Amirhesam Abedsoltan

According to our database, Amirhesam Abedsoltan authored at least 9 papers between 2022 and 2025.

Collaborative distances:

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

2025

Task Generalization With AutoRegressive Compositional Structure: Can Learning From <i>D</i> Tasks Generalize to <i>D</i>^T Tasks?

Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen, Hongzhou Lin, Jingzhao Zhang, Mikhail Belkin

CoRR, February, 2025

2024

Fast training of large kernel models with delayed projections.

Amirhesam Abedsoltan, Siyuan Ma, Parthe Pandit, Mikhail Belkin

CoRR, 2024

Context-Scaling versus Task-Scaling in In-Context Learning.

Amirhesam Abedsoltan, Adityanarayanan Radhakrishnan, Jingfeng Wu, Mikhail Belkin

CoRR, 2024

Uncertainty Estimation with Recursive Feature Machines.

Daniel Gedon, Amirhesam Abedsoltan, Thomas B. Schön, Mikhail Belkin

Proceedings of the Uncertainty in Artificial Intelligence, 2024

On the Nyström Approximation for Preconditioning in Kernel Machines.

Amirhesam Abedsoltan, Parthe Pandit, Luis Rademacher, Mikhail Belkin

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

On Emergence of Clean-Priority Learning in Early Stopped Neural Networks.

Chaoyue Liu, Amirhesam Abedsoltan, Mikhail Belkin

CoRR, 2023

Toward Large Kernel Models.

Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit

Proceedings of the International Conference on Machine Learning, 2023

2022

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting.

Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit, Mikhail Belkin, Preetum Nakkiran

CoRR, 2022

Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting.

Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit, Mikhail Belkin, Preetum Nakkiran

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022