Asia
Deductive Verification of Chain-of-Thought Reasoning
To facilitate this procedure, we propose Natural Program, a natural language-based deductive reasoning format. Our approach enables models to generate precise reasoning steps where subsequent steps are more rigorously grounded on prior steps.
Constrained Graph Variational Autoencoders for Molecule Design
Qi Liu, Miltiadis Allamanis, Marc Brockschmidt, Alexander Gaunt
Neural Information Processing Systems http://nips.cc/
ARC: A Generalist Graph Anomaly Detector with In-Context Learning
To address these limitations, this paper proposes ARC, a generalist GAD approach that enables a "one-for-all" GAD model
Fast Sparse Group Lasso
Yasutoshi Ida, Yasuhiro Fujiwara, Hisashi Kashima
However,asan update ofonlyoneparameter group depends onalltheparameter groups ordata points, the computation cost is high when the number of the parameters or data points islarge. This paper proposes afast Block Coordinate Descent for Sparse GroupLasso.
Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods
The dataset is created to addressing a real-world challenge: creating a clean fine-grained taxonomy dataset.
Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations
Debraj Basu, Deepesh Data, Can Karakus, Suhas Diggavi
Neural Information Processing Systems http://nips.cc/
The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning
Neural Information Processing Systems http://nips.cc/