Information Bottleneck

Feeds to Scour
SubscribedAll
Scoured 17 posts in 25.2 ms

Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation

 📡Information Theory  Content type: Academic
arxiv.org·
Less-relevant results

Deep Learning Weekly: Issue 458

 📡Information Theory

The Wrong Epsilon to the Brain

 📡Information Theory
hari.computer··Hacker News

Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

 📡Information Theory  Content type: Academic
arxiv.org·

IB-HFN: Information Bottleneck-Driven SAR-Optical Fusion Network for High-Fidelity Cloud Removal

 📡Information Theory  Content type: Academic
arxiv.org·

Jürgen Schmidhuber - World Models, RL, and the Year that chang…

 📡Information Theory

What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents

 📡Information Theory  Content type: Academic
arxiv.org·

Information Bottleneck Meets Quantization: Finite Rate Analysis and Optimal Designs

 📡Information Theory  Content type: Academic
arxiv.org·

Ultra-Fast Neural Video Compression

 🧠Synaptic pruning  Content type: Academic
arxiv.org·

Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks

 📡Information Theory  Content type: Academic
arxiv.org·

Adaptive state-action abstractions via rate-distortion

 🎯Reinforcement Learning  Content type: Academic
arxiv.org·

Finite-Blocklength Lossy Joint Source-Channel Coding over Unknown Channels

 📡Information Theory  Content type: Academic
arxiv.org·

Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms

 📐Information geometry  Content type: Academic
arxiv.org·

Towards Pretraining Text Encoders for TabPFN

 📡Information Theory  Content type: Academic
arxiv.org·

CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding

 📡Information Theory  Content type: Academic
arxiv.org·

Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

 📡Information Theory  Content type: Academic
arxiv.org·

Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability

 📡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