Zobrazeno 1 - 10
of 183
pro vyhledávání: '"Li, Qianxiao"'
Autor:
Arisaka, Sohei, Li, Qianxiao
Scientific computing is an essential tool for scientific discovery and engineering design, and its computational cost is always a main concern in practice. To accelerate scientific computing, it is a promising approach to use machine learning (especi
Externí odkaz:
http://arxiv.org/abs/2405.02952
Autor:
Liu, Fusheng, Li, Qianxiao
A State Space Model (SSM) is a foundation model in time series analysis, which has recently been shown as an alternative to transformers in sequence modeling. In this paper, we theoretically study the generalization of SSMs and propose improvements t
Externí odkaz:
http://arxiv.org/abs/2405.02670
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 semantically indi
Externí odkaz:
http://arxiv.org/abs/2404.00828
Autor:
Zhu, Aiqing, Li, Qianxiao
Learning unknown stochastic differential equations (SDEs) from observed data is a significant and challenging task with applications in various fields. Current approaches often use neural networks to represent drift and diffusion functions, and const
Externí odkaz:
http://arxiv.org/abs/2402.14475
Autor:
Wang, Shida, Li, Qianxiao
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 similar to tha
Externí odkaz:
http://arxiv.org/abs/2311.14495
The performance of state-of-the-art machine learning models often deteriorates when testing on demographics that are under-represented in the training dataset. This problem has predominately been studied in a supervised learning setting where the dat
Externí odkaz:
http://arxiv.org/abs/2311.10223
In data-driven modelling of complex dynamic processes, it is often desirable to combine different classes of models to enhance performance. Examples include coupled models of different fidelities, or hybrid models based on physical knowledge and data
Externí odkaz:
http://arxiv.org/abs/2311.02967
We present an approach to construct approximate Koopman-type decompositions for dynamical systems depending on static or time-varying parameters. Our method simultaneously constructs an invariant subspace and a parametric family of projected Koopman
Externí odkaz:
http://arxiv.org/abs/2310.01124
We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory. Specifically, we consider two properties that arise from supervised learning, namely universal interpolation - the
Externí odkaz:
http://arxiv.org/abs/2309.06015
Autor:
Chen, Xiaoli, Soh, Beatrice W., Ooi, Zi-En, Vissol-Gaudin, Eleonore, Yu, Haijun, Novoselov, Kostya S., Hippalgaonkar, Kedar, Li, Qianxiao
One of the most exciting applications of artificial intelligence (AI) is automated scientific discovery based on previously amassed data, coupled with restrictions provided by known physical principles, including symmetries and conservation laws. Suc
Externí odkaz:
http://arxiv.org/abs/2308.04119