Loss Landscapes

Feeds to Scour
SubscribedAll
Scoured 8 posts in 11.4 ms

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

聽馃Machine Learning 聽Content type: Academic
arxiv.org路
Less-relevant results

Human-Like Neural Nets by Catapulting

聽馃LLM
gwern.net路路Hacker News

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

聽馃搻Optimization Theory 聽Content type: Academic
arxiv.org路

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

聽馃寑Riemannian Optimization 聽Content type: Academic
arxiv.org路

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

聽馃搻Optimization Theory 聽Content type: Academic
arxiv.org路

Explaining Data Mixing Scaling Laws

聽馃搻Optimization Theory 聽Content type: Academic
arxiv.org路

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

聽馃搻Linear Algebra 聽Content type: Academic
arxiv.org路

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

聽馃摗Information Theory 聽Content type: Academic
arxiv.org路

No more posts from yfff's subscribed feeds.

Scour all 25257 feedsLearn more about Feeds

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