conftrace_

gradient decomposition

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

one-stage training (1) neural network editing (1) task consolidation (1) surrogate gap (1) perturbed loss (1) parameter editing (1) neural network (1) layer-wise optimization (1) auxiliary task (1) flat minima (1)

Papers

Fast Model Editing at Scale ICLR 2022 Surrogate Gap Minimization Improves Sharpness-Aware Training ICLR 2022 AUXILIARY TASK UPDATE DECOMPOSITION: THE GOOD, THE BAD AND THE NEUTRAL ICLR 2021 Layerwise Optimization by Gradient Decomposition for Continual Learning CVPR 2021 Training Generative Adversarial Networks in One Stage CVPR 2021