Zobrazeno 1 - 10
of 1 156
pro vyhledávání: '"Fang, DI"'
Autor:
Li, Jiaxu, Lai, Songning, Li, Rui, Fang, Di, Fan, Kejia, Tang, Jianheng, Zhao, Yuhan, Zhao, Rongchang, Zhou, Dongzhan, Yue, Yutao, Zhuang, Huiping
While deep learning has made remarkable progress in recent years, models continue to struggle with catastrophic forgetting when processing continuously incoming data. This issue is particularly critical in continual learning, where the balance betwee
Externí odkaz:
http://arxiv.org/abs/2412.10834
Continual learning enables AI models to learn new data sequentially without retraining in real-world scenarios. Most existing methods assume the training data are balanced, aiming to reduce the catastrophic forgetting problem that models tend to forg
Externí odkaz:
http://arxiv.org/abs/2408.10349
In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come in an online fashion, and mod
Externí odkaz:
http://arxiv.org/abs/2405.17779
Autor:
Zhuang, Huiping, He, Run, Tong, Kai, Fang, Di, Sun, Han, Li, Haoran, Chen, Tianyi, Zeng, Ziqian
In this paper, we introduce analytic federated learning (AFL), a new training paradigm that brings analytical (i.e., closed-form) solutions to the federated learning (FL) community. Our AFL draws inspiration from analytic learning -- a gradient-free
Externí odkaz:
http://arxiv.org/abs/2405.16240
Hamiltonian simulation becomes more challenging as the underlying unitary becomes more oscillatory. In such cases, an algorithm with commutator scaling and a weak dependence, such as logarithmic, on the derivatives of the Hamiltonian is desired. We i
Externí odkaz:
http://arxiv.org/abs/2405.12925
Understanding the mixing of open quantum systems is a fundamental problem in physics and quantum information science. Existing approaches for estimating the mixing time often rely on the spectral gap estimation of the Lindbladian generator, which can
Externí odkaz:
http://arxiv.org/abs/2404.11503
Autor:
Zhuang, Huiping, Chen, Yizhu, Fang, Di, He, Run, Tong, Kai, Wei, Hongxin, Zeng, Ziqian, Chen, Cen
Class incremental learning (CIL) trains a network on sequential tasks with separated categories in each task but suffers from catastrophic forgetting, where models quickly lose previously learned knowledge when acquiring new tasks. The generalized CI
Externí odkaz:
http://arxiv.org/abs/2403.15706
Exemplar-free class-incremental learning (EFCIL) aims to mitigate catastrophic forgetting in class-incremental learning without available historical data. Compared with its counterpart (replay-based CIL) that stores historical samples, the EFCIL suff
Externí odkaz:
http://arxiv.org/abs/2403.13522
Learning a many-body Hamiltonian from its dynamics is a fundamental problem in physics. In this work, we propose the first algorithm to achieve the Heisenberg limit for learning an interacting $N$-qubit local Hamiltonian. After a total evolution time
Externí odkaz:
http://arxiv.org/abs/2210.03030
Autor:
Borns-Weil, Yonah, Fang, Di
Known as no fast-forwarding theorem in quantum computing, the simulation time for the Hamiltonian evolution needs to be $O(\|H\| t)$ in the worst case, which essentially states that one can not go across the multiple scales as the simulation time for
Externí odkaz:
http://arxiv.org/abs/2208.07957