Image de couverture de livre

Pruning Cannot Hurt Robustness: Certified Trade-offs in Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pedley, James, Etheridge, Benjamin, Roberts, Stephen J., Quinzan, Francesco
Format:	Preprint
Publié:	2025
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

Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning
par: Ye, Kai, et autres
Publié: (2025)

Model Merging by Output-Space Projection
par: Evans, Bethan, et autres
Publié: (2026)

Learning Decision Policies with Instrumental Variables through Double Machine Learning
par: Shao, Daqian, et autres
Publié: (2024)

Double Machine Learning for Conditional Moment Restrictions: IV Regression, Proximal Causal Learning and Beyond
par: Shao, Daqian, et autres
Publié: (2025)

Learning Counterfactually Invariant Predictors
par: Quinzan, Francesco, et autres
Publié: (2022)

Double Machine Learning Based Structure Identification from Temporal Data
par: Angelis, Emmanouil, et autres
Publié: (2023)

Detecting Changes in Causal Dependence with Kernels and Copulas
par: Gavioli-Akilagun, Shakeel, et autres
Publié: (2026)

Doubly Robust Alignment for Large Language Models
par: Xu, Erhan, et autres
Publié: (2025)

Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs
par: Song, Meichen, et autres
Publié: (2026)

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning
par: Song, Yuda, et autres
Publié: (2025)

Enhancing Certifiable Semantic Robustness via Robust Pruning of Deep Neural Networks
par: Hu, Hanjiang, et autres
Publié: (2025)

CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization
par: Wang, Derui, et autres
Publié: (2025)

AI Alignment in Medical Imaging: Unveiling Hidden Biases Through Counterfactual Analysis
par: Ma, Haroui, et autres
Publié: (2025)

Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
par: Lei, Runlin, et autres
Publié: (2025)

On the Trade-offs between Adversarial Robustness and Actionable Explanations
par: Krishna, Satyapriya, et autres
Publié: (2023)

Navigating Trade-offs: Policy Summarization for Multi-Objective Reinforcement Learning
par: Osika, Zuzanna, et autres
Publié: (2024)

Learning to Orchestrate Agents under Uncertainty
par: Oliver, Mary Chriselda Antony, et autres
Publié: (2026)

Where Do Reasoning Models Refuse?
par: Yamaguchi, Kureha, et autres
Publié: (2025)

A Fundamental Accuracy--Robustness Trade-off in Regression and Classification
par: Bahmani, Sohail
Publié: (2024)

Architecture Selection via the Trade-off Between Accuracy and Robustness
par: Deng, Zhun, et autres
Publié: (2019)

BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning
par: Gong, Shijin, et autres
Publié: (2026)

Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
par: Liu, Shijie, et autres
Publié: (2025)

RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing
par: Rekavandi, Aref Miri, et autres
Publié: (2024)

Learning Better Certified Models from Empirically-Robust Teachers
par: De Palma, Alessandro
Publié: (2026)

Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
par: Chen, Cheng, et autres
Publié: (2021)

Representation Invariance and Allocation: When Subgroup Balance Matters
par: Alloula, Anissa, et autres
Publié: (2025)

DeePM: Regime-Robust Deep Learning for Systematic Macro Portfolio Management
par: Wood, Kieran, et autres
Publié: (2026)

Deep Learning for Options Trading: An End-To-End Approach
par: Tan, Wee Ling, et autres
Publié: (2024)

LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning
par: Hu, Yanzhe, et autres
Publié: (2026)

A Recipe for Improved Certifiable Robustness
par: Hu, Kai, et autres
Publié: (2023)

On the Trade-off between Flatness and Optimization in Distributed Learning
par: Cao, Ying, et autres
Publié: (2024)

Safety-Oriented Pruning and Interpretation of Reinforcement Learning Policies
par: Gross, Dennis, et autres
Publié: (2024)

Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
par: Li, Zichao, et autres
Publié: (2026)

Graph Representational Learning: When Does More Expressivity Hurt Generalization?
par: Maskey, Sohir, et autres
Publié: (2025)

When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer
par: Liu, Shuqi, et autres
Publié: (2026)

Position: Certified Robustness Does Not (Yet) Imply Model Security
par: Cullen, Andrew C., et autres
Publié: (2025)

Robust off-policy Reinforcement Learning via Soft Constrained Adversary
par: Nakanishi, Kosuke, et autres
Publié: (2024)

Certifiably Robust Encoding Schemes
par: Saxena, Aman, et autres
Publié: (2024)

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity
par: Jiang, Zhengping, et autres
Publié: (2025)

Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
par: Najafi, Amir, et autres
Publié: (2024)