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.
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.
Low-Rank Tucker Decomposition of Large Tensors Using TensorSketch
Osman Asif Malik, Stephen Becker
Neural Information Processing Systems http://nips.cc/
Communication Compression for Decentralized Training
Hanlin Tang, Shaoduo Gan, Ce Zhang, Tong Zhang, Ji Liu
Neural Information Processing Systems http://nips.cc/
