Optimization

Feeds to Scour
SubscribedAll
Scoured 72 posts in 5.9 ms

Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

馃Calculus + AIContent type: Academic
arxiv.org

Machine learning from scratch, what to build before using scikit-learn

馃攧BackpropagationContent type: Tutorial
iwtlp.comDEV

smile/deep at master 路 haifengl/smile

馃Linear Algebra + AIContent type: Code
github.comHacker News

Loss Functions in Machine Learning

馃Calculus + AIContent type: Blog
medium.com

Lightweight CNN SE transformer for robust weed classification with optimizer aware performance

馃TransformersContent type: Academic
nature.com

LLM are universal simulators

馃Calculus + AI

Gram Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon

馃Linear Algebra + AIContent type: Blog
tridao.meHacker News

Welcome to Machine Learning With Manya: The Ultimate Adventure Map!

馃Calculus + AIContent type: Blog
medium.com

Discrete Diffusion Modelling by Estimating the Ratios of the Data Distribution

馃敟PyTorchContent type: NewsContent type: Blog

Reinventing Entropy

馃Calculus + AIContent type: NewsContent type: Blog

Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent

馃Calculus + AIContent type: Academic
arxiv.org

Vibe Diaries: Training Nanochat

馃Linear Algebra + AI
vibediary.devHacker News
Less-relevant results

Agents Need Work Data: A Primer on RLWD, or Reinforcement Learning on Work Data

馃Calculus + AI
anjalishriva.comHacker News

The sample efficiency black hole

馃Calculus + AIContent type: News
dwarkesh.comHacker News

Physics-informed neural networks with caputo-fabrizio derivatives for nonlinear fractal-fractional delay equations and chaotic systems

馃Calculus + AIContent type: Academic
nature.com

Capacity-Constrained Online Convex Optimization with Delayed Feedback

馃攧BackpropagationContent type: Academic
arxiv.org

Unpacking AI: The Hardware Behind AI

馃Linear Algebra + AIContent type: News
pathtostaff.comHacker News

Direct Indexing with Exclusions

馃Calculus + AI
world.hey.comHacker News

Multilevel Stochastic Gradient Descent for Risk-Averse PDE-Constrained Optimization

馃Calculus + AIContent type: Academic
arxiv.org

Sakana AI's Recursive Self-Improvement (RSI) Lab

馃Calculus + AI
sakana.aiHacker News

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help