Bingqing Song

Deep Learning (3) Machine Learning (3) Optimization & Theory · Machine Learning (3) Optimization & Theory · Deep Learning (3) Architectures (2) Mathematics & Optimization (1) Learning Paradigms (1) Optimization (1)

neural network (2) convergence analysis (2) attention mechanism (1) communication complexity (1) distributed optimization (1) neural network optimization (1) loss landscape (1) gradient descent (1) linear regression (1) optimization theory (1) linear convergence (1) convergence guarantee (1) weight initialization (1) data heterogeneity (1) overparameterized model (1) gradient descent dynamics (1) attention kernel (1) overparameterized neural network (1) local sgd (1) federated learning (1)