Optimization

Convex Optimization, Loss Functions, Gradient Methods, Adam Optimizer

Feeds to Scour
SubscribedAll
Scoured 138 posts in 10.1 ms

Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks

 🧠Deep Learning  Content type: Academic
arxiv.org·

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

 🤖Machine Learning  Content type: Tutorial
iwtlp.com··DEV

Pytorch for Neural Networks Part 6: Understanding Epochs and Loss

 🧠Deep Learning  Content type: Blog
dev.to··DEV

How LLMs Work?

 🤖Transformers
pub.towardsai.net
·

ml-from-scratch-book/code: Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.

 🤖Machine Learning  Content type: Code
github.com··Hacker News

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

 📐Linear Algebra  Content type: Blog
tridao.me··Hacker News

Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

 🧠Deep Learning

Pytorch for Neural Networks Part 5: Preparing the Model for Training

 🧠Deep Learning  Content type: Blog
dev.to··DEV

Karpathy’s 90-Second Time Machine Through 33 Years of Neural Networks

 🧠Deep Learning
pub.towardsai.net
·

Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

 🤖Machine Learning  Content type: Academic
arxiv.org·

markusheimerl/gpt: A generative pretrained transformer implementation

 🤖Transformers  Content type: Code
github.com··Hacker News

Building a Multilayer Perceptron from Scratch: What It Taught Me About Neural Networks

 🧠Deep Learning  Content type: Blog
dev.to··DEV

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

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

Beyond Basic RAG (Part 3): Agentic RAG, CRAG, Self-RAG and GraphRAG Explained | M012 | Mehul Ligade

 🤖LLMs
pub.towardsai.net
·

Second-Order Path Kernel Interpolation Formulas in Machine Learning

 🧠Deep Learning  Content type: Academic
arxiv.org·

Meltedd/scarecrow: An adversarial frame pattern optimizer for evading automated license plate recognition, personalized to your plate.

 🎭Anthropic Claude  Content type: Code
github.com··Hacker News

From Linear Regression to Gradient Descent

 🧠Deep Learning  Content type: Blog
dev.to··DEV

Optimizing Energy-based Neural Network Training with Coherent Ising Machine

 🧠Deep Learning  Content type: Academic
arxiv.org·

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

 🔥PyTorch  Content type: Academic
arxiv.org·

Fourier fractal dimension to predict the generalization of deep neural networks

 🧠Deep Learning  Content type: Academic
arxiv.org·

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