Scaling Exponents Across Parameterizations and Optimizers
30:58
Large Language Models to Enhance Bayesian Optimization
45:33
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
45:12
Nick Erickson - AutoGluon 1.0: Shattering the SOTA with Zeroshot-HPO & Dynamic Stacking
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
51:05
Samuel Mueller | "PFNs: Use neural networks for 100x faster Bayesian predictions"
38:27
einspace: Searching for Neural Architectures from Fundamental Operations
33:42
FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
43:47