English
Related papers

Related papers: Regularity and Stability Properties of Selective S…

200 papers

Estimation of structure, such as in variable selection, graphical modelling or cluster analysis is notoriously difficult, especially for high-dimensional data. We introduce stability selection. It is based on subsampling in combination with…

Methodology · Statistics 2009-05-16 Nicolai Meinshausen , Peter Buehlmann

We study the effect of fading in the communication channels between sensor nodes on the performance of the incremental least mean square (ILMS) algorithm, and derive steady state performance metrics, including the mean-square deviation…

Information Theory · Computer Science 2015-09-10 Azam Khalili , Amir Rastegarnia

Markov state models (MSMs) have been broadly adopted for analyzing molecular dynamics trajectories, but the approximate nature of the models that results from coarse-graining into discrete states is a long-known limitation. We show…

Computational Physics · Physics 2021-05-31 John D. Russo , Jeremy Copperman , David Aristoff , Gideon Simpson , Daniel M. Zuckerman

State space models (SSMs) have gained attention by showing potential to outperform Transformers. However, previous studies have not sufficiently addressed the mechanisms underlying their high performance owing to a lack of theoretical…

Machine Learning · Computer Science 2025-10-02 JingChuan Guan , Tomoyuki Kubota , Yasuo Kuniyoshi , Kohei Nakajima

We introduce a robust framework for learning various generalized Hamiltonian dynamics from noisy, sparse phase-space data and in an unsupervised manner based on variational Bayesian inference. Although conservative, dissipative, and…

Machine Learning · Computer Science 2025-09-10 Luke McLennan , Yi Wang , Ryan Farell , Minh Nguyen , Chandrajit Bajaj

In this paper, we investigate the long-term memory learning capabilities of state-space models (SSMs) from the perspective of parameterization. We prove that state-space models without any reparameterization exhibit a memory limitation…

Machine Learning · Computer Science 2024-06-06 Shida Wang , Qianxiao Li

Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has…

Machine Learning · Statistics 2021-11-08 Kentaro Ohno , Atsutoshi Kumagai

This paper studies input-to-state stability (ISS) of general nonlinear time-delay systems subject to delay-dependent impulse effects. Sufficient conditions for ISS are constructed by using the method of Lyapunov functionals. It is shown…

Optimization and Control · Mathematics 2022-06-09 Xinzhi Liu , Kexue Zhang

The study proposes new results on the set input-to-state stability (ISS) subject to a small input time delay for compact, invariant sets that contains the origin. First, using the nonlinear small-gain theory, we prove a Razumikhin-type…

Systems and Control · Electrical Eng. & Systems 2022-11-24 Pallavi Sinha , Irinel-Constantin Morărescu , Sukumar Srikant

Due to the special gating schemes of Long Short-Term Memory (LSTM), LSTMs have shown greater potential to process complex sequential information than the traditional Recurrent Neural Network (RNN). The conventional LSTM, however, fails to…

Computer Vision and Pattern Recognition · Computer Science 2018-04-13 Naifan Zhuang , The Duc Kieu , Guo-Jun Qi , Kien A. Hua

A coupled oscillator system displays enhanced sensitivity of its saturated steady-state (SS) oscillation frequency to small parameter perturbations near an exceptional point degeneracy (EPD), a property that can be used to realize EPD-based…

Applied Physics · Physics 2026-02-03 Benjamin Bradshaw , Amin Hakimi , Filippo Capolino

We study feedback stabilization of continuous-time linear systems under finite data-rate constraints in the presence of unknown disturbances. A communication and control strategy based on sampled and quantized state measurements is…

Systems and Control · Electrical Eng. & Systems 2026-03-31 Mahmoud Zamani , Guosong Yang

The Transformer architecture has become the foundation of modern deep learning, yet its core self-attention mechanism suffers from quadratic computational complexity and lacks grounding in biological neural computation. We propose Selective…

Machine Learning · Computer Science 2026-02-17 Hasi Hays

Self-sustained, elevated neuronal activity persisting on time scales of ten seconds or longer is thought to be vital for aspects of working memory, including brain representations of real space. Continuous-attractor neural networks, one of…

Neurons and Cognition · Quantitative Biology 2020-08-19 Joseph L. Natale , H. George E. Hentschel , Ilya Nemenman

Impulsive systems are a very flexible class of systems that can be used to represent switched and sampled-data systems. We propose to extend here the previously obtained results on deterministic impulsive systems to the stochastic setting.…

Optimization and Control · Mathematics 2016-08-02 Corentin Briat

The recent rapid proliferation of renewable energy is fundamentally changing the dynamic operations of power systems, necessitating new approaches to assess stability for these highly nonlinear systems. In this paper, we prove that…

Systems and Control · Electrical Eng. & Systems 2026-05-07 Maryam Khodabakhshloo , Elizabeth L. Ratnam , Ian R. Petersen

With the increasing penetration of converter-interfaced distributed generation systems, it would be advantageous to specify local compliance criteria for these devices to ensure the small-signal stability of the interconnected system.…

Systems and Control · Electrical Eng. & Systems 2022-07-21 Kaustav Dey , Anil Kulkarni

Stability of ultra-low-voltage SRAM bitcells in retention mode is threatened by two types of uncertainty: process variability and intrinsic noise. While variability dominates the failure probability, noise-induced bit flips in weakened…

Hardware Architecture · Computer Science 2024-02-20 Léopold Van Brandt , Jean-Charles Delvenne , Denis Flandre

Quantum information can be encoded in the set of steady-states (SSS) of a driven-dissipative system. Non steady-states are separated by a large dissipative gap that adiabatically decouples them way while the dynamics inside the SSS is…

Quantum Physics · Physics 2015-06-03 Paolo Zanardi , Lorenzo Campos Venuti

In this paper we consider input-to-state stability (ISS) of impulsive control systems with and without time-delays. We prove that if the time-delay system possesses an exponential Lyapunov-Razumikhin function or an exponential…

Dynamical Systems · Mathematics 2012-02-23 Sergey Dashkovskiy , Michael Kosmykov , Andrii Mironchenko , Lars Naujok
‹ Prev 1 4 5 6 7 8 10 Next ›