11 citations · 41 across the 18 of their papers we have counts for
4 papers · 1 filter
SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems
Kailash Gogineni, Sai Santosh Dayapule, Juan Gómez-Luna +6
Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, lead…
Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction
Hanhan Zhou, Tian Lan, Guru Venkataramani +1
Cross-device Federated Learning (FL) faces significant challenges where low-end clients that could potentially make unique contributions are excluded from training large models due…
MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization
Yongsheng Mei, Hanhan Zhou, Tian Lan +2
Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay signific…
On the Convergence of Heterogeneous Federated Learning with Arbitrary Adaptive Online Model Pruning
Hanhan Zhou, Tian Lan, Guru Venkataramani +1
One of the biggest challenges in Federated Learning (FL) is that client devices often have drastically different computation and communication resources for local updates. To this…