Active Sequential Two-Sample Testing

no code implementations • 30 Jan 2023 • Weizhi Li, Karthikeyan Natesan Ramamurthy, Prad Kadambi, Pouria Saidi, Gautam Dasarathy, Visar Berisha

The classification model is adaptively updated and then used to guide an active query scheme called bimodal query to label sample features in the regions with high dependency between the feature variables and the label variables.

Two-sample testing valid +1

Comparing Fisher Information Regularization with Distillation for DNN Quantization

no code implementations • NeurIPS Workshop DL-IG 2020 • Prad Kadambi, Karthikeyan Natesan Ramamurthy, Visar Berisha

A large body of work addresses deep neural network (DNN) quantization and pruning to mitigate the high computational burden of deploying DNNs.

Knowledge Distillation Quantization

Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation

no code implementations • 14 Jan 2020 • Chuteng Zhou, Prad Kadambi, Matthew Mattina, Paul N. Whatmough

Hence, for successful deployment on analog accelerators, it is essential to be able to train deep neural networks to be robust to random continuous noise in the network weights, which is a somewhat new challenge in machine learning.

Knowledge Distillation