Summary of Strong Convexity-guided Hyper-parameter Optimization For Flatter Losses, by Rahul Yedida et al.
Strong convexity-guided hyper-parameter optimization for flatter lossesby Rahul Yedida, Snehanshu SahaFirst submitted to arxiv on:…
Strong convexity-guided hyper-parameter optimization for flatter lossesby Rahul Yedida, Snehanshu SahaFirst submitted to arxiv on:…
Towards Improved Imbalance Robustness in Continual Multi-Label Learning with Dual Output Spiking Architecture (DOSA)by Sourav…
The Fine-Grained Complexity of Gradient Computation for Training Large Language Modelsby Josh Alman, Zhao SongFirst…
Reducing the Cost of Quantum Chemical Data By Backpropagating Through Density Functional Theoryby Alexander Mathiasen,…
Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codesby Xiaoxin Su, Yipeng Zhou, Laizhong Cui, John…
Lens: A Foundation Model for Network Trafficby Qineng Wang, Chen Qian, Xiaochang Li, Ziyu Yao,…
Explicit Flow Matching: On The Theory of Flow Matching Algorithms with Applicationsby Gleb Ryzhakov, Svetlana…
A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learningby Abdelhakim…
Dual Interior Point Optimization Learningby Michael Klamkin, Mathieu Tanneau, Pascal Van HentenryckFirst submitted to arxiv…
Implicit Neural Representation of Tileable Material Texturesby Hallison Paz, Tiago Novello, Luiz VelhoFirst submitted to…