English
Related papers

Related papers: Provably Safe Model Updates

200 papers

Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially expensive or unsafe online data collection. Significant…

Machine Learning · Computer Science 2022-03-17 Cong Lu , Philip J. Ball , Jack Parker-Holder , Michael A. Osborne , Stephen J. Roberts

The design of data-driven formulations for machine learning and decision-making with good out-of-sample performance is a key challenge. The observation that good in-sample performance does not guarantee good out-of-sample performance is…

Machine Learning · Statistics 2025-02-04 Amine Bennouna , Bart Van Parys , Ryan Lucas

Reproducibility is an increasing concern in Artificial Intelligence (AI), particularly in the area of Deep Learning (DL). Being able to reproduce DL models is crucial for AI-based systems, as it is closely tied to various tasks like…

Machine Learning · Computer Science 2022-02-08 Boyuan Chen , Mingzhi Wen , Yong Shi , Dayi Lin , Gopi Krishnan Rajbahadur , Zhen Ming , Jiang

Despite the effectiveness of deep neural networks in numerous natural language processing applications, recent findings have exposed the vulnerability of these language models when minor perturbations are introduced. While appearing…

Computation and Language · Computer Science 2024-04-02 Zhuotong Chen , Zihu Wang , Yifan Yang , Qianxiao Li , Zheng Zhang

High-dimensional predictive models, those with more measurements than observations, require regularization to be well defined, perform well empirically, and possess theoretical guarantees. The amount of regularization, often determined by…

Methodology · Statistics 2019-07-16 Darren Homrighausen , Daniel J. McDonald

Machine learning applications frequently come with multiple diverse objectives and constraints that can change over time. Accordingly, trained models can be tuned with sets of hyper-parameters that affect their predictive behavior (e.g.,…

Machine Learning · Computer Science 2022-10-17 Bracha Laufer-Goldshtein , Adam Fisch , Regina Barzilay , Tommi Jaakkola

This paper investigates the ability of the stochastic subspace identification technique to return a valid model from finite measurement data, its asymptotic properties as the data set becomes large, and asymptotic error bounds of the…

Systems and Control · Computer Science 2017-06-06 Quan Li , Jeffrey T. Scruggs

Ensuring safety through set invariance has proven to be a valuable method in various robotics and control applications. This paper introduces a comprehensive framework for the safe probabilistic invariance verification of both discrete- and…

Systems and Control · Electrical Eng. & Systems 2024-08-06 Taoran Wu , Yiqing Yu , Bican Xia , Ji Wang , Bai Xue

Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident…

Computer Vision and Pattern Recognition · Computer Science 2020-07-16 Yang Zou , Zhiding Yu , Xiaofeng Liu , B. V. K. Vijaya Kumar , Jinsong Wang

Learning models that are robust to distribution shifts is a key concern in the context of their real-life applicability. Invariant Risk Minimization (IRM) is a popular framework that aims to learn robust models from multiple environments.…

Machine Learning · Computer Science 2023-04-04 Moulik Choraria , Ibtihal Ferwana , Ankur Mani , Lav R. Varshney

Safety is a major concern in reinforcement learning (RL): we aim at developing RL systems that not only perform optimally, but are also safe to deploy by providing formal guarantees about their safety. To this end, we introduce…

Machine Learning · Computer Science 2025-10-22 Edwin Hamel-De le Court , Gaspard Ohlmann , Francesco Belardinelli

We consider the problem of stabilization of a linear system, under state and control constraints, and subject to bounded disturbances and unknown parameters in the state matrix. First, using a simple least square solution and available…

Systems and Control · Electrical Eng. & Systems 2020-07-22 Edouard Leurent , Denis Efimov , Odalric-Ambrym Maillard

As machine learning models are deployed ever more broadly, it becomes increasingly important that they are not only able to perform well on their training distribution, but also yield accurate predictions when confronted with distribution…

Machine Learning · Computer Science 2022-04-14 Paul Michel , Tatsunori Hashimoto , Graham Neubig

As AI systems migrate to safety-critical domains, verifying that their actions comply with well-defined rules remains a challenge. Formal methods provide provable guarantees but demand hand-crafted temporal-logic specifications, offering…

Robotics · Computer Science 2025-11-03 Yunhao Yang , Neel P. Bhatt , Pranay Samineni , Rohan Siva , Zhanyang Wang , Ufuk Topcu

Progress in Prognostics and Health Management (PHM) is hindered by the lack of standardized and reusable evaluation practices across tasks, datasets, and application domains. Reported results are often difficult to reproduce and compare, as…

Artificial Intelligence · Computer Science 2026-05-28 Lev Telyatnikov , Raffael Theiler , Leandro Von Krannichfeldt , Olga Fink

Adapting pre-trained foundation models for various downstream tasks has been prevalent in artificial intelligence. Due to the vast number of tasks and high costs, adjusting all parameters becomes unfeasible. To mitigate this, several…

Computer Vision and Pattern Recognition · Computer Science 2025-02-07 Chongjie Si , Xuehui Wang , Xue Yang , Zhengqin Xu , Qingyun Li , Jifeng Dai , Yu Qiao , Xiaokang Yang , Wei Shen

Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility…

Machine Learning · Computer Science 2026-05-22 Yonghui Yang , Wenjian Tao , Jilong Liu , Xingyu Zhu , Junfeng Fang , Weibiao Huang , Le Wu , Richang Hong , Tat-Sent Chua

One of the critical challenges in automated driving is ensuring safety of automated vehicles despite the unknown behavior of the other vehicles. Although motion prediction modules are able to generate a probability distribution associated…

Systems and Control · Electrical Eng. & Systems 2024-03-28 Luyao Zhang , George Pantazis , Shaohang Han , Sergio Grammatico

End-to-end learning has emerged as a major paradigm for developing autonomous systems. Unfortunately, with its performance and convenience comes an even greater challenge of safety assurance. A key factor of this challenge is the absence of…

Machine Learning · Computer Science 2024-06-21 Zhenjiang Mao , Carson Sobolewski , Ivan Ruchkin

LLMs are typically fine-tuned offline on domain-specific data, assuming a static domain. In practice, domain knowledge evolves continuously through new regulations, products, services, and interaction patterns. Retraining or fine-tuning…

Machine Learning · Computer Science 2026-02-10 Mohammad Abu-Shaira , Weishi Shi
‹ Prev 1 8 9 10 Next ›