Loss Landscapes

Feeds to Scour
SubscribedAll
Scoured 12 posts in 10.9 ms

Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape

 🧠Machine Learning  Content type: Academic
arxiv.org·
Less-relevant results

Human-Like Neural Nets by Catapulting

 🧠LLM
gwern.net··Hacker News

AI and physics have more in common than you might think

 📐Math  Content type: News  Content type: Academic
news.northeastern.edu·

From SGD to Muon: An Incremental Tutorial (Fable-5)

 📐Linear Algebra  Content type: Blog

A Geometric Characterization of the Stationary Plateau for Two-Layer Neural Networks

 🌀Riemannian Optimization  Content type: Academic
arxiv.org·

Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?

 📐Optimization Theory  Content type: Academic
arxiv.org·

Food Glazing Agents Market Trends, Demand Analysis & Forecast 2026–2033

 📋Product Management
community.ops.io·

When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks

 📐Optimization Theory  Content type: Academic
arxiv.org·

Liquid Neural Networks as a Drop-in Continuous-Time Deformation Field for Dynamic 3D Gaussian Splatting

 🔥PyTorch  Content type: Academic
arxiv.org·

Explaining Data Mixing Scaling Laws

 📐Optimization Theory  Content type: Academic
arxiv.org·

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

 📐Linear Algebra  Content type: Academic
arxiv.org·

Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting

 📡Information Theory  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