FP32-converged language models enter a post-convergence phase where INT4 quantization error explodes while FP32 perplexity remains stable, with onset tied to fine convergence rather than learning rate decay.
InInternational Conference on Machine Learning
2 Pith papers cite this work, alongside 16 external citations. Polarity classification is still indexing.
2
Pith papers citing it
16
external citations · external index
years
2026 2representative citing papers
SEADA introduces an analytical framework combining cost models, mapping tools, and entropy-based precision selection to optimize mixed-precision DNNs on multi-precision spatial architectures.
citing papers explorer
-
When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence
FP32-converged language models enter a post-convergence phase where INT4 quantization error explodes while FP32 perplexity remains stable, with onset tied to fine convergence rather than learning rate decay.
-
SEADA: An efficient methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures
SEADA introduces an analytical framework combining cost models, mapping tools, and entropy-based precision selection to optimize mixed-precision DNNs on multi-precision spatial architectures.