arg min substack
Subscribe
Sign in
Home
Lecture Blogs
Archive
About
New
Top
Discussion
The Deep Optimization Cookbook
Get those models to converge with one weird trick.
18 hrs ago
•
Ben Recht
6
Share this post
The Deep Optimization Cookbook
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
7
No one knows how the brain works.
Is that why we believed it was hard to train neural networks?
Sep 21
•
Ben Recht
11
Share this post
No one knows how the brain works.
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
23
It's not a trick...
It's not an illusion either.
Sep 20
•
Ben Recht
8
Share this post
It's not a trick...
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
14
The maddening nonlinear multiverse
The paths to nonlinear prediction all lead to the same place
Sep 19
•
Ben Recht
3
Share this post
The maddening nonlinear multiverse
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
9
Hidden Foundations
We hide a lot of theory in our representation of data.
Sep 15
•
Ben Recht
6
Share this post
Hidden Foundations
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
5
Features of the foundations of machine learning
Which measurements let us predict?
Sep 14
•
Ben Recht
8
Share this post
Features of the foundations of machine learning
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
1
I don't know what I've been trying to prove.
Yeah, yeah. Why I feel like I do about generalization theory.
Sep 13
•
Ben Recht
9
Share this post
I don't know what I've been trying to prove.
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
29
Three paths to generalization
Uniform Convergence, Sequential Prediction, and Stability
Sep 12
•
Ben Recht
7
Share this post
Three paths to generalization
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
Generally speaking when god plays dice
An attempt at re-rethinking generalization theory
Sep 11
•
Ben Recht
9
Share this post
Generally speaking when god plays dice
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
1
Regretfully Yours
This is a live blog of Lecture 5 of my graduate machine learning class “Patterns, Predictions, and Actions.” A Table of Contents for this series is…
Sep 7
•
Ben Recht
10
Share this post
Regretfully Yours
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
4
Rigor vs. GitHub Descent
Is there a principled way to optimize in machine learning?
Sep 6
•
Ben Recht
17
Share this post
Rigor vs. GitHub Descent
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
22
7 Minute Opts
Optimization for Machine Learning In 1000 Words or Less.
Sep 5
•
Ben Recht
9
Share this post
7 Minute Opts
argmin.substack.com
Copy link
Facebook
Email
Notes
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts