Advait Parulekar

regret bound (2) representation learning (1) contrastive learning (1) reinforcement learning (1) model misspecification (1) in-context learning (1) policy learning (1) linear function approximation (1) stochastic shortest path (1) contextual bandit (1) sublinear regret (1) regression task (1) softmax attention (1) function lipschitzness (1) nearest-neighbor predictor (1) pretraining task (1) stationary policy (1) linear markov decision process (1) infonce loss (1) cluster-preserving representation (1)