Fine-Tuning Gradient Dynamics
Explore the dynamics of low-rank fine-tuning beyond kernels in the context of gradient dynamics. Key bottleneck: Spurious Paulis and anticoncentration lemma explained. Form of the gradient and more insights revealed.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
GRADIENT DYNAMICS FOR LOW-RANK FINE-TUNING BEYOND KERNELS KEREM DAYI HARVARD SITAN CHEN HARVARD
KEY BOTTLENECK: SPURIOUS PAULIS Anticoncentration lemma [Grewal et al. 23]: With high probability, Paulis obtained from Bell difference sampling ? ?/?4 times include generators for ?
FORM OF THE GRADIENT ? = ? ?
