paper-with-me

홈 › Papers

Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning

2026-06-08 · Ghodsiyeh Rostami, Po-Han Chen, Mahdi S. Hosseini arxiv

Parameter-efficient fine-tuning (PEFT) aims to adapt pretrained models with a small trainable parameter subset, however, most existing methods choose this subset from fixed architectural heuristics rather than using dynamic, task-aware criteria. We introduce \textbf{FisherAdapTune}, a Fisher-guided Adaptive Fine-Tuning framework that progressively selects parameter groups by tracking the temporal drift of their Fisher geometry. Starting from a PAC-Bayesian view of fine-tuning, we decompose the generalization error bound into Fisher-weighted update costs and show that parameter groups whose curvature contribution has stabilized can be frozen to reduce the error bound without interrupting the remaining adaptation dynamics. FisherAdapTune formulates this criterion with a scale-invariant Jensen-Shannon distance between consecutive Fisher distributions, yielding an adaptive active parameter set. We evaluate our approach on a downstream segmentation task, and results show FisherAdapTune improves the in-distribution performance and zero-shot transfer in multiple settings, validating that Fisher structural drift is a useful signal for efficient, task-aware adaptation. We release our \href{https://github.com/AtlasAnalyticsLab/FisherAdapTune}{code} publicly to enable further application of our proposed approach.

📄 PDF Abstract BibTeX arXiv:2606.10196

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation

2025-11-25 · Shilei Cao, Ziyang Gong, Hehai Lin, Yang Liu 외 arxiv

In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstream tasks. However, existing specialized P…

parameter-efficient fine-tuningSemantic Segmentation

Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models

2025-09-26 · Shilei Cao, Hehai Lin, Jiashun Cheng, Yang Liu 외 arxiv

While recent advances in machine learning have equipped Weather Foundation Models (WFMs) with substantial generalization capabilities across diverse downstream tasks, the escalating computational requirements associated …

parameter-efficient fine-tuning

FGGM: Fisher-Guided Gradient Masking for Continual Learning

2026-01-26 · Chao-Hong Tan, Qian Chen, Wen Wang, Yukun Ma 외 arxiv

Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically selecting parameters for updates using …

Continual LearningCode Generation

Safety-Driven Battery Charging: A Fisher Information-guided Adaptive MPC with Real-time Parameter Identification

2024-06-12 · Jorge Espin, Yuichi Kajiura, Dong Zhang

Lithium-ion (Li-ion) batteries are ubiquitous in modern energy storage systems, highlighting the critical need to comprehend and optimize their performance. Yet, battery models often exhibit poor parameter identifiabilit…

ManagementModel Predictive Controlparameter estimation

Composable and adaptive design of machine learning interatomic potentials guided by Fisher-information analysis

2025-04-27 · Weishi Wang, Mark K. Transtrum, Vincenzo Lordi, Vasily V. Bulatov 외

An adaptive physics-informed model design strategy for machine-learning interatomic potentials (MLIPs) is proposed. This strategy follows an iterative reconfiguration of composite models from single-term models, followed…

Hyperparameter Optimization