Maissam Barkeshli

According to our database, Maissam Barkeshli authored at least 11 papers between 2019 and 2026.

Collaborative distances:

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

2026

Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate.

Dayal Singh Kalra, Maissam Barkeshli

CoRR, May, 2026

Artificial Intelligence and the Structure of Mathematics.

Maissam Barkeshli, Michael R. Douglas, Michael H. Freedman

CoRR, April, 2026

On the origin of neural scaling laws: from random graphs to natural language.

Maissam Barkeshli, Alberto Alfarano, Andrey Gromov

CoRR, January, 2026

2025

Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and Interpretability.

Tao Tao, Maissam Barkeshli

CoRR, October, 2025

When Can You Get Away with Low Memory Adam?

Dayal Singh Kalra, John Kirchenbauer, Maissam Barkeshli, Tom Goldstein

CoRR, March, 2025

(How) Can Transformers Predict Pseudo-Random Numbers?

Tao Tao, Darshil Doshi, Dayal Singh Kalra, Tianyu He, Maissam Barkeshli

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos.

Dayal Singh Kalra, Tianyu He, Maissam Barkeshli

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Why Warmup the Learning Rate? Underlying Mechanisms and Improvements.

Dayal Singh Kalra, Maissam Barkeshli

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Phase diagram of training dynamics in deep neural networks: effect of learning rate, depth, and width.

Dayal Singh Kalra, Maissam Barkeshli

CoRR, 2023

Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width.

Dayal Singh Kalra, Maissam Barkeshli

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2019

Universal logical gates with constant overhead: instantaneous Dehn twists for hyperbolic quantum codes.

Ali Lavasani, Guanyu Zhu, Maissam Barkeshli

Quantum, 2019