Sample-Optimal Multi-Group Learning with an ERM Oracle
cs.LG, cs.DS, cs.GT
Submitted: 2026-10-11
Updated: 2026-10-11
Sources
- Oracle Efficient Algorithms for Groupwise Regret
- Group-realizable multi-group learning by minimizing empirical risk
- The price of multi-group transductive learning
- Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs
- The Sample Complexity of Multicalibration
- Group-wise oracle-efficient algorithms for online multi-group learning
- Oracle Efficient Online Multicalibration and Omniprediction
- Optimal Deterministic Multicalibration and Omniprediction
- Oracle-efficient Hybrid Learning with Constrained Adversaries
- Oracle-Efficient Hybrid Online Learning with Unknown Distribution
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks