Jacob Clarysse

According to our database, Jacob Clarysse authored at least 4 papers between 2022 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

How robust accuracy suffers from certified training with convex relaxations.

Piersilvio De Bartolomeis, Jacob Clarysse, Amartya Sanyal, Fanny Yang

CoRR, 2023

Margin-based sampling in high dimensions: When being active is less efficient than staying passive.

Alexandru Tifrea, Jacob Clarysse, Fanny Yang

Proceedings of the International Conference on Machine Learning, 2023

Why adversarial training can hurt robust accuracy.

Jacob Clarysse, Julia Hörrmann, Fanny Yang

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Uniform versus uncertainty sampling: When being active is less efficient than staying passive.

Alexandru Tifrea, Jacob Clarysse, Fanny Yang

CoRR, 2022