Cover Image

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ngnawé, Jonas, Heuillet, Maxime, Sahoo, Sabyasachi, Pequignot, Yann, Ahmad, Ola, Durand, Audrey, Precioso, Frédéric, Gagné, Christian
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
by: Ngnawé, Jonas, et al.
Published: (2024)

A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
by: Heuillet, Maxime, et al.
Published: (2025)

A Layer Selection Approach to Test Time Adaptation
by: Sahoo, Sabyasachi, et al.
Published: (2024)

Randomized Confidence Bounds for Stochastic Partial Monitoring
by: Heuillet, Maxime, et al.
Published: (2024)

Neural Active Learning Meets the Partial Monitoring Framework
by: Heuillet, Maxime, et al.
Published: (2024)

LLM-as-a-Judge: Toward World Models for Slate Recommendation Systems
by: Bonin, Baptiste, et al.
Published: (2025)

Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
by: Heuillet, Maxime, et al.
Published: (2025)

Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets
by: Ngnawe, Jonas, et al.
Published: (2023)

TrackPGD: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers
by: Nokabadi, Fatemeh Nourilenjan, et al.
Published: (2024)

GROOD: GRadient-Aware Out-of-Distribution Detection
by: ElAraby, Mostafa, et al.
Published: (2023)

Towards Better: A motivated introduction to better-quasi-orders
by: Pequignot, Yann
Published: (2016)

Finite versus infinite: an insufficient shift
by: Pequignot, Yann
Published: (2016)

Faithful and Robust Local Interpretability for Textual Predictions
by: Lopardo, Gianluigi, et al.
Published: (2023)

Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs
by: Taraghi, Mina, et al.
Published: (2025)

A well-quasi-order for continuous functions
by: Carroy, Raphaël, et al.
Published: (2024)

Automated Data Curation for Robust Language Model Fine-Tuning
by: Chen, Jiuhai, et al.
Published: (2024)

Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare
by: Tupper, Adam, et al.
Published: (2025)

FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics
by: Du, Yupei, et al.
Published: (2023)

Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
by: Li, Jiaqi, et al.
Published: (2023)

Embeddability on functions: order and chaos
by: Carroy, Raphaël, et al.
Published: (2018)

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
by: Tajwar, Fahim, et al.
Published: (2024)

On the Robustness Tradeoff in Fine-Tuning
by: Li, Kunyang, et al.
Published: (2025)

Tuning-Free, Low Memory Robust Estimator to Mitigate GPS Spoofing Attacks
by: Lee, Junhwan, et al.
Published: (2019)

Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
by: Ran, Yide, et al.
Published: (2025)

The Magic Correlations: Understanding Knowledge Transfer from Pretraining to Supervised Fine-Tuning
by: Fan, Simin, et al.
Published: (2026)

Convergence Rates of the Regularized Optimal Transport : Disentangling Suboptimality and Entropy
by: Malamut, Hugo, et al.
Published: (2023)

El oficio de pensar. Visiones y papeles de Pierre Bourdieu
by: Bruno Péquignot
Published: (2002)

Third-dredge-up oxygen in planetary nebulae?
by: D. Péquignot
Published: (2000)

La sociologie de l’art et de la culture en France: un état des lieux
by: Bruno Péquignot
Published: (2005)

Caught between two states: The compromise in acclimation of photosynthesis, transpiration and mesophyll conductance to different amplitudes of fluctuating irradiance
by: Maxime Durand, et al.
Published: (2024)

Source-Optimal Training is Transfer-Suboptimal
by: Hedges, C. Evans
Published: (2025)

Understanding Post-hoc Explainers: The Case of Anchors
by: Lopardo, Gianluigi, et al.
Published: (2023)

A Sea of Words: An In-Depth Analysis of Anchors for Text Data
by: Lopardo, Gianluigi, et al.
Published: (2022)

Attention Meets Post-hoc Interpretability: A Mathematical Perspective
by: Lopardo, Gianluigi, et al.
Published: (2024)

Recommender Systems for Democracy: Toward Adversarial Robustness in Voting Advice Applications
by: Berdoz, Frédéric, et al.
Published: (2025)

Selective Fine-Tuning for Targeted and Robust Concept Unlearning
by: Mansi, et al.
Published: (2026)

AutoFT: Learning an Objective for Robust Fine-Tuning
by: Choi, Caroline, et al.
Published: (2024)

Robust Graph Fine-Tuning with Adversarial Graph Prompting
by: Zhang, Ziyan, et al.
Published: (2026)

A Review on Efficient and Scalable Graph‐Based Clustering Algorithms for Protein Complex Identification in PPI Networks
by: Sabyasachi Patra, et al.
Published: (2025)

Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
by: Lv, Kangtao, et al.
Published: (2024)