Imagen de Portada

Provably Safe Model Updates

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Elmecker-Plakolm, Leo, Fasterling, Pierre, Sosnin, Philip, Tsay, Calvin, Wicker, Matthew
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy
por: Sosnin, Philip, et al.
Publicado: (2025)

Certified Robustness to Data Poisoning in Gradient-Based Training
por: Sosnin, Philip, et al.
Publicado: (2024)

SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning
por: Anisimov, Maksim, et al.
Publicado: (2026)

Exact Certification of Data-Poisoning Attacks Using Mixed-Integer Programming
por: Sosnin, Philip, et al.
Publicado: (2026)

Certification for Differentially Private Prediction in Gradient-Based Training
por: Wicker, Matthew, et al.
Publicado: (2024)

Scaling Mixed-Integer Programming for Certification of Neural Network Controllers Using Bounds Tightening
por: Sosnin, Philip, et al.
Publicado: (2024)

Relaxation-Informed Training of Neural Network Surrogate Models
por: Tsay, Calvin
Publicado: (2026)

Training Neural ODEs Using Fully Discretized Simultaneous Optimization
por: Shapovalova, Mariia, et al.
Publicado: (2025)

Bayesian optimization as a flexible and efficient design framework for sustainable process systems
por: Paulson, Joel A., et al.
Publicado: (2024)

Towards Poisoning Robustness Certification for Natural Language Generation
por: Ghitu, Mihnea, et al.
Publicado: (2026)

P-split formulations: A class of intermediate formulations between big-M and convex hull for disjunctive constraints
por: Kronqvist, Jan, et al.
Publicado: (2022)

Model Guidance via Robust Feature Attribution
por: Ghitu, Mihnea, et al.
Publicado: (2025)

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
por: Li, Albus Yizhuo, et al.
Publicado: (2026)

When Deep Learning Meets Polyhedral Theory: A Survey
por: Huchette, Joey, et al.
Publicado: (2023)

Global Optimization of Gaussian Process Acquisition Functions Using a Piecewise-Linear Kernel Approximation
por: Xie, Yilin, et al.
Publicado: (2024)

Global optimization of graph acquisition functions for neural architecture search
por: Xie, Yilin, et al.
Publicado: (2025)

An Efficient Spatial Branch-and-Bound Algorithm for Global Optimization of Gaussian Process Posterior Mean Functions
por: Tang, Wei-Ting, et al.
Publicado: (2026)

EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization
por: Cheon, Mujin, et al.
Publicado: (2024)

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
por: Banerjee, Arko, et al.
Publicado: (2024)

Modeling High-Dimensional Dependent Data in the Presence of Many Explanatory Variables and Weak Signals
por: Gao, Zhaoxing, et al.
Publicado: (2024)

Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning
por: Zhao, Weiye, et al.
Publicado: (2024)

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
por: Feng, Chen, et al.
Publicado: (2024)

Local Updates in Distributed Optimization: Provable Acceleration and Topology Effects
por: Wang, Zuang, et al.
Publicado: (2026)

Leveraging Analytic Gradients in Provably Safe Reinforcement Learning
por: Walter, Tim, et al.
Publicado: (2025)

Provably Safe Reinforcement Learning for Stochastic Reach-Avoid Problems with Entropy Regularization
por: Mazumdar, Abhijit, et al.
Publicado: (2026)

Optimal Bias-Correction and Valid Inference in High-Dimensional Ridge Regression: A Closed-Form Solution
por: Gao, Zhaoxing, et al.
Publicado: (2024)

Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea
por: Krasowski, Hanna, et al.
Publicado: (2024)

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees
por: Marzari, Luca, et al.
Publicado: (2023)

Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis
por: Chung, Long Kiu, et al.
Publicado: (2025)

Provably Overwhelming Transformer Models with Designed Inputs
por: Stambler, Lev, et al.
Publicado: (2025)

Provably Safe Generative Sampling with Constricting Barrier Functions
por: Gadginmath, Darshan, et al.
Publicado: (2026)

A Provable Approach for End-to-End Safe Reinforcement Learning
por: Wachi, Akifumi, et al.
Publicado: (2025)

Provable Unrestricted Adversarial Training without Compromise with Generalizability
por: Zhang, Lilin, et al.
Publicado: (2023)

System-Aware Neural ODE Processes for Few-Shot Bayesian Optimization
por: Qing, Jixiang, et al.
Publicado: (2024)

Decision-Point Guided Safe Policy Improvement
por: Sharma, Abhishek, et al.
Publicado: (2024)

Enabling Asymmetric Knowledge Transfer in Multi-Task Learning with Self-Auxiliaries
por: Graffeuille, Olivier, et al.
Publicado: (2024)

CSULoRA: Closest Safe Update Low-Rank Adaptation
por: Breneur, Oleksandr Marchenko, et al.
Publicado: (2026)

Scalable High-Dimensional Multivariate Linear Regression for Feature-Distributed Data
por: Huang, Shuo-Chieh, et al.
Publicado: (2023)

Provable Model Provenance Set for Large Language Models
por: Qiu, Xiaoqi, et al.
Publicado: (2026)

Provable Statistical Rates for Consistency Diffusion Models
por: Dou, Zehao, et al.
Publicado: (2024)