Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Gradient-Based Data Valuation Improves Curriculum Learning for Game-Theoretic Motion Planning
Shihao Li, Jiachen Li, Dongmei Chen
We demonstrate that gradient-based data valuation produces curriculum orderings that significantly outperform metadata-based heuristics for training game-theoretic motion planners.…
cs.LG2025
Natural Geometry of Robust Data Attribution: From Convex Models to Deep Networks
Shihao Li, Jiachen Li, Dongmei Chen
Data attribution methods identify which training examples are responsible for a model's predictions, but their sensitivity to distributional perturbations undermines practical reli…
cs.LG2025
Algorithm-Relative Trajectory Valuation in Policy Gradient Control
Shihao Li, Jiachen Li, Jiamin Xu +3
We study how trajectory value depends on the learning algorithm in policy-gradient control. Using Trajectory Shapley in an uncertain LQR, we find a negative correlation between Per…