Jason Lee optimizes gradient flow with multiple AI subscriptions · Digg

/TECH

Jason Lee optimizes gradient flow with multiple AI subscriptions

Mila's Amir-massoud Farahmand also tested models on convex optimization proofs.

Combined views

4K

2 posts, first seen 18h ago

33 likes

Jason Lee optimizes gradient flow with multiple AI subscriptions

Mila's Amir-massoud Farahmand also tested models on convex optimization proofs.

Source Posts on X

Cluster sources

Amir-massoud Farahmand@SoloGenTECH

Combined views

4K

2 posts, first seen 18h ago

33 likes6 comments

6 comments

3 saves

Sentiment

Positive0%0%Negative

Guardrails removed spam, off-topic, unclear, or duplicate replies.

Digg Deeper

Ask a question below.

Published answers will appear here.

Source Posts on X

Cluster sources

Amir-massoud Farahmand@SoloGenTECH

My prompts: 1) How long can be the path of a gradient flow on a convex function given the constraint that it stays within the unit Euclidean ball in dimension n? [Took 1m 30s. Didn't prove anything, but found some exisiting results.]

Jason Lee@jasondeanleeTECH

OK finally paid for 4th pro subscription. Gotta push down the grad flow currently at 2.25380.... @SebastienBubeck @thsottiaux @gabrielchua

My prompts: 1) How long can be the path of a gradient flow on a convex function given the constraint that it stays within the unit Euclidean ball in dimension n? [Took 1m 30s. Didn't prove anything, but found some exisiting results.]

Jason Lee@jasondeanleeTECH

OK finally paid for 4th pro subscription. Gotta push down the grad flow currently at 2.25380.... @SebastienBubeck @thsottiaux @gabrielchua

3 saves

Sentiment

Positive0%0%Negative

Guardrails removed spam, off-topic, unclear, or duplicate replies.

Digg Deeper

Ask a question below.

Published answers will appear here.