Behnia, Tina

5 publications

ICLRW 2025 Can Transformers Learn Tasks of Varying Complexity In-Context? Puneesh Deora, Bhavya Vasudeva, Tina Behnia, Christos Thrampoulidis

ICLR 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

AISTATS 2023 On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian, Christos Thrampoulidis

NeurIPS 2022 Imbalance Trouble: Revisiting Neural-Collapse Geometry Christos Thrampoulidis, Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia

NeurIPSW 2022 On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian, Christos Thrampoulidis