·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions34m◆Mapping Scientific Literature with Large Language Models and Topic Modeling34m◆Grounding Computer Use Agents on Human Demonstrations34m◆Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models34m◆LSTM based IoT Device Identification34m◆Breaking the Ice: Analyzing Cold Start Latency in vLLM34m◆Higher order PCA-like rotation-invariant features for detailed shape descriptors modulo rotation34m◆Minimal surfaces, Knots, and Neural Networks34m◆CCKS: Consensus-based Communication and Knowledge Sharing34m◆APPO: Agentic Procedural Policy Optimization34m◆Noise-Aware Framework for Correcting Corrupted Labels34m◆Using Explainability as a Training-Time Reliability Signal for Efficient ECG Classification34m◆Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity34m◆Measuring Semantic Progress in Multi-turn Dialogue via Information Gain34m◆Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems34m◆Persistent Homology as a Theory of Emergent Structure34m◆Bypassing Prompt Guards in Production with Controlled-Release Prompting34m◆Open Materials Generation with Inference-Time Reinforcement Learning34m◆Mechanisms of Introspective Awareness34m◆Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data34m◆Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions34m◆Mapping Scientific Literature with Large Language Models and Topic Modeling34m◆Grounding Computer Use Agents on Human Demonstrations34m◆Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models34m◆LSTM based IoT Device Identification34m◆Breaking the Ice: Analyzing Cold Start Latency in vLLM34m◆Higher order PCA-like rotation-invariant features for detailed shape descriptors modulo rotation34m◆Minimal surfaces, Knots, and Neural Networks34m◆CCKS: Consensus-based Communication and Knowledge Sharing34m◆APPO: Agentic Procedural Policy Optimization34m◆Noise-Aware Framework for Correcting Corrupted Labels34m◆Using Explainability as a Training-Time Reliability Signal for Efficient ECG Classification34m◆Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity34m◆Measuring Semantic Progress in Multi-turn Dialogue via Information Gain34m◆Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems34m◆Persistent Homology as a Theory of Emergent Structure34m◆Bypassing Prompt Guards in Production with Controlled-Release Prompting34m◆Open Materials Generation with Inference-Time Reinforcement Learning34m◆Mechanisms of Introspective Awareness34m◆Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data34m◆
News/Smoothed Analysis of Learning from Positive Samples
arxiv
PublishedMay 13, 2026 at 4:00 AM
—neutral

Smoothed Analysis of Learning from Positive Samples

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

arXiv:2504.10428v2 Announce Type: replace-cross Abstract: Binary classification from positive-only samples is a variant of PAC learning where the learner receives i.i.d. positive samples and aims to learn a classifier with low error. Previous work by Natarajan, Gereb-Graus, and Shvaytser characteriz

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
arxivGeneralizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions34marxivMapping Scientific Literature with Large Language Models and Topic Modeling34marxivGrounding Computer Use Agents on Human Demonstrations34marxivEmbodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models34m
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