Ganesh R. Kini

Orcid: 0000-0003-1175-9226

According to our database1, Ganesh R. Kini authored at least 12 papers between 2016 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Towards Understanding Overparameterized Neural Networks: Insights into Imbalances and Neural Representations
PhD thesis, 2024

Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Supervised-Contrastive Loss Learns Orthogonal Frames and Batching Matters.
CoRR, 2023

On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
Imbalance Trouble: Revisiting Neural-Collapse Geometry.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021
Label-Imbalanced and Group-Sensitive Classification under Overparameterization.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Phase Transitions for One-Vs-One and One-Vs-All Linear Separability in Multiclass Gaussian Mixtures.
Proceedings of the IEEE International Conference on Acoustics, 2021

2020
Analytic Study of Double Descent in Binary Classification: The Impact of Loss.
Proceedings of the IEEE International Symposium on Information Theory, 2020

2018
A Rate-Optimal Construction of Codes with Sequential Recovery with Low Block Length.
CoRR, 2018

Clay Codes: Moulding MDS Codes to Yield an MSR Code.
Proceedings of the 16th USENIX Conference on File and Storage Technologies, 2018

2017
A tight rate bound and a matching construction for locally recoverable codes with sequential recovery from any number of multiple erasures.
Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017

2016
A Bound on Rate of Codes with Locality with Sequential Recovery from Multiple Erasures.
CoRR, 2016


  Loading...