Archives AI News

Understanding SOAP from the Perspective of Gradient Whitening

arXiv:2509.22938v1 Announce Type: new Abstract: Shampoo with Adam in the Preconditioner’s eigenbasis (SOAP) has recently emerged as a promising optimization algorithm for neural network training, achieving superior training efficiency over both Adam and Shampoo in language modeling tasks. In this…

Compute-Optimal Quantization-Aware Training

arXiv:2509.22935v1 Announce Type: new Abstract: Quantization-aware training (QAT) is a leading technique for improving the accuracy of quantized neural networks. Previous work has shown that decomposing training into a full-precision (FP) phase followed by a QAT phase yields superior accuracy…

A Graph-in-Graph Learning Framework for Drug-Target Interaction Prediction

arXiv:2507.11757v2 Announce Type: replace Abstract: Accurately predicting drug-target interactions (DTIs) is pivotal for advancing drug discovery and target validation techniques. While machine learning approaches including those that are based on Graph Neural Networks (GNN) have achieved notable success in DTI…

Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders

arXiv:2509.22913v1 Announce Type: new Abstract: Manifold alignment (MA) involves a set of techniques for learning shared representations across domains, yet many traditional MA methods are incapable of performing out-of-sample extension, limiting their real-world applicability. We propose a guided representation learning…

FedCF: Fair Federated Conformal Prediction

arXiv:2509.22907v1 Announce Type: new Abstract: Conformal Prediction (CP) is a widely used technique for quantifying uncertainty in machine learning models. In its standard form, CP offers probabilistic guarantees on the coverage of the true label, but it is agnostic to…