Derivative-Free Optimization via Finite Difference Approximation: An Experimental Studyby Wang Du-Yi, Liang Guo, Liu Guangwu,…
Learning local discrete features in explainable-by-design convolutional neural networksby Pantelis I. Kaplanoglou, Konstantinos DiamantarasFirst submitted…
TrAct: Making First-layer Pre-Activations Trainableby Felix Petersen, Christian Borgelt, Stefano ErmonFirst submitted to arxiv on:…
Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networksby Nikolaos Tsilivis, Gal…
On the Role of Depth and Looping for In-Context Learning with Task Diversityby Khashayar Gatmiry,…
Provable optimal transport with transformers: The essence of depth and prompt engineeringby Hadi DaneshmandFirst submitted…
Super Gradient Descent: Global Optimization requires Global Gradientby Seifeddine AchourFirst submitted to arxiv on: 25…
Toward Finding Strong Pareto Optimal Policies in Multi-Agent Reinforcement Learningby Bang Giang Le, Viet Cuong…
Gradient Descent Efficiency Indexby Aviral DhingraFirst submitted to arxiv on: 25 Oct 2024CategoriesMain: Machine Learning…
Newton Losses: Using Curvature Information for Learning with Differentiable Algorithmsby Felix Petersen, Christian Borgelt, Tobias…