Ron Dorfman

meta learning (1) model compression (1) federated learning (1) stochastic optimization (1) temporal difference learning (1) offline reinforcement learning (1) variational inference (1) convex optimization (1) bayesian reinforcement learning (1) belief state (1) markov chain (1) communication efficiency (1) mixing time (1) exploration strategy (1) reference-free evaluation (1) multi-level monte carlo (1) cross-device setting (1) downlink compression (1) large language model (1) tool-use capability (1)