↓Skip to main content

🏢 Washington State University

Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
·2087 words·10 mins· loading · loading
AI Theory Optimization 🏢 Washington State University
IGNITE improves offline optimization by incorporating surrogate gradient norm to reduce model sharpness, boosting performance up to 9.6%
Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration
·4855 words·23 mins· loading · loading
Machine Learning Deep Learning 🏢 Washington State University
RC3P, a novel algorithm, significantly reduces prediction set sizes in class-conditional conformal prediction while guaranteeing class-wise coverage, even on imbalanced datasets.
Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
·2127 words·10 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 Washington State University
WSAC, a novel algorithm, robustly optimizes safe offline RL policies using adversarial training, guaranteeing improved performance over reference policies with limited data.