English
Related papers

Related papers: Controlling Transient Amplification Improves Long-…

200 papers

We present a novel framework that jointly trains a neural network controller and a neural Riemannian metric with rigorous closed-loop contraction guarantees using formal bound propagation. Directly bounding the symmetric Riemannian…

Systems and Control · Electrical Eng. & Systems 2026-03-31 Akash Harapanahalli , Samuel Coogan , Alexander Davydov

Cosimulation methods allow combination of simulation tools of physical systems running in parallel to act as a single simulation environment for a big system. As data is passed across subsystem boundaries instead of solving the system as…

Computational Engineering, Finance, and Science · Computer Science 2017-03-21 Dirk Scharff , Thilo Moshagen , Jaroslav Vondřejc

We present a Kalman smoothing framework based on modeling errors using the heavy tailed Student's t distribution, along with algorithms, convergence theory, open-source general implementation, and several important applications. The…

Optimization and Control · Mathematics 2013-03-25 Aleksandr Y. Aravkin , James V. Burke , Gianluigi Pillonetto

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…

Machine Learning · Computer Science 2024-03-06 Suzan Ece Ada , Emre Ugur , H. Levent Akin

We present a new approach to understanding the relationship between loss curvature and input-output model behaviour in deep learning. Specifically, we use existing empirical analyses of the spectrum of deep network loss Hessians to ground…

Machine Learning · Computer Science 2023-09-28 Lachlan Ewen MacDonald , Jack Valmadre , Simon Lucey

Datasets scraped from the internet have been critical to the successes of large-scale machine learning. Yet, this very success puts the utility of future internet-derived datasets at potential risk, as model outputs begin to replace human…

Machine Learning · Computer Science 2022-09-09 Rohan Taori , Tatsunori B. Hashimoto

Forecasting physical systems over long horizons from irregularly sampled observations demands models that are stable, computationally efficient, and free of fixed-timestep assumptions. We address this with a continuous-time Koopman…

Machine Learning · Computer Science 2026-05-11 Rares Grozavescu , Pengyu Zhang , Etienne Meunier , Mark Girolami

Diffusion Transformers require repeated denoiser evaluations during iterative sampling, making inference computationally expensive. Cache-based acceleration reduces this cost by reusing intermediate representations across denoising steps,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Mingyu Liang , Dingkun Xu , Jingwei Xu

Gradient control plays an important role in feed-forward networks applied to various computer vision tasks. Previous work has shown that Recurrent Highway Networks minimize the problem of vanishing or exploding gradients. They achieve this…

Machine Learning · Computer Science 2018-09-28 Chi Zhang , Thang Nguyen , Shagan Sah , Raymond Ptucha , Alexander Loui , Carl Salvaggio

In most practical applications such as recommendation systems, display advertising, and so forth, the collected data often contains missing values and those missing values are generally missing-not-at-random, which deteriorates the…

Machine Learning · Computer Science 2024-05-27 Mingming Ha , Xuewen Tao , Wenfang Lin , Qionxu Ma , Wujiang Xu , Linxun Chen

Trajectory augmentation serves as a means to mitigate distributional shift in imitation learning. However, imitating trajectories that inadequately represent the original expert data can result in undesirable behaviors, particularly in…

Machine Learning · Computer Science 2024-04-23 Hamidreza Mirkhani , Behzad Khamidehi , Kasra Rezaee

In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal…

Machine Learning · Computer Science 2024-02-21 Elena Agliari , Francesco Alemanno , Miriam Aquaro , Alberto Fachechi

Genes are connected in regulatory networks, often modelled by ordinary differential equations. Changes in expression of a gene propagate to other genes along paths in the network. At a stable state, the system's Jacobian matrix confers…

Molecular Networks · Quantitative Biology 2014-11-03 Arne B. Gjuvsland , Erik Plahte

Most uncertainty-aware robotic systems collapse prediction uncertainty into a single scalar score and use it to trigger uniform corrective responses. This aggregation obscures whether uncertainty arises from corrupted observations or from…

In offline imitation learning (IL), we generally assume only a handful of expert trajectories and a supplementary offline dataset from suboptimal behaviors to learn the expert policy. While it is now common to minimize the divergence…

Machine Learning · Computer Science 2024-01-19 Hee-Jun Ahn , Seong-Woong Shim , Byung-Jun Lee

Deep neural networks often produce overconfident predictions, undermining their reliability in safety-critical applications. This miscalibration is further exacerbated under distribution shift, where test data deviates from the training…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Yilin Zhang , Cai Xu , You Wu , Ziyu Guan , Wei Zhao

Irregular multivariate time series impose a trade-off for long-horizon forecasting: discrete methods can distort temporal structure via re-gridding, while continuous-time models often require sequential solvers prone to drift. To bridge…

Machine Learning · Computer Science 2026-05-20 Zinuo You , Jin Zheng , John Cartlidge

Covariate shift has been shown to sharply degrade both predictive accuracy and the calibration of uncertainty estimates for deep learning models. This is worrying, because covariate shift is prevalent in a wide range of real world…

Machine Learning · Computer Science 2021-01-18 Zachary Nado , Shreyas Padhy , D. Sculley , Alexander D'Amour , Balaji Lakshminarayanan , Jasper Snoek

This work presents a new sufficient condition for synthesizing nonlinear controllers that yield bounded closed-loop tracking error transients despite the presence of unmatched uncertainties that are concurrently being learned online. The…

Systems and Control · Electrical Eng. & Systems 2023-10-23 Samuel G. Gessow , Brett T. Lopez

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