bi-level optimization
An optimization framework involving two levels of problems, where the solution to the upper level depends on the solution to the lower level, often used in hyperparameter tuning.
- Backdoor Mitigation via Invertible Pruning Masks
- Bandit Guided Submodular Curriculum for Adaptive Subset Selection
- Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
- Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification
- Differentiation Through Black-Box Quadratic Programming Solvers
- DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning
- FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning
- Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
- Inverse Methods for Missing Data Imputation
- KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis
- On the Sample Complexity Bounds of Bilevel Reinforcement Learning
- Semi-Supervised Regression with Heteroscedastic Pseudo-Labels
- TANDEM: Bi-Level Data Mixture Optimization with Twin Networks