Author of the publication

The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon

, , , , , and . (2022)cite arxiv:2206.04817Comment: Removed Tex formatting commands in title Title and Abstract.

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

When can transformers reason with abstract symbols?, , , , , and . CoRR, (2023)LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures., , , , , , , and . CoRR, (2023)Holographic stress tensor for non-relativistic theories, and . Journal of High Energy Physics, 2009 (09): 009 (Jul 10, 2009)Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks., , , , , , and . CoRR, (2021)An Improved Continuous-Action Extended Classifier Systems for Function Approximation., , and . Complex Adaptive Systems, volume 61 of Procedia Computer Science, page 361-366. Elsevier, (2015)What Algorithms can Transformers Learn? A Study in Length Generalization., , , , , , , and . CoRR, (2023)Adaptivity and Modularity for Efficient Generalization Over Task Complexity., , , , , , , , , and 1 other author(s). CoRR, (2023)Vanishing Gradients in Reinforcement Finetuning of Language Models., , , , , , , and . CoRR, (2023)An Improved eXtended Classifier System for the Real-time-input Real-time-output (XCSRR) Stability Control of a Biped Robot., , , and . Complex Adaptive Systems, volume 61 of Procedia Computer Science, page 492-499. Elsevier, (2015)The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon., , , , , and . CoRR, (2022)