activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate

Dayal Singh Kalra, Maissam Barkeshli

Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large language models (LLMs). This is…

cs.LG2026

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

Tao Tao, Maissam Barkeshli

We study the ability of Transformer models to learn sequences generated by Permuted Congruential Generators (PCGs), a widely used family of pseudo-random number generators (PRNGs).…

cs.LG2026

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

Maissam Barkeshli, Alberto Alfarano, Andrey Gromov

Scaling laws have played a major role in the modern AI revolution, providing practitioners predictive power over how the model performance will improve with increasing data, comput…

cs.LG2025

(How) Can Transformers Predict Pseudo-Random Numbers?

Tao Tao, Darshil Doshi, Dayal Singh Kalra +2

Transformers excel at discovering patterns in sequential data, yet their fundamental limitations and learning mechanisms remain crucial topics of investigation. In this paper, we s…

cs.LG2025

When Can You Get Away with Low Memory Adam?

Dayal Singh Kalra, John Kirchenbauer, Maissam Barkeshli +1

Adam is the go-to optimizer for training modern machine learning models, but it requires additional memory to maintain the moving averages of the gradients and their squares. While…

cs.LG2025

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

Dayal Singh Kalra, Tianyu He, Maissam Barkeshli

In gradient descent dynamics of neural networks, the top eigenvalue of the loss Hessian (sharpness) displays a variety of robust phenomena throughout training. This includes early…