Proposes Architecture-driven Shift (ADS) as an architecture-based proxy for logit shift in continual learning, derived from spectral norm scaling, optimization path length and task conflict, with monotonic correlation rs >= 0.731 across 175 architectures and utility as expected calibration error pro
Hallmarks of optimiza- tion trajectories in neural networks: Directional exploration and redundancy.arXiv preprint arXiv:2403.07379,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift
Proposes Architecture-driven Shift (ADS) as an architecture-based proxy for logit shift in continual learning, derived from spectral norm scaling, optimization path length and task conflict, with monotonic correlation rs >= 0.731 across 175 architectures and utility as expected calibration error pro