Image de couverture de livre

Least but not Last: Fine-tuning Intermediate Principal Components for Better Performance-Forgetting Trade-Offs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Quercia, Alessio, Bangun, Arya, Assent, Ira, Scharr, Hanno
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Classifier Reconstruction Through Counterfactual-Aware Wasserstein Prototypes
par: Zhao, Xuan, et autres
Publié: (2025)

MRI Reconstruction with Regularized 3D Diffusion Model (R3DM)
par: Bangun, Arya, et autres
Publié: (2024)

1LoRA: Summation Compression for Very Low-Rank Adaptation
par: Quercia, Alessio, et autres
Publié: (2025)

Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging
par: Valdy, Laurentius, et autres
Publié: (2025)

Galaxy Morphology Classification with Counterfactual Explanation
par: Cao, Zhuo, et autres
Publié: (2025)

FlowTIE: Flow-based Transport of Intensity Equation for Phase Gradient Estimation from 4D-STEM Data
par: Bangun, Arya, et autres
Publié: (2025)

LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
par: Cao, Zhuo, et autres
Publié: (2025)

Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation
par: Paul, Richard D., et autres
Publié: (2024)

Enhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks
par: Quercia, Alessio, et autres
Publié: (2025)

Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning
par: Taheri, Ali, et autres
Publié: (2025)

Grow, Don't Overwrite: Fine-tuning Without Forgetting
par: Adila, Dyah, et autres
Publié: (2026)

DCFO: Density-Based Counterfactuals for Outliers -- Additional Material
par: Amico, Tommaso, et autres
Publié: (2025)

From Drops to Grid: Noise-Aware Spatio-Temporal Neural Process for Rainfall Estimation
par: Sarabia, Rafael Pablos, et autres
Publié: (2026)

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
par: Wołczyk, Maciej, et autres
Publié: (2024)

An Analytical Approach to Privacy and Performance Trade-Offs in Healthcare Data Sharing
par: Wei, Yusi, et autres
Publié: (2025)

ExDBSCAN: Explaining DBSCAN with Counterfactual Reasoning -- Additional Material
par: Matthews, Pernille, et autres
Publié: (2026)

Internal Evaluation of Density-Based Clusterings with Noise
par: Beer, Anna, et autres
Publié: (2025)

An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning
par: Bai, Andrew, et autres
Publié: (2024)

Fine-tuning Flow Matching Generative Models with Intermediate Feedback
par: Fan, Jiajun, et autres
Publié: (2025)

Data Preparation for Fairness-Performance Trade-Offs: A Practitioner-Friendly Alternative?
par: Voria, Gianmario, et autres
Publié: (2024)

Trade-Offs of Diagonal Fisher Information Matrix Estimators
par: Soen, Alexander, et autres
Publié: (2024)

Untrained Perceptual Loss for image denoising of line-like structures in MR images
par: Pfaehler, Elisabeth, et autres
Publié: (2024)

Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models
par: Morocutti, Tobias, et autres
Publié: (2025)

Temporal Subspace Clustering for Molecular Dynamics Data
par: Beer, Anna, et autres
Publié: (2024)

Ultrametric Cluster Hierarchies: I Want 'em All!
par: Draganov, Andrew, et autres
Publié: (2025)

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
par: Zhang, Zhixin, et autres
Publié: (2025)

Fine-tuning MLLMs Without Forgetting Is Easier Than You Think
par: Li, He, et autres
Publié: (2026)

Fine-tuning for Better Few Shot Prompting: An Empirical Comparison for Short Answer Grading
par: Walsh, Joel, et autres
Publié: (2025)

Fairness-Accuracy Trade-Offs: A Causal Perspective
par: Plecko, Drago, et autres
Publié: (2024)

Calibrated Principal Component Regression
par: Wu, Yixuan Florence, et autres
Publié: (2025)

First-See-Then-Design: A Multi-Stakeholder View for Optimal Performance-Fairness Trade-Offs
par: Gupta, Kavya, et autres
Publié: (2026)

Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks
par: Zhang, Guanhua, et autres
Publié: (2024)

Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
par: Singh, Naman Deep, et autres
Publié: (2025)

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models
par: Yao, Kai, et autres
Publié: (2024)

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
par: Kurtic, Eldar, et autres
Publié: (2024)

Heavy-Tailed Principal Component Analysis
par: Sayde, Mario, et autres
Publié: (2026)

Highly Adaptive Principal Component Regression
par: Wang, Mingxun, et autres
Publié: (2026)

Quasicyclic Principal Component Analysis
par: Rumsey, Susanna E., et autres
Publié: (2025)

Pruning Extensions and Efficiency Trade-Offs for Sustainable Time Series Classification
par: Fischer, Raphael, et autres
Publié: (2026)

Computational Discovery of Microstructured Composites with Optimal Stiffness-Toughness Trade-Offs
par: Li, Beichen, et autres
Publié: (2023)