conftrace_

gradient statistics

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

optimizer state (1) block-wise quantization (1) low-rank projection (1) dynamic quantization (1) error feedback (1) memory footprint (1) memory efficiency (1) adaptive optimization (1) language model training (1) language modeling (1)

Papers

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics ICLR 2025 8-bit Optimizers via Block-wise Quantization ICLR 2022