Convergence Rates for Neural-Network Estimation with Current-Status Data
2026-06-10T07:23:59Z•e3be7b83cd0676e268d37ae7ef732f4fda7c8fec7b66fd99aced0c429fb82b99
Boltzmann marginGromov-WassersteinItô mapSDEsactive learningcalibrationconformal predictioncurrent-status datadecision-calibrated uncertaintydiffusion/generative modelsdistributional shiftfederated learninggraph classificationheteroscedasticityhuman-AI teamingk-NNnear-exponential ratesneural networkspartition matroidpolar clusteringprobabilistic programming','program-based posterior training','Prange regularizationsieve MLEsubmodular optimizationtext-to-SQL
What happened
Collection of recent arXiv papers (June 10, 2026) presenting theoretical and applied advances in statistical machine learning and uncertainty-aware modeling. Key contributions include: neural-network sieve MLE convergence rates for current-status survival data; a robust active-learning approach for few-shot example selection in text-to-SQL with heteroscedasticity and partition-matroid constraints; a decision-calibrated conformal framework for pacing in streaming advertising that yields much tighter, policy-relevant uncertainty radii; k-NN classification consistency results in Gromov–Wassertein
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_stat_ml
- Record identifier
- e3be7b83cd0676e268d37ae7ef732f4fda7c8fec7b66fd99aced0c429fb82b99
- Enrichment time
- 2026-06-10T07:23:59Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.