Arushi Gupta

representation learning (1) reinforcement learning (1) adversarial robustness (1) few-shot learning (1) online learning (1) feature attribution (1) model interpretability (1) markov chain (1) low-rank representation (1) regret bound (1) regret guarantee (1) model-free reinforcement learning (1) adversarial environment (1) online adaptation (1) parameter identification (1) model initialization (1) choice model (1) train-validation splitting (1) heat map (1) saliency method (1)