conftrace_

second-order derivative

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

tensor expression (1) neural network hessian (1) layer-wise error (1) curvature approximation (1) mini-batch gradient (1) optimal brain surgeon (1) deep linear network (1) layer-wise pruning (1) rank deficiency (1) symbolic computation (1)

Papers

Convexity Certificates for Symbolic Tensor Expressions IJCAI 2024 Analytic Insights into Structure and Rank of Neural Network Hessian Maps NeurIPS 2021 BackPACK: Packing more into Backprop ICLR 2020 Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon NeurIPS 2017