·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Startup Battlefield 200 applications officially close in 3 days1h◆Google will pay SpaceX $920M per month for compute2h◆The most interesting startups right now want to get you off your phone4h◆This is your laptop… on AI5h◆New York lawmakers pass one-year ban on new data centers6h◆The token bill comes due: Inside the industry scramble to manage AI’s runaway costs6h◆The latest AI news we announced in May 20267h◆The ‘together tech’ wave might be the most intriguing startup bet of 20267h◆This AI startup says it can tell if a script will make a hit film7h◆AirTrunk commits $30B to build 5GW of AI data centers in India8h◆The Meta hack shows there’s more to AI security than Mythos12h◆Mira Murati steps back into the spotlight, carefully16h◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning17h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning17h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models17h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents17h◆Why Muon Outperforms Adam: A Curvature Perspective17h◆Vision Hopfield Memory Networks17h◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies17h◆FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment17h◆Startup Battlefield 200 applications officially close in 3 days1h◆Google will pay SpaceX $920M per month for compute2h◆The most interesting startups right now want to get you off your phone4h◆This is your laptop… on AI5h◆New York lawmakers pass one-year ban on new data centers6h◆The token bill comes due: Inside the industry scramble to manage AI’s runaway costs6h◆The latest AI news we announced in May 20267h◆The ‘together tech’ wave might be the most intriguing startup bet of 20267h◆This AI startup says it can tell if a script will make a hit film7h◆AirTrunk commits $30B to build 5GW of AI data centers in India8h◆The Meta hack shows there’s more to AI security than Mythos12h◆Mira Murati steps back into the spotlight, carefully16h◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning17h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning17h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models17h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents17h◆Why Muon Outperforms Adam: A Curvature Perspective17h◆Vision Hopfield Memory Networks17h◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies17h◆FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment17h◆
News/Deciphering Two Training Clocks in Grokking via Deep Linear Network Theory with Conditional ReLU Reduction
arxiv
PublishedJune 5, 2026 at 4:00 AM
—neutral

Deciphering Two Training Clocks in Grokking via Deep Linear Network Theory with Conditional ReLU Reduction

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2606.05863v1 Announce Type: new Abstract: Grokking suggests that fitting the training data and learning a simple underlying rule may occur on different time scales. We formalize this phenomenon by separating the fast decay of the classification loss from the slower simplification of the learne

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning17harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning17harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models17harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents17h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews