English
Related papers

Related papers: Provably Safe Model Updates

200 papers

Updating machine learning models with new information usually improves their predictive performance, yet, in many applications, it is also desirable to avoid changing the model predictions too much. This property is called stability. In…

Machine Learning · Computer Science 2024-02-22 Morten Blørstad , Berent Å. S. Lunde , Nello Blaser

Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interpretability and safety more quantitative. Toward assessing…

Machine Learning · Computer Science 2022-11-04 Dennis Wei , Rahul Nair , Amit Dhurandhar , Kush R. Varshney , Elizabeth M. Daly , Moninder Singh

We present a novel framework for training large language models with continuously adjustable internal representations that span the full spectrum from localist (interpretable, rule-based) to distributed (generalizable, efficient) encodings.…

Machine Learning · Computer Science 2025-10-21 Joachim Diederich

Ensuring the safety of reinforcement learning (RL) algorithms is crucial to unlock their potential for many real-world tasks. However, vanilla RL and most safe RL approaches do not guarantee safety. In recent years, several methods have…

Machine Learning · Computer Science 2023-11-21 Hanna Krasowski , Jakob Thumm , Marlon Müller , Lukas Schäfer , Xiao Wang , Matthias Althoff

We consider optimal control problems with integer-valued controls and a total variation regularization penalty in the objective on domains of dimension two or higher. The penalty yields that the feasible set is sequentially closed in the…

Optimization and Control · Mathematics 2023-08-23 Paul Manns , Annika Schiemann

To improve the predictive capacity of system models in the input-output sense, this paper presents a framework for model updating via learning of modeling uncertainties in locally (and thus also in globally) Lipschitz nonlinear systems.…

Systems and Control · Electrical Eng. & Systems 2024-06-11 Farhad Ghanipoor , Carlos Murguia , Peyman Mohajerin Esfahani , Nathan van de Wouw

Creating a domain model, even for classical, domain-independent planning, is a notoriously hard knowledge-engineering task. A natural approach to solve this problem is to learn a domain model from observations. However, model learning…

Artificial Intelligence · Computer Science 2021-07-12 Brendan Juba , Hai S. Le , Roni Stern

Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe reinforcement learning, leads to constraint-violating behavior…

Optimization and Control · Mathematics 2020-07-09 Adam Stooke , Joshua Achiam , Pieter Abbeel

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…

Robotics · Computer Science 2018-05-31 Massimiliano Mancini , Samuel Rota Bulò , Barbara Caputo , Elisa Ricci

A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated…

Programming Languages · Computer Science 2025-02-27 Yao Feng , Jun Zhu , André Platzer , Jonathan Laurent

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…

Computation and Language · Computer Science 2024-10-01 Sachin Kumar

When neural networks are confronted with unfamiliar data that deviate from their training set, this signifies a domain shift. While these networks output predictions on their inputs, they typically fail to account for their level of…

Machine Learning · Computer Science 2025-09-09 Fin Amin , Jung-Eun Kim

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…

Computation and Language · Computer Science 2026-02-11 Yisu Wang , Ming Wang , Haoyuan Song , Wenjie Huang , Chaozheng Wang , Yi Xie , Xuming Ran

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Riccardo Volpi , Diane Larlus , Grégory Rogez

Safety assurance is uncompromisable for safety-critical environments with the presence of drastic model uncertainties (e.g., distributional shift), especially with humans in the loop. However, incorporating uncertainty in safe learning will…

Machine Learning · Computer Science 2023-10-05 Alaa Eddine Chriat , Chuangchuang Sun

Robots such as autonomous vehicles and assistive manipulators are increasingly operating in dynamic environments and close physical proximity to people. In such scenarios, the robot can leverage a human motion predictor to predict their…

Robotics · Computer Science 2023-06-07 Kensuke Nakamura , Somil Bansal

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality…

Machine Learning · Computer Science 2022-06-20 Zuxin Liu , Zhepeng Cen , Vladislav Isenbaev , Wei Liu , Zhiwei Steven Wu , Bo Li , Ding Zhao

A crucial aspect in reliable machine learning is to design a deployable system in generalizing new related but unobserved environments. Domain generalization aims to alleviate such a prediction gap between the observed and unseen…

Machine Learning · Computer Science 2021-06-01 Changjian Shui , Boyu Wang , Christian Gagné

Human mesh recovery from single images remains challenging due to inherent depth ambiguity and limited generalization across domains. While recent methods combine regression and optimization approaches, they struggle with poor…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Shaurjya Mandal , Nutan Sharma , John Galeotti

In this work we seek for an approach to integrate safety in the learning process that relies on a partly known state-space model of the system and regards the unknown dynamics as an additive bounded disturbance. We introduce a framework for…

Machine Learning · Computer Science 2018-11-12 Stanislav Fedorov , Antonio Candelieri