English
Related papers

Related papers: Stability-Certified Reinforcement Learning via Spe…

200 papers

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

In this paper, we aim to find the conditions for input-state stability (ISS) and incremental input-state stability ($\delta$ISS) of Gated Graph Neural Networks (GGNNs). We show that this recurrent version of Graph Neural Networks (GNNs) can…

Robotics · Computer Science 2024-03-12 Antonio Marino , Claudio Pacchierotti , Paolo Robuffo Giordano

In the Bayesian reinforcement learning (RL) setting, a prior distribution over the unknown problem parameters -- the rewards and transitions -- is assumed, and a policy that optimizes the (posterior) expected return is sought. A common…

Machine Learning · Computer Science 2021-09-27 Aviv Tamar , Daniel Soudry , Ev Zisselman

We study the problem of learning to stabilize (LTS) a linear time-invariant (LTI) system. Policy gradient (PG) methods for control assume access to an initial stabilizing policy. However, designing such a policy for an unknown system is one…

Machine Learning · Computer Science 2025-05-07 Leonardo F. Toso , Lintao Ye , James Anderson

We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and…

Machine Learning · Computer Science 2019-11-14 Jan Laermann , Wojciech Samek , Nils Strodthoff

In recommender systems, users always choose the favorite items to rate, which leads to data missing not at random and poses a great challenge for unbiased evaluation and learning of prediction models. Currently, the doubly robust (DR)…

Machine Learning · Computer Science 2023-08-25 Haoxuan Li , Chunyuan Zheng , Peng Wu

We consider the failure of localized control in a nonlinear spatially extended system caused by extremely small amounts of noise. It is shown that this failure occurs as a result of a nonlinear instability. Nonlinear instabilities can occur…

Pattern Formation and Solitons · Physics 2009-11-07 Roman O. Grigoriev , Andreas Handel

Recent research shows that supervised learning can be an effective tool for designing near-optimal feedback controllers for high-dimensional nonlinear dynamic systems. But the behavior of neural network controllers is still not well…

Optimization and Control · Mathematics 2022-10-10 Tenavi Nakamura-Zimmerer , Qi Gong , Wei Kang

Maintaining numerical stability in machine learning models is crucial for their reliability and performance. One approach to maintain stability of a network layer is to integrate the condition number of the weight matrix as a regularizing…

Machine Learning · Computer Science 2024-10-02 Rossen Nenov , Daniel Haider , Peter Balazs

Regularization techniques such as L2 regularization (Weight Decay) and Dropout are fundamental to training deep neural networks, yet their underlying physical mechanisms regarding feature frequency selection remain poorly understood. In…

Machine Learning · Computer Science 2025-12-30 Jiahao Lu

This paper presents a method that learns a regionally stable recurrent neural network model from a set of input-output data generated by an unknown dynamical system. Relying on generalized sector conditions on the deadzone activation…

Systems and Control · Electrical Eng. & Systems 2026-05-19 Daniel Frank , Fahim Shakib , Steffen Staab

Ensuring safety and meeting temporal specifications are critical challenges for long-term robotic tasks. Signal temporal logic (STL) has been widely used to systematically and rigorously specify these requirements. However, traditional…

Machine Learning · Computer Science 2023-09-12 Yue Meng , Chuchu Fan

Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as…

Machine Learning · Statistics 2018-07-03 Henry Gouk , Bernhard Pfahringer , Eibe Frank , Michael Cree

We propose a policy search approach to learn controllers from specifications given as Signal Temporal Logic (STL) formulae. The system model, which is unknown but assumed to be an affine control system, is learned together with the control…

Systems and Control · Electrical Eng. & Systems 2023-03-07 Wenliang Liu , Mirai Nishioka , Calin Belta

Likelihood ratios are used for a variety of applications in particle physics data analysis, including parameter estimation, unfolding, and anomaly detection. When the data are high-dimensional, neural networks provide an effective tools for…

High Energy Physics - Phenomenology · Physics 2025-03-27 Fernando Torales Acosta , Tanvi Wamorkar , Vinicius Mikuni , Benjamin Nachman

In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark contrast with this trend, state-of-the-art reinforcement…

Machine Learning · Computer Science 2022-01-05 Johan Bjorck , Carla P. Gomes , Kilian Q. Weinberger

Classical conditions for ensuring the robust stability of a linear system in feedback with a sector-bounded nonlinearity include small gain, circle, passivity, and conicity theorems. In this work, we present a similar stability condition,…

Optimization and Control · Mathematics 2019-09-18 Saman Cyrus , Laurent Lessard

This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy…

Machine Learning · Computer Science 2025-12-04 Chujie Zheng , Kai Dang , Bowen Yu , Mingze Li , Huiqiang Jiang , Junrong Lin , Yuqiong Liu , Hao Lin , Chencan Wu , Feng Hu , An Yang , Jingren Zhou , Junyang Lin

Reinforcement learning (RL) has shown great potential in training agile and adaptable controllers for legged robots, enabling them to learn complex locomotion behaviors directly from experience. However, policies trained in simulation often…

Robotics · Computer Science 2026-03-23 Jaeyong Shin , Woohyun Cha , Donghyeon Kim , Junhyeok Cha , Jaeheung Park

I investigate a stronger form of regularization by deactivating neurons for extended periods, a departure from the temporary changes of methods like Dropout. However, this long-term dynamism introduces a critical challenge: severe training…

Machine Learning · Computer Science 2025-09-26 Zichuan Yang
‹ Prev 1 3 4 5 6 7 10 Next ›