Summary of Improving Generalization and Convergence by Enhancing Implicit Regularization, By Mingze Wang et al.
Improving Generalization and Convergence by Enhancing Implicit Regularizationby Mingze Wang, Jinbo Wang, Haotian He, Zilin…
Improving Generalization and Convergence by Enhancing Implicit Regularizationby Mingze Wang, Jinbo Wang, Haotian He, Zilin…
Occam Gradient Descentby B.N. KausikFirst submitted to arxiv on: 30 May 2024CategoriesMain: Machine Learning (cs.LG)Secondary:…
I Bet You Did Not Mean That: Testing Semantic Importance via Bettingby Jacopo Teneggi, Jeremias…
It’s Not a Modality Gap: Characterizing and Addressing the Contrastive Gapby Abrar Fahim, Alex Murphy,…
Why are Visually-Grounded Language Models Bad at Image Classification?by Yuhui Zhang, Alyssa Unell, Xiaohan Wang,…
4-bit Shampoo for Memory-Efficient Network Trainingby Sike Wang, Pan Zhou, Jia Li, Hua HuangFirst submitted…
DMT-JEPA: Discriminative Masked Targets for Joint-Embedding Predictive Architectureby Shentong Mo, Sukmin YunFirst submitted to arxiv…
WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Averageby Louis Fournier, Adel Nabli, Masih…
Transformer In-Context Learning for Categorical Databy Aaron T. Wang, Ricardo Henao, Lawrence CarinFirst submitted to…
AdaFisher: Adaptive Second Order Optimization via Fisher Informationby Damien Martins Gomes, Yanlei Zhang, Eugene Belilovsky,…