most citedAn Adaptive Method Stabilizing Activations for Enhanced Generalization

1 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025

Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-Tuning

Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko

We introduce LOREN, a curvature-aware zeroth-order (ZO) optimization method for fine-tuning large language models (LLMs). Existing ZO methods, which estimate gradients via finite d…

cs.LG20251 cited

NysAct: A Scalable Preconditioned Gradient Descent using Nystrom Approximation

Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko

Adaptive gradient methods are computationally efficient and converge quickly, but they often suffer from poor generalization. In contrast, second-order methods enhance convergence…

cs.LG20251 cited

An Adaptive Method Stabilizing Activations for Enhanced Generalization

Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko

We introduce AdaAct, a novel optimization algorithm that adjusts learning rates according to activation variance. Our method enhances the stability of neuron outputs by incorporati…

cs.LG2025

MAC: An Efficient Gradient Preconditioning using Mean Activation Approximated Curvature

Hyunseok Seung, Jaewoo Lee, Hyunsuk Ko

Second-order optimization methods for training neural networks, such as KFAC, exhibit superior convergence by utilizing curvature information of loss landscape. However, it comes a…

cs.LG2025

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning

Qitao Tan, Jun Liu, Zheng Zhan +6

Large language models (LLMs) excel across various tasks, but standard first-order (FO) fine-tuning demands considerable memory, significantly limiting real-world deployment. Recent…