2 papers
cs.LG2026
VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation
Eli Corn, Daphna Weinshall
Deep learning models may converge to suboptimal solutions despite strong validation accuracy, masking an optimization failure we term Trajectory Deviation. This is because as train…
cs.LG2025
Forget Me Not: Fighting Local Overfitting with Knowledge Fusion and Distillation
Uri Stern, Eli Corn, Daphna Weinshall
Overfitting in deep neural networks occurs less frequently than expected. This is a puzzling observation, as theory predicts that greater model capacity should eventually lead to o…