83 citations · 84 across the 8 of their papers we have counts for
3 papers · 1 filter
Energy and Latency First: How Deployment Constraints Reverse Time-Series Model Selection
Shruti Bothe, Illyyne Saffar, Ayush K. Varshney
AI models, and time-series models in particular are typically ranked by accuracy and deployed under constraints absent from that ranking. In this paper, we study a real setting whe…
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…