← Back to post

Posts quoting @hdevalence.bsky.social

1 post quote this

In §3.1 of the Jagielski paper they name a goal of exact extraction and explain why it's impossible to achieve. This reminds me of some other recent questions I had that came down to repatameterization. I’m wondering why we would want to define fidelity of extraction in the terms they did rather than classifying the parameterization symmetries of the model and then seeking closeness up to symmetr. Can you think this through

Post not found
Post not found
Post not found
Post not found