4 papers
When is Offline Policy Selection Sample Efficient for Reinforcement Learning?
Vincent Liu, Prabhat Nagarajan, Andrew Patterson +1
Offline reinforcement learning algorithms often require careful hyperparameter tuning. Before deployment, we need to select amongst a set of candidate policies. However, there is l…
Dynamic Rebatching for Efficient Early-Exit Inference with DREX
Xuting Liu, Daniel Alexander, Siva Kesava Reddy Kakarla +2
Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However…
Context-Action Embedding Learning for Off-Policy Evaluation in Contextual Bandits
Kushagra Chandak, Vincent Liu, Haanvid Lee
We consider off-policy evaluation (OPE) in contextual bandits with finite action space. Inverse Propensity Score (IPS) weighting is a widely used method for OPE due to its unbiased…
The Dawn of Disaggregation and the Coherence Conundrum: A Call for Federated Coherence
Jaewan Hong, Marcos K. Aguilera, Emmanuel Amaro +3
Disaggregated memory is an upcoming data center technology that will allow nodes (servers) to share data efficiently. Sharing data creates a debate on the level of cache coherence…