HELENE is a proposed memory-efficient zeroth-order optimizer with annealed gradients and layer-wise clipped diagonal Hessian, claimed to converge in O(max layer dimension) steps.
Distributed second-order optimization using kronecker-factored approximations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization
HELENE is a proposed memory-efficient zeroth-order optimizer with annealed gradients and layer-wise clipped diagonal Hessian, claimed to converge in O(max layer dimension) steps.