PowerStep delivers coordinate-wise adaptive optimization by nonlinearly transforming a momentum buffer under an lp-norm steepest-descent geometry, matching Adam convergence with half the memory and supporting aggressive quantization.
International Conference on Learning Representations , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
AGoQ delivers up to 52% lower memory use and 1.34x faster training for 8B-32B LLaMA models by using near-4-bit adaptive activations and 8-bit gradients while preserving pretraining convergence and downstream accuracy.
citing papers explorer
-
PowerStep: Memory-Efficient Adaptive Optimization via $\ell_p$-Norm Steepest Descent
PowerStep delivers coordinate-wise adaptive optimization by nonlinearly transforming a momentum buffer under an lp-norm steepest-descent geometry, matching Adam convergence with half the memory and supporting aggressive quantization.
-
AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
AGoQ delivers up to 52% lower memory use and 1.34x faster training for 8B-32B LLaMA models by using near-4-bit adaptive activations and 8-bit gradients while preserving pretraining convergence and downstream accuracy.