YHYaohua Hu

Yaohua Hu

*This is an algorithmically generated author record based on publicly available information.

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


Yaohua Hu has a total of 79 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Recovery Bounds for Cardinality Regularized Optimization Problem

    by Carisa Kwok Wai Yu, Yaohua Hu, Minghua Li, Xiaoqi Yang

    Mixed sparse optimization has been extensively applied in the modeling of many important problems in various disciplines, in which the sparse structure appears as the inter-group and intra-group manners simultaneously. In this paper, we consider the $$\ell _0$$ ℓ 0 regularization problem for mixed sparse optimization and investigate its consistency theory. In particular, we first introduce the notions of sparse eigenvalue conditions, one of the weakest regularity conditions in the literature, and discuss their relations with the uniquely solvable property and restricted eigenvalue conditions. Then we establish the oracle property without any regularity condition and provide a recovery bound for the global solutions of the $$\ell _0$$ ℓ 0 regularized mixed sparse optimization problem under the assumption of sparse eigenvalue condition. Moreover, by virtue of the notion of epi-convergence, an asymptotic analysis is provided to advance the understanding of the convergence of the $$\ell _{2,p}$$ ℓ 2 , p regularization to the $$\ell _{2,0}$$ ℓ 2 , 0 regularization as $$p\rightarrow 0_+$$ p → 0 + , in terms of regularity condition, global solution set and recovery bound, respectively.

  • Avoiding Strict Saddle Points of Nonconvex Regularized Problems

    by Luwei Bai, Yaohua Hu, Hao Wang, Xiaoqi Yang

    This paper considers a class of nonconvex and nonsmooth sparse optimization problems, encompassing most existing nonconvex sparsity-inducing terms. We show that their second-order optimality conditions depend only on the nonzeros of the stationary points. We propose two damped iteratively reweighted algorithms, which are the iteratively reweighted [Formula: see text] algorithm (DIRL[Formula: see text]) and the iteratively reweighted [Formula: see text] (DIRL[Formula: see text]) algorithm, to solve these problems. For DIRL[Formula: see text], we show that the reweighted [Formula: see text] subproblem has the support identification property so that DIRL[Formula: see text] locally reverts to a gradient descent algorithm around a stationary point. For DIRL[Formula: see text], we show that the solution map of the reweighted [Formula: see text] subproblem is differentiable and Lipschitz continuous everywhere. Therefore, the solution maps of DIRL[Formula: see text] and DIRL[Formula: see text] and their inverses are Lipschitz continuous, and the strict saddle points are their unstable fixed points. By applying the stable manifold theorem, these algorithms starting from almost every initial point are shown to converge to local minima when the strict saddle point property is assumed.

  • ℓ1-2 Regularization for Sparse Optimization: Consistency and Global Convergence

    by Yaohua Hu, Hao Wang, Xiaoqi Yang

    The [ ] regularization method has a strong sparsity-promoting capability in approaching sparse solutions of linear inverse problems and gains successful applications in various mathematics disciplines and applied science fields. This paper aims to investigate the consistency theory and global convergent algorithms for the [ ] regularization problem. In the theoretical aspect, we introduce a notion of restricted eigenvalue condition relative to the [ ] penalty and employ it to establish an oracle property and a recovery bound for the global solution of the [ ] regularization problem. In the algorithmic aspect, we propose two types of iterative thresholding algorithms with the truncation technique and the continuation technique, respectively, to solve the [ ] regularization problem. Moreover, under the assumption of the well-known restricted isometry property, we establish the convergence of the proposed algorithms to the ground true sparse solution within a tolerance relevant to the noise level and the recovery bound. Preliminary numerical results verify our theoretical convergence results in showing that the proposed algorithms can approach the ground true sparse solution and significantly enhance the sparsity recovery capability, compared with the popular sparse optimization algorithms in the literature. Funding: This work was supported by the National Outstanding Youth Foundation of China [Grant 12222112]. Y. Hu’s work is supported by the National Key Research and Development Program of China [Grant 2025YFA1016903], Shenzhen Medical Research Fund [Grant B2502001], National Natural Science Foundation of China [Grants 12571327 and 12426311], Project of Educational Commission of Guangdong Province [Grant 2025ZDZX2059], and Shenzhen Science and Technology Program [Grants RCJC20221008092753082 and JCYJ20241202124209011]. H. Wang’s work is supported by the National Natural Science Foundation of China [Grant 12571326]. X. Yang’s work is supported by the Research Grants Council of Hong Kong [Grants PolyU 15205223 and N_PolyU507/22] and an internal grant [Grant 4-ZZPP].

  • Open Access

    Structure-enhanced graph meta learning for few-shot gene regulatory network inference

    by Weiming Yu, Zhuobin Chen, Yaohua Hu, Jing Qin, Le Ou-Yang

    Inferring gene regulatory networks (GRNs) is essential for understanding biological regulation. Although numerous deep learning approaches have been developed for GRN inference, most require large amounts of labeled data. We present Meta-TGLink, a structure-enhanced graph meta-learning model for few-shot GRN inference. By formulating GRN inference as a link prediction task, Meta-TGLink captures transferable regulatory patterns while reducing dependence on extensive labeled datasets. The model combines graph neural networks with Transformer architectures to integrate relational and positional information, thereby improving predictive performance under data-scarce conditions. Experiments on real datasets demonstrate its superiority over state-of-the-art baselines, particularly in cross-domain few-shot scenarios.


  • Open Access

    A Globalized Semismooth Newton Method for Prox-regular Optimization Problems

    by Yuqia Wu, Pengcheng Wu, Yaohua Hu, Shaohua Pan, Xiaoqi Yang

    We are concerned with a class of nonconvex and nonsmooth composite optimization problems, comprising a twice differentiable function and a prox-regular function. We establish a sufficient condition for the proximal mapping of a prox-regular function to be single-valued and locally Lipschitz continuous. By virtue of this property, we propose a hybrid of proximal gradient and semismooth Newton methods for solving these composite optimization problems, which is a globalized semismooth Newton method. The whole sequence is shown to converge to an $L$-stationary point under a Kurdyka-Łojasiewicz exponent assumption. Under an additional error bound condition and some other mild conditions, we prove that the sequence converges to a nonisolated $L$-stationary point at a superlinear convergence rate. Numerical comparison with several existing second order methods reveal that our approach performs comparably well in solving both the $\ell_q(0<q<1)$ quasi-norm regularized problems and the fused zero-norm regularization problems.

  • Open Access

    An Inexact Variable Metric Proximal Gradient-subgradient Algorithm for a Class of Fractional Optimization Problems

    by Lei Yang, Xiangrui Kong, Min Zhang, Yaohua Hu

    In this paper, we study a class of fractional optimization problems, in which the numerator of the objective is the sum of a convex function and a differentiable function with a Lipschitz continuous gradient, while the denominator is a nonsmooth convex function. This model has broad applicability and encompasses several important optimization problems in the literature. To address these problems, we propose an inexact variable metric proximal gradient-subgradient algorithm (iVPGSA), which, to our knowledge, is the first inexact proximal algorithm specifically designed for solving such type of fractional problems. By incorporating a variable metric proximal term and allowing for inexact solutions to the subproblem under a flexible error criterion, the proposed algorithm is highly adaptable to a broader range of problems while achieving favorable computational efficiency. Under mild assumptions, we establish that any accumulation point of the sequence generated by the iVPGSA is a critical point of the target problem. Moreover, we develop an improved Kurdyka-Łojasiewicz (KL)-based analysis framework to prove the global convergence of the entire sequence and characterize its convergence rate, \textit{without} requiring a strict sufficient descent property. Our results offer detailed insights into how the KL exponent and inexactness influence the convergence rate. The proposed analysis framework also has the potential to serve as a theoretical tool for studying the convergence rates of a wide range of inexact algorithms beyond the iVPGSA. Finally, some numerical experiments on the $\ell_1/\ell_2$ Lasso problem and the constrained $\ell_1/\ell_2$ sparse optimization problem are conducted to show the superior performance of the iVPGSA in comparison to existing algorithms.