·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
OpenAI says Hugging Face was breached by its own pre-release models36m◆The State of Simulation for Physical AI: An Overview1h◆Jack Dorsey is taking on Slack with Buzz, a group chat platform for teams and their AI agents1h◆AI and the rise of the universal entertainment app1h◆Substack adds an AI detector to help spot blogs written by no one2h◆Data centers expected to use 4x more electricity by 20353h◆Google releases three new Gemini models — but no 3.5 Pro4h◆Introducing the ChatGPT for small business program4h◆Anthropic’s $1.5 billion book piracy settlement approved by judge4h◆US threatens sanctions against Chinese AI models over IP theft5h◆Google launches a cheaper alternative to large AI security models like Mythos6h◆Music streamer Deezer says more than 50% of daily uploads are AI-generated8h◆Halliday’s latest smart glasses feature a much-improved display8h◆America needs to stop getting shocked by Chinese AI10h◆Advancing next-gen AI with materials science innovation10h◆Gritt exits stealth with $32 million for robots to build solar plants — then, everything else11h◆OpenAI and Hugging Face partner to address security incident during model evaluation14h◆Capacity and Redundancy Trade-offs in Multi-Task Learning17h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation17h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making17h◆OpenAI says Hugging Face was breached by its own pre-release models36m◆The State of Simulation for Physical AI: An Overview1h◆Jack Dorsey is taking on Slack with Buzz, a group chat platform for teams and their AI agents1h◆AI and the rise of the universal entertainment app1h◆Substack adds an AI detector to help spot blogs written by no one2h◆Data centers expected to use 4x more electricity by 20353h◆Google releases three new Gemini models — but no 3.5 Pro4h◆Introducing the ChatGPT for small business program4h◆Anthropic’s $1.5 billion book piracy settlement approved by judge4h◆US threatens sanctions against Chinese AI models over IP theft5h◆Google launches a cheaper alternative to large AI security models like Mythos6h◆Music streamer Deezer says more than 50% of daily uploads are AI-generated8h◆Halliday’s latest smart glasses feature a much-improved display8h◆America needs to stop getting shocked by Chinese AI10h◆Advancing next-gen AI with materials science innovation10h◆Gritt exits stealth with $32 million for robots to build solar plants — then, everything else11h◆OpenAI and Hugging Face partner to address security incident during model evaluation14h◆Capacity and Redundancy Trade-offs in Multi-Task Learning17h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation17h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making17h◆
News/On Local Population-Risk Certificates
arxiv
PublishedJune 30, 2026 at 4:00 AM
—neutral

On Local Population-Risk Certificates

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

arXiv:2606.19147v2 Announce Type: replace-cross Abstract: We develop finite-sample certificates for local population-risk increments \(P\delta_v=R(\theta_0+v)-R(\theta_0)\), \(v\in\mathcal D\). The primitive object is an expected-valid upper endpoint \(\widehat{\mathsf U}_{\mathcal D}\) satisfying \

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
arxivCapacity and Redundancy Trade-offs in Multi-Task Learning17harxivPredictive Training with Latent Imagination for Visual Quadruped Navigation17harxivWhere Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making17h
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