Summary of Towards Compositional Interpretability For Xai, by Sean Tull et al.
Towards Compositional Interpretability for XAIby Sean Tull, Robin Lorenz, Stephen Clark, Ilyas Khan, Bob CoeckeFirst…
Towards Compositional Interpretability for XAIby Sean Tull, Robin Lorenz, Stephen Clark, Ilyas Khan, Bob CoeckeFirst…
Learning Dynamic Bayesian Networks from Data: Foundations, First Principles and Numerical Comparisonsby Vyacheslav Kungurtsev, Fadwa…
Distributed Training of Large Graph Neural Networks with Variable Communication Ratesby Juan Cervino, Md Asadullah…
Paraphrase and Aggregate with Large Language Models for Minimizing Intent Classification Errorsby Vikas Yadav, Zheng…
Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysisby Hongkang Li, Meng Wang,…
Minimax Optimality in Contextual Dynamic Pricing with General Valuation Modelsby Xueping Gong, Jiheng ZhangFirst submitted…
Reinforcement Learning via Auxiliary Task Distillationby Abhinav Narayan Harish, Larry Heck, Josiah P. Hanna, Zsolt…
Geometric Median (GM) Matching for Robust Data Pruningby Anish Acharya, Inderjit S Dhillon, Sujay SanghaviFirst…
Contrastive General Graph Matching with Adaptive Augmentation Samplingby Jianyuan Bo, Yuan FangFirst submitted to arxiv…
Machine Unlearning Fails to Remove Data Poisoning Attacksby Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu,…