5 papers
Scale When Needed: Adaptive Neuron-level Mixed Precision Quantization Aware Training
Ayush K. Varshney, Konstantinos Vandikas, Šarūnas Girdzijauskas +2
Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware Training (QAT) has emerged as a…
When to restart? Exploring escalating restarts on convergence
Ayush K. Varshney, Šarūnas Girdzijauskas, Konstantinos Vandikas +1
Learning rate scheduling plays a critical role in the optimization of deep neural networks, directly influencing convergence speed, stability, and generalization. While existing sc…
Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention
Ayush K. Varshney, Vicenç Torra
Machine Unlearning allows participants to remove their data from a trained machine learning model in order to preserve their privacy, and security. However, the machine unlearning…
Unlearning Clients, Features and Samples in Vertical Federated Learning
Ayush K. Varshney, Konstantinos Vandikas, Vicenç Torra
Federated Learning (FL) has emerged as a prominent distributed learning paradigm. Within the scope of privacy preservation, information privacy regulations such as GDPR entitle use…
Efficient Federated Unlearning under Plausible Deniability
Ayush K. Varshney, Vicenç Torra
Privacy regulations like the GDPR in Europe and the CCPA in the US allow users the right to remove their data ML applications. Machine unlearning addresses this by modifying the ML…