Gaon An

adversarial attack (2) offline reinforcement learning (2) neural network pruning (1) contrastive learning (1) reward modeling (1) policy optimization (1) network efficiency (1) query efficiency (1) neural network optimization (1) gradient estimation (1) discrete optimization (1) quadratic programming (1) black-box attack (1) ensemble method (1) randomized smoothing (1) adversarial defense (1) adversarial perturbation (1) bi-level optimization (1) uncertainty estimation (1) preference-based reinforcement learning (1)