↓Skip to main content

🏢 KTH Royal Institute of Technology

Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport
·2832 words·14 mins· loading · loading
AI Generated AI Theory Optimization 🏢 KTH Royal Institute of Technology
Outlier-robust distributionally robust optimization achieved via a novel Unbalanced Optimal Transport (UOT) distance, improving efficiency and accuracy.
Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data
·1738 words·9 mins· loading · loading
Machine Learning Federated Learning 🏢 KTH Royal Institute of Technology
This paper proposes a novel federated learning algorithm for nonconvex problems on compact smooth manifolds, achieving both computational and communication efficiency while mitigating client drift.
Learning from Offline Foundation Features with Tensor Augmentations
·1797 words·9 mins· loading · loading
Computer Vision Image Classification 🏢 KTH Royal Institute of Technology
LOFF-TA leverages offline foundation model features and tensor augmentations for efficient, resource-light training, achieving up to 37x faster training and 26x less GPU memory usage.
Can Transformers Smell Like Humans?
·2615 words·13 mins· loading · loading
AI Theory Representation Learning 🏢 KTH Royal Institute of Technology
Pre-trained transformer models can predict human smell perception by encoding odorant chemical structures, aligning with expert labels, continuous ratings, and similarity assessments.