Towards Efficient Hyperdimensional Computing Using Photonics

no code implementations • 29 Nov 2023 • Farbin Fayza, Cansu Demirkiran, Hanning Chen, Che-Kai Liu, Avi Mohan, Hamza Errahmouni, Sanggeon Yun, Mohsen Imani, David Zhang, Darius Bunandar, Ajay Joshi

Over the past few years, silicon photonics-based computing has emerged as a promising alternative to CMOS-based computing for Deep Neural Networks (DNN).

Better than the Best: Gradient-based Improper Reinforcement Learning for Network Scheduling

no code implementations • 1 May 2021 • Mohammani Zaki, Avi Mohan, Aditya Gopalan, Shie Mannor

We consider the problem of scheduling in constrained queueing networks with a view to minimizing packet delay.

reinforcement-learning Reinforcement Learning (RL) +1

Explicit Best Arm Identification in Linear Bandits Using No-Regret Learners

no code implementations • 13 Jun 2020 • Mohammadi Zaki, Avi Mohan, Aditya Gopalan

We study the problem of best arm identification in linearly parameterised multi-armed bandits.

Multi-Armed Bandits