Reducing the Adaptation Gap Through Reachable Fisher Geometry

arXiv:2609.36329 · cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Adaptation — 1× in this paper · explained in 1 episode

Sources

• Subgroups Matter for Robust Bias Mitigation
• BEiT: BERT Pre-Training of Image Transformers
• FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants
• FairSAM: Fair Classification on Corrupted Image Data Through Sharpness-Aware Minimization
• BackPACK: Packing more into backprop
• On Fairness of Low-Rank Adaptation of Large Models
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity
• Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
• Sharpness-Aware Minimization for Efficiently Improving Generalization
• LoRA: Low-Rank Adaptation of Large Language Models
• A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
• On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
• Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
• DoRA: Weight-Decomposed Low-Rank Adaptation
• DINOv2: Learning Robust Visual Features without Supervision
• FoRA: Fisher-orthogonal Rank Adaptation for Parameter-Efficient Fine-Tuning
• Ethical Fairness in Ubiquitous Health Sensing without Known Attributes
• Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
• DINOv3

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks