English
Related papers

Related papers: Universal Value-Function Uncertainties

200 papers

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory…

This paper proposes a paradigm of uncertainty injection for training deep learning model to solve robust optimization problems. The majority of existing studies on deep learning focus on the model learning capability, while assuming the…

Machine Learning · Computer Science 2023-02-28 Wei Cui , Wei Yu

Multi-agent trajectory modeling has primarily focused on forecasting future states, often overlooking broader tasks like trajectory completion, which are crucial for real-world applications such as correcting tracking data. Existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Guillem Capellera , Antonio Rubio , Luis Ferraz , Antonio Agudo

Uncertainty quantification is a critical yet unsolved challenge for deep learning, especially for the time series imputation with irregularly sampled measurements. To tackle this problem, we propose a novel framework based on the principles…

Machine Learning · Computer Science 2023-06-05 Shweta Dahale , Sai Munikoti , Balasubramaniam Natarajan

Offline reinforcement learning (RL) has garnered significant interest due to its safe and easily scalable paradigm. However, training under this paradigm presents its own challenge: the extrapolation error stemming from out-of-distribution…

Machine Learning · Computer Science 2026-02-24 Thanh Nguyen , Tung Luu , Tri Ton , Sungwoong Kim , Chang D. Yoo

Approximation and learning of classifiers of large data sets by neural networks in terms of high-dimensional geometry and statistical learning theory are investigated. The influence of the VC dimension of sets of input-output functions of…

Machine Learning · Statistics 2025-11-18 Vera Kurkova , Marcello Sanguineti

While several methods for predicting uncertainty on deep networks have been recently proposed, they do not readily translate to large and complex datasets. In this paper we utilize a simplified form of the Mixture Density Networks (MDNs) to…

Machine Learning · Computer Science 2019-12-05 Nicholas Wilkins , Michael Johnson , Ifeoma Nwogu

The increasingly wide use of deep machine learning techniques in computational mechanics has significantly accelerated simulations of problems that were considered unapproachable just a few years ago. However, in critical applications such…

Machine Learning · Computer Science 2026-04-01 David Gonzalez , Alba Muixi , Beatriz Moya , Elias Cueto

Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Xiaotong Li , Yongxing Dai , Yixiao Ge , Jun Liu , Ying Shan , Ling-Yu Duan

Uncertainty quantification (UQ) is crucial in machine learning, yet most (axiomatic) studies of uncertainty measures focus on classification, leaving a gap in regression settings with limited formal justification and evaluations. In this…

Machine Learning · Computer Science 2025-05-19 Christopher Bülte , Yusuf Sale , Timo Löhr , Paul Hofman , Gitta Kutyniok , Eyke Hüllermeier

Model ensembles are effective tools for estimating prediction uncertainty in deep learning atomistic force fields. However, their widespread adoption is hindered by high computational costs and overconfident error estimates. In this work,…

Machine Learning · Computer Science 2024-05-24 Joshua A. Vita , Amit Samanta , Fei Zhou , Vincenzo Lordi

Deep neural policies have recently been installed in a diverse range of settings, from biotechnology to automated financial systems. However, the utilization of deep neural networks to approximate the value function leads to concerns on the…

Machine Learning · Computer Science 2024-06-26 Ezgi Korkmaz

Comprehensive visual, geometric, and semantic understanding of a 3D scene is crucial for successful execution of robotic tasks, especially in unstructured and complex environments. Additionally, to make robust decisions, it is necessary for…

Robotics · Computer Science 2026-03-13 Christian Maurer , Snehal Jauhri , Sophie Lueth , Georgia Chalvatzaki

For the retrieval of large-scale vegetation biophysical parameters, the inversion of radiative transfer models (RTMs) is the most commonly used approach. In recent years, Artificial Neural Network (ANN)-based methods have become the…

Machine Learning · Computer Science 2024-11-08 Dasheng Fan , Xihan Mu , Yongkang Lai , Donghui Xie , Guangjian Yan

Most uncertainty quantification (UQ) approaches provide a single scalar value as a measure of model reliability. However, different uncertainty measures could provide complementary information on the prediction confidence. Even measures…

Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is…

Computation and Language · Computer Science 2022-03-16 Adam Gleave , Geoffrey Irving

In many applications with real-world consequences, it is crucial to develop reliable uncertainty estimation for the predictions made by the AI decision systems. Targeting at the goal of estimating uncertainty, various deep neural network…

Machine Learning · Computer Science 2022-10-13 Huimin Zeng , Zhenrui Yue , Yang Zhang , Ziyi Kou , Lanyu Shang , Dong Wang

We present a simple and effective approach for posterior uncertainty quantification in deep operator networks (DeepONets); an emerging paradigm for supervised learning in function spaces. We adopt a frequentist approach based on randomized…

Machine Learning · Computer Science 2022-08-17 Yibo Yang , Georgios Kissas , Paris Perdikaris

Machine learning applications require fast and reliable per-sample uncertainty estimation. A common approach is to use predictive distributions from Bayesian or approximation methods and additively decompose uncertainty into aleatoric…

Machine Learning · Computer Science 2026-02-10 H. Martin Gillis , Isaac Xu , Thomas Trappenberg

While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods exploit the return distribution to provide stronger learning signals and to enable applications…

Machine Learning · Computer Science 2026-03-05 Perry Dong , Chongyi Zheng , Chelsea Finn , Dorsa Sadigh , Benjamin Eysenbach