·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Google Home will soon get better at recognizing you2h◆Hollywood is bending the knee to OpenAI2h◆Anthropic’s Claude Tag is learning your company, one Slack message at a time7h◆Why corporate AI super PACs spent $27 million on a local election7h◆How GPT-5 helped immunologist Derya Unutmaz solve a 3-year-old mystery7h◆Something’s off with Midjourney’s pivot to body scanners8h◆The Fitbit Air takes a smarter approach to the AI health dumpster fire9h◆4 days left to save up to $190 on TechCrunch Founder Summit 202610h◆Sony’s AI Camera Assistant is exactly as bad as it looks11h◆Helping build shared standards for advanced AI11h◆Fika Jobs raises $4M to build a video-first hiring platform where AI agents interview candidates11h◆Meta launches cheaper smart glasses without Ray-Ban11h◆Build real agentic apps using CUGA: two dozen working examples on a lightweight harness11h◆The $400 million machine powering the future of chipmaking15h◆The running list: major tech layoffs in 2026 where employers cited AI23h◆OpenAI launches new initiative to help find and patch open source bugs1d◆Shipping huggingface_hub every week with AI, open tools, and a human in the loop1d◆Experimenting with the proposed Cross-Origin Storage API in Transformers.js1d◆How Omio is building the future of conversational travel1d◆Nvidia says its AI data center design runs hotter to use a lot less water1d◆Google Home will soon get better at recognizing you2h◆Hollywood is bending the knee to OpenAI2h◆Anthropic’s Claude Tag is learning your company, one Slack message at a time7h◆Why corporate AI super PACs spent $27 million on a local election7h◆How GPT-5 helped immunologist Derya Unutmaz solve a 3-year-old mystery7h◆Something’s off with Midjourney’s pivot to body scanners8h◆The Fitbit Air takes a smarter approach to the AI health dumpster fire9h◆4 days left to save up to $190 on TechCrunch Founder Summit 202610h◆Sony’s AI Camera Assistant is exactly as bad as it looks11h◆Helping build shared standards for advanced AI11h◆Fika Jobs raises $4M to build a video-first hiring platform where AI agents interview candidates11h◆Meta launches cheaper smart glasses without Ray-Ban11h◆Build real agentic apps using CUGA: two dozen working examples on a lightweight harness11h◆The $400 million machine powering the future of chipmaking15h◆The running list: major tech layoffs in 2026 where employers cited AI23h◆OpenAI launches new initiative to help find and patch open source bugs1d◆Shipping huggingface_hub every week with AI, open tools, and a human in the loop1d◆Experimenting with the proposed Cross-Origin Storage API in Transformers.js1d◆How Omio is building the future of conversational travel1d◆Nvidia says its AI data center design runs hotter to use a lot less water1d◆
News/Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers
arxiv
PublishedMay 20, 2026 at 4:00 AM

Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers

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

arXiv:2601.15014v2 Announce Type: replace-cross Abstract: We study in-context learning for nonparametric regression with $\alpha$-H\"older smooth regression functions, for some $\alpha>0$. We prove that, with $n$ in-context examples and $d$-dimensional regression covariates, a pretrained transformer

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 →
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