Sarath Shekkizhar

According to our database, Sarath Shekkizhar authored at least 13 papers between 2019 and 2023.

Collaborative distances:

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

2023

Characterizing Large Language Model Geometry Solves Toxicity Detection and Generation.

Randall Balestriero, Romain Cosentino, Sarath Shekkizhar

CoRR, 2023

Study of Manifold Geometry Using Multiscale Non-Negative Kernel Graphs.

Carlos Hurtado, Sarath Shekkizhar, Javier Ruiz Hidalgo, Antonio Ortega

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning.

Romain Cosentino, Sarath Shekkizhar, Mahdi Soltanolkotabi, Salman Avestimehr, Antonio Ortega

CoRR, 2022

Channel Redundancy and Overlap in Convolutional Neural Networks with Channel-Wise NNK Graphs.

David Bonet, Antonio Ortega, Javier Ruiz Hidalgo, Sarath Shekkizhar

Proceedings of the IEEE International Conference on Acoustics, 2022

NNK-Means: Data summarization using dictionary learning with non-negative kernel regression.

Sarath Shekkizhar, Antonio Ortega

Proceedings of the 30th European Signal Processing Conference, 2022

2021

NNK-Means: Dictionary Learning using Non-Negative Kernel regression.

Sarath Shekkizhar, Antonio Ortega

CoRR, 2021

Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation.

David Bonet, Antonio Ortega, Javier Ruiz Hidalgo, Sarath Shekkizhar

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2021

Model selection and explainability in neural networks using a polytope interpolation framework.

Sarath Shekkizhar, Antonio Ortega

Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, 2021

2020

DeepNNK: Explaining deep models and their generalization using polytope interpolation.

Sarath Shekkizhar, Antonio Ortega

CoRR, 2020

Graph-based Deep Learning Analysis and Instance Selection.

Keisuke Nonaka, Sarath Shekkizhar, Antonio Ortega

Proceedings of the 22nd IEEE International Workshop on Multimedia Signal Processing, 2020

Efficient Graph Construction For Image Representation.

Sarath Shekkizhar, Antonio Ortega

Proceedings of the IEEE International Conference on Image Processing, 2020

Graph Construction from Data by Non-Negative Kernel Regression.

Sarath Shekkizhar, Antonio Ortega

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Graph Construction from Data using Non Negative Kernel regression (NNK Graphs).

Sarath Shekkizhar, Antonio Ortega

CoRR, 2019