Mansheej Paul

training dynamics (2) loss landscape (2) feature learning (1) in-context learning (1) kernel learning (1) linear regression (1) bayesian estimator (1) deep neural network (1) gradient norm (1) task diversity (1) sparse training (1) data pruning (1) loss surface (1) network initialization (1) iterative magnitude pruning (1) training dynamic (1) error norm (1) lottery ticket hypothesis (1) example importance (1) neural tangent kernel (1)