Yihan He

deep reinforcement learning (1) neural network compression (1) attention mechanism (1) in-context learning (1) global convergence (1) autonomous driving (1) nonparametric learning (1) nearest neighbor (1) gradient descent (1) weibull distribution (1) nearest neighbor classifier (1) optimization theory (1) gradient flow (1) mean-field limit (1) weight decay regularization (1) weight decay (1) transformer training (1) softmax attention (1) wasserstein gradient flow (1) gradient quantization (1)