◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Tina Behnia

3 papers here

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author2
  • last author1

Across the 3 of 3 papers where every author was matched, so the position is known.

fields
  • cs.LG3
same name
  • Tina Behnia — 2 papers, h 5

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20222024
most citedImbalance Trouble: Revisiting Neural-Collapse Geometry

13 citations · 14 across the 3 of their papers we have counts for

collaborators

3 papers

cs.LG2024

Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features

Tina Behnia, Christos Thrampoulidis

Recent findings reveal that over-parameterized deep neural networks, trained beyond zero training-error, exhibit a distinctive structural pattern at the final layer, termed as Neur…

cs.LG2023★ 1 cited

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

Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian +1

Various logit-adjusted parameterizations of the cross-entropy (CE) loss have been proposed as alternatives to weighted CE for training large models on label-imbalanced data far bey…

cs.LG2022★ 13 cited

Imbalance Trouble: Revisiting Neural-Collapse Geometry

Christos Thrampoulidis, Ganesh R. Kini, Vala Vakilian +1

Neural Collapse refers to the remarkable structural properties characterizing the geometry of class embeddings and classifier weights, found by deep nets when trained beyond zero t…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.