13 citations · 25 across the 7 of their papers we have counts for
7 papers
Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia +2
Supervised contrastive loss (SCL) is a competitive and often superior alternative to the cross-entropy loss for classification. While prior studies have demonstrated that both loss…
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…
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…
Label-Imbalanced and Group-Sensitive Classification under Overparameterization
Ganesh Ramachandra Kini, Orestis Paraskevas, Samet Oymak +1
The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cr…
Analytic Study of Double Descent in Binary Classification: The Impact of Loss
Ganesh Kini, Christos Thrampoulidis
Extensive empirical evidence reveals that, for a wide range of different learning methods and datasets, the risk curve exhibits a double-descent (DD) trend as a function of the mod…
A Rate-Optimal Construction of Codes with Sequential Recovery with Low Block Length
Balaji Srinivasan Babu, Ganesh R. Kini, P. Vijay Kumar
An erasure code is said to be a code with sequential recovery with parameters and , if for any erased code symbols, there is an -step recovery process in which…
A Tight Rate Bound and a Matching Construction for Locally Recoverable Codes with Sequential Recovery From Any Number of Multiple Erasures
S. B. Balaji, Ganesh R. Kini, P. Vijay Kumar
An code is said to be locally recoverable in the presence of a single erasure, and with locality parameter , if each of the code symbols of $\mathcal{C…