B2P-Corr: Batch-to-Population Gradient Estimators for Non-Decomposable Correlation Losses
Published in NeurIPS 2026 (Poster, 25.7% acceptance rate), 2026
Keywords: Mini-batch Optimization, Non-decomposable Objectives, Correlation Learning
Authors: Jingquan Yan, Yuwei Miao, Peiran Yu, Junzhou Huang
Recommended citation: Jingquan Yan, Yuwei Miao, Peiran Yu, Junzhou Huang. "B2P-Corr: Batch-to-Population Gradient Estimators for Non-Decomposable Correlation Losses." NeurIPS 2026.