Towards Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural…
Intelligent Learning Rate Distribution to reduce Catastrophic Forgetting in Transformersby Philip Kenneweg, Alexander Schulz, Sarah…
Improving Line Search Methods for Large Scale Neural Network Trainingby Philip Kenneweg, Tristan Kenneweg, Barbara…
A Stochastic Quasi-Newton Method for Non-convex Optimization with Non-uniform Smoothnessby Zhenyu Sun, Ermin WeiFirst submitted…
Vehicle Detection Performance in Nordic Regionby Hamam Mokayed, Rajkumar Saini, Oluwatosin Adewumi, Lama Alkhaled, Bjorn…
Tree-based Learning for High-Fidelity Prediction of Chaosby Adam Giammarese, Kamal Rana, Erik M. Bollt, Nishant…
M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Schedulingby Xudong Sun, Nutan…
SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modulesby Xiangyu Chen, Jing Liu, Ye Wang, Pu…
Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Ratesby Riccardo Grazzi, Massimiliano Pontil, Saverio SalzoFirst submitted…
Interpretable Machine Learning for TabPFNby David Rundel, Julius Kobialka, Constantin von Crailsheim, Matthias Feurer, Thomas…