arg min
Subscribe
Sign in
Home
Lecture Blogs
Collections
Archive
About
Latest
Top
Discussions
Benchmarking our benchmarks
The only validated theories of generalization are sociological and historical.
13 hrs ago
•
Ben Recht
10
2
Reshelving generalization
You don't need a theorem to argue more data is better than less data
Oct 9
•
Ben Recht
20
4
Henry Was Right
OpenAI selling the world as a mumblecore adaptation of Philip K Dick
Oct 8
•
Ben Recht
33
11
Minimal Theory
What are the most important lessons from optimization theory for machine learning?
Oct 7
•
Ben Recht
15
2
Sunday Never Knows
When do you give up on your model and trust your gut?
Oct 6
•
Ben Recht
13
6
How do you know so much about swallows?
A dialogue about the use and meaning of statistics with Ben Chugg
Oct 3
•
Ben Recht
19
4
Highly optimized optimizers
Justifying a laser focus on stochastic gradient methods.
Oct 2
•
Ben Recht
20
13
September 2025
Universal Cascades
A little approximation theory goes a long way
Sep 30
•
Ben Recht
18
6
Don't be resulting
On the vulgar arrogance of the vulgar positivism of decision theory
Sep 29
•
Ben Recht
32
12
Boxes of numbers
Machine learning's universal theory of data representation
Sep 25
•
Ben Recht
19
17
Changing the meta
Going for two down eight might be a worse idea than ever
Sep 24
•
Ben Recht
8
10
Common Descent
Machine learning begins with the perceptron
Sep 23
•
Ben Recht
21
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
