Tina Behnia

According to our database, Tina Behnia authored at least 7 papers between 2022 and 2024.

Collaborative distances:

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

2024

Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations.

Yize Zhao, Tina Behnia, Vala Vakilian, Christos Thrampoulidis

CoRR, 2024

Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features.

Tina Behnia, Christos Thrampoulidis

Proceedings of the IEEE International Symposium on Information Theory, 2024

Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching.

Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia, Jaidev Gill, Christos Thrampoulidis

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Supervised-Contrastive Loss Learns Orthogonal Frames and Batching Matters.

Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia, Jaidev Gill, Christos Thrampoulidis

CoRR, 2023

On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data.

Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian, Christos Thrampoulidis

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Imbalance Trouble: Revisiting Neural-Collapse Geometry.

Christos Thrampoulidis, Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia

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

On how to avoid exacerbating spurious correlations when models are overparameterized.

Tina Behnia, Ke Wang, Christos Thrampoulidis

Proceedings of the IEEE International Symposium on Information Theory, 2022