Jiulong Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jiulong Liu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoqun Zhang
Shanghai Jiao Tong University
3 shared publications - Fengmiao Bian
Department of Mathematics The Hong Kong University of Science and Technology Hong Kong China
2 shared publications Hao Gao
Department of Radiation Oncology, University of Kansas Medical Center, Kansas City, KS, United States of America
1 shared publication- Hao Gao
Department of Radiation Oncology University of Kansas Medical Center Kansas City Kansas USA
1 shared publication Jian-Feng Cai
Department of Mathematics, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong Special Administrative Region of China, People’s Republic of China
1 shared publication- Jian-Feng Cai
Hong Kong University of Science and Technology
1 shared publication
Latest Publications
- 19 August 2025
- Published by IOP Publishing in Inverse Problems
- Vol. 41 (8) , 085009
Bayesian compressive sensing using generative models
Generative models, used to create new data resembling a given dataset, have achieved notable success in image reconstruction, especially in scenarios involving incomplete or noisy measurements. In Bayesian compressive sensing (CS) and more broadly in Bayesian inverse problems, the posterior inference of unknown quantities plays a crucial role, as it enables the incorporation of prior knowledge, handles ill-posedness, and provides a principled way to quantify uncertainty. However, it encounters challenges with high-dimensional inverse problems and complex prior distributions that are challenging to represent mathematically in traditional Bayesian frameworks. In this paper, we leverage generative models to establish variational inference for posterior mean (PM) estimation in Bayesian CS. The PM estimation is demonstrated to be straightforward and offers theoretical guarantees for Bayesian CS. Our proposed method, incorporating reparameterization techniques and variational approximations, not only significantly enhances reconstruction quality but also demonstrates robust performance in experiments on CS and magnetic resonance imaging reconstruction.
- 19 August 2025
- Published by IOP Publishing in Inverse Problems
- Vol. 41 (8) , 085009
Bayesian compressive sensing using generative models
Generative models, used to create new data resembling a given dataset, have achieved notable success in image reconstruction, especially in scenarios involving incomplete or noisy measurements. In Bayesian compressive sensing (CS) and more broadly in Bayesian inverse problems, the posterior inference of unknown quantities plays a crucial role, as it enables the incorporation of prior knowledge, handles ill-posedness, and provides a principled way to quantify uncertainty. However, it encounters challenges with high-dimensional inverse problems and complex prior distributions that are challenging to represent mathematically in traditional Bayesian frameworks. In this paper, we leverage generative models to establish variational inference for posterior mean (PM) estimation in Bayesian CS. The PM estimation is demonstrated to be straightforward and offers theoretical guarantees for Bayesian CS. Our proposed method, incorporating reparameterization techniques and variational approximations, not only significantly enhances reconstruction quality but also demonstrates robust performance in experiments on CS and magnetic resonance imaging reconstruction.
- Open Access
- 24 January 2025
- Published by IOP Publishing in Inverse Problems
- Vol. 41 (2) , 025007
Flash proton radiation therapy via a stochastic three-operator splitting method
The inverse radiation therapy planning problem is crucial in achieving tumoricidal doses while minimizing radiation-induced normal-tissue toxicity. Compared to conventional radiation therapy (with conventional dose rates), flash proton radiation therapy (with ultra-high dose rates) can provide additional normal tissue sparing. However, this groundbreaking advancement in radiation oncology introduces a challenging nonconvex and nonsmooth optimization problem. In this paper, we propose a stochastic three-operator splitting (STOS) algorithm to address the flash proton radiation therapy problem. We establish the convergence and convergence rates of the STOS algorithm under the nonconvex framework for both unbiased gradient estimators and variance-reduced gradient estimators. These stochastic gradient estimators include the most popular ones, such as SGD, SAGA, SARAH, and SAG, among others. Experimental results demonstrate that the flash proton radiation therapy plans obtained by the STOS algorithm can effectively kill tumors while better protecting normal tissues.
- 24 January 2025
- Published by IOP Publishing in Inverse Problems
- Vol. 41 (2) , 025007
Open AccessFlash proton radiation therapy via a stochastic three-operator splitting method
The inverse radiation therapy planning problem is crucial in achieving tumoricidal doses while minimizing radiation-induced normal-tissue toxicity. Compared to conventional radiation therapy (with conventional dose rates), flash proton radiation therapy (with ultra-high dose rates) can provide additional normal tissue sparing. However, this groundbreaking advancement in radiation oncology introduces a challenging nonconvex and nonsmooth optimization problem. In this paper, we propose a stochastic three-operator splitting (STOS) algorithm to address the flash proton radiation therapy problem. We establish the convergence and convergence rates of the STOS algorithm under the nonconvex framework for both unbiased gradient estimators and variance-reduced gradient estimators. These stochastic gradient estimators include the most popular ones, such as SGD, SAGA, SARAH, and SAG, among others. Experimental results demonstrate that the flash proton radiation therapy plans obtained by the STOS algorithm can effectively kill tumors while better protecting normal tissues.
- Open Access
Stochastic Three-Operator Splitting Algorithms for Nonconvex and Nonsmooth Optimization Arising from FLASH Radiotherapy
Radiation therapy (RT) aims to deliver tumoricidal doses with minimal radiation-induced normal-tissue toxicity. Compared to conventional RT (of conventional dose rate), FLASH-RT (of ultra-high dose rate) can provide additional normal tissue sparing, which however has created a new nonconvex and nonsmooth optimization problem that is highly challenging to solve. In this paper, we propose a stochastic three-operator splitting (STOS) algorithm to address the FLASH optimization problem. We establish the convergence and convergence rates of the STOS algorithm under the nonconvex framework for both unbiased gradient estimators and variance-reduced gradient estimators. These stochastic gradient estimators include the most popular ones, such as SGD, SAGA, SARAH, and SVRG, among others. The effectiveness of the STOS algorithm is validated using FLASH radiotherapy planning for patients.
Open AccessStochastic Three-Operator Splitting Algorithms for Nonconvex and Nonsmooth Optimization Arising from FLASH Radiotherapy
Radiation therapy (RT) aims to deliver tumoricidal doses with minimal radiation-induced normal-tissue toxicity. Compared to conventional RT (of conventional dose rate), FLASH-RT (of ultra-high dose rate) can provide additional normal tissue sparing, which however has created a new nonconvex and nonsmooth optimization problem that is highly challenging to solve. In this paper, we propose a stochastic three-operator splitting (STOS) algorithm to address the FLASH optimization problem. We establish the convergence and convergence rates of the STOS algorithm under the nonconvex framework for both unbiased gradient estimators and variance-reduced gradient estimators. These stochastic gradient estimators include the most popular ones, such as SGD, SAGA, SARAH, and SVRG, among others. The effectiveness of the STOS algorithm is validated using FLASH radiotherapy planning for patients.
- Open Access
Generative Principal Component Analysis
In this paper, we study the problem of principal component analysis with generative modeling assumptions, adopting a general model for the observed matrix that encompasses notable special cases, including spiked matrix recovery and phase retrieval. The key assumption is that the underlying signal lies near the range of an $L$-Lipschitz continuous generative model with bounded $k$-dimensional inputs. We propose a quadratic estimator, and show that it enjoys a statistical rate of order $\sqrt{\frac{k\log L}{m}}$, where $m$ is the number of samples. We also provide a near-matching algorithm-independent lower bound. Moreover, we provide a variant of the classic power method, which projects the calculated data onto the range of the generative model during each iteration. We show that under suitable conditions, this method converges exponentially fast to a point achieving the above-mentioned statistical rate. We perform experiments on various image datasets for spiked matrix and phase retrieval models, and illustrate performance gains of our method to the classic power method and the truncated power method devised for sparse principal component analysis.Open AccessGenerative Principal Component Analysis
In this paper, we study the problem of principal component analysis with generative modeling assumptions, adopting a general model for the observed matrix that encompasses notable special cases, including spiked matrix recovery and phase retrieval. The key assumption is that the underlying signal lies near the range of an $L$-Lipschitz continuous generative model with bounded $k$-dimensional inputs. We propose a quadratic estimator, and show that it enjoys a statistical rate of order $\sqrt{\frac{k\log L}{m}}$, where $m$ is the number of samples. We also provide a near-matching algorithm-independent lower bound. Moreover, we provide a variant of the classic power method, which projects the calculated data onto the range of the generative model during each iteration. We show that under suitable conditions, this method converges exponentially fast to a point achieving the above-mentioned statistical rate. We perform experiments on various image datasets for spiked matrix and phase retrieval models, and illustrate performance gains of our method to the classic power method and the truncated power method devised for sparse principal component analysis.