Search Results for author:
Found 3 papers, 0 papers with code
Highway Reinforcement Learning
We show, however, that such IS-free methods underestimate the optimal value function (VF), especially for large $n$, restricting their capacity to efficiently utilize information from distant future time steps.
Improving Accelerated Federated Learning with Compression and Importance Sampling
In this setting, the communication between the server and clients poses a major bottleneck.
Can 5th Generation Local Training Methods Support Client Sampling? Yes!
The celebrated FedAvg algorithm of McMahan et al. (2017) is based on three components: client sampling (CS), data sampling (DS) and local training (LT).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
