Author name cluster

Ying Cui

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

ICML Conference 2025 Conference Paper

An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions

Yuhan Ye
Ying Cui
Jingyi Wang

We propose an online adaptive sampling algorithm for solving stochastic nonsmooth difference-of-convex (DC) problems under time-varying distributions. At each iteration, the algorithm relies solely on data generated from the current distribution and employs distinct adaptive sampling rates for the convex and concave components of the DC function, a novel design guided by our theoretical analysis. We show that, under proper conditions on the convergence of distributions, the algorithm converges subsequentially to DC critical points almost surely. Furthermore, the sample size requirement of our proposed algorithm matches the results achieved in the smooth case or when a measurable subgradient selector is available, both under static distributions. A key element of this analysis is the derivation of a novel $O(\sqrt{p/n})$ pointwise convergence rate (modulo logarithmic factors) for the sample average approximation of subdifferential mappings, where $p$ is the dimension of the variable and $n$ is the sample size – a result of independent interest. Numerical experiments confirm that the proposed algorithm is both efficient and effective for addressing stochastic nonsmooth problems.

Details

AAAI Conference 2025 Conference Paper

DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation

Xiankang He
Guangkai Xu
Bo Zhang
Hao Chen
Ying Cui
Dongyan Guo

Monocular camera calibration is a key precondition for numerous 3D vision applications. Despite considerable advancements, existing methods often hinge on specific assumptions and struggle to generalize across varied real-world scenarios, and the performance is limited by insufficient training data. Recently, diffusion models trained on expansive datasets have been confirmed to maintain the capability to generate diverse, high-quality images. This success suggests a strong potential of the models to effectively understand varied visual information. In this work, we leverage the comprehensive visual knowledge embedded in pre-trained diffusion models to enable more robust and accurate monocular camera intrinsic estimation. Specifically, we reformulate the problem of estimating the four degrees of freedom (4-DoF) of camera intrinsic parameters as a dense incident map generation task. The map details the angle of incidence for each pixel in the RGB image, and its format aligns well with the paradigm of diffusion models. The camera intrinsic then can be derived from the incident map with a simple non-learning RANSAC algorithm during inference. Moreover, to further enhance the performance, we jointly estimate a depth map to provide extra geometric information for the incident map estimation. Extensive experiments on multiple testing datasets demonstrates that our model achieves state-of-the-art performance, gaining up to a 40% reduction in prediction errors. Besides, the experiments also show that the precise camera intrinsic and depth maps estimated by our pipeline can greatly benefit practical applications such as 3D reconstruction from a single in-the-wild image.

PDF Details DOI

JMLR Journal 2025 Journal Article

Fast Computation of Superquantile-Constrained Optimization Through Implicit Scenario Reduction

Jake Roth
Ying Cui

Superquantiles have recently gained significant interest as a risk-aware metric for addressing fairness and distribution shifts in statistical learning and decision making problems. This paper introduces a fast, scalable and robust second-order computational framework to solve large-scale optimization problems with superquantile-based constraints. Unlike empirical risk minimization, superquantile-based optimization requires ranking random functions evaluated across all scenarios to compute the tail conditional expectation. While this tail-based feature might seem computationally unfriendly, it provides an advantageous setting for a semismooth-Newton-based augmented Lagrangian method. The superquantile operator effectively reduces the dimensions of the Newton systems since the tail expectation involves considerably fewer scenarios. Notably, the extra cost of obtaining relevant second-order information and performing matrix inversions is often comparable to, and sometimes even less than, the effort required for gradient computation. Our developed solver is particularly effective when the number of scenarios substantially exceeds the number of decision variables. In synthetic problems with linear and convex diagonal quadratic objectives, numerical experiments demonstrate that our method outperforms existing approaches by a large margin: It achieves speeds more than 750 times faster for linear and quadratic objectives than the alternating direction method of multipliers as implemented by OSQP for computing low-accuracy solutions. Additionally, it is up to 25 times faster for linear objectives and 70 times faster for quadratic objectives than the commercial solver Gurobi, and 20 times faster for linear objectives and 30 times faster for quadratic objectives than the Portfolio Safeguard optimization suite for high-accuracy solution computations. For the quantile regression problem involving over 30 million scenarios, our method computes solution paths up to 20 times faster than Gurobi. The Julia implementation of the solver is available at https://github.com/jacob-roth/superquantile-opt. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2025. ( edit, beta )

PDF Details

NeurIPS Conference 2025 Conference Paper

Score-Based Diffusion Modeling for Nonparametric Empirical Bayes in Heteroscedastic Gaussian Mixtures

Gongyu Chen
Ying Cui

We propose a generalized score-based diffusion framework for learning multivariate Gaussian mixture models with homoscedastic or heteroscedastic noise. Our goal is to nonparametrically estimate the latent location distribution and denoise the observations. Departing from the conventional maximum likelihood approach, we reinterpret each observation as a temporal slice of a family of stochastic diffusion processes. This modeling choice enables a principled characterization of the additive noise structure and supports a multi-step denoising procedure grounded in reverse-time dynamics. We introduce a score-based objective that explicitly models the latent distribution and accommodates observation-specific noise covariances. Theoretically, we establish that the score estimation error with $n$ independent observations achieves a near-parametric error rate of $\frac{\mathrm{polylog}(n)}{n}$, improving upon existing results in the diffusion literature. Empirically, our method outperforms the nonparametric maximum likelihood estimator in both density estimation and denoising fidelity, especially in high-dimensional settings. These findings suggest a promising direction for integrating nonparametric empirical Bayes with diffusion-based generative modeling for latent structure recovery.

PDF Details

EAAI Journal 2025 Journal Article

Transforming physics-informed machine learning to convex optimization

Letian Yi
Siyuan Yang
Ying Cui
Zhilu Lai

Physics-Informed Machine Learning (PIML) offers a powerful paradigm of integrating data with physical laws to address important problems in engineering, such as parameter estimation, inferring hidden physics, equation discovery, and state prediction. However, PIML, such as Physics-Informed Neural Networks (PINNs), still lack the necessary accuracy, stability, and interpretability when applying in practical engineering due to many serious optimization challenges including the spectral bias, non-convex optimization, multi-objective optimization, and non-smooth optimization. In this study, we propose the Convex-PIML based on convex optimization and basis functions widely used in well-established numerical solvers to overcome all these limitations. The linear combination of B-splines is utilized to approximate the data, promoting the convexity of the loss function. By dividing variables into blocks and replacing the non-convex loss terms with convex approximations, the problem is further converted into a sequence of successively refined approximated convex optimization problems. This conversion known as Block Successive Convex Approximation (BSCA) allows the use of well-established convex optimization algorithms, obtaining solutions effectively and efficiently. Furthermore, an adaptive knot optimization method is introduced to mitigate the spectral bias issue of PIML, further improving the performance. The proposed fully adaptive framework by combining the adaptive knot optimization and BSCA is tested in scenarios with distinct types of physical prior. The results indicate that optimization problems are effectively solved in these scenarios, highlighting the potential of the framework for broad applications. Note that the Convex-PIML is also flexible since many other basis functions can also be incorporated to handle different systems.

Details DOI

JMLR Journal 2024 Journal Article

On Efficient and Scalable Computation of the Nonparametric Maximum Likelihood Estimator in Mixture Models

Yangjing Zhang
Ying Cui
Bodhisattva Sen
Kim-Chuan Toh

In this paper, we focus on the computation of the nonparametric maximum likelihood estimator (NPMLE) in multivariate mixture models. Our approach discretizes this infinite dimensional convex optimization problem by setting fixed support points for the NPMLE and optimizing over the mixing proportions. We propose an efficient and scalable semismooth Newton based augmented Lagrangian method (ALM). Our algorithm outperforms the state-of-the-art methods (Kim et al., 2020; Koenker and Gu, 2017), capable of handling $n \approx 10^6$ data points with $m \approx 10^4$ support points. A key advantage of our approach is its strategic utilization of the solution's sparsity, leading to structured sparsity in Hessian computations. As a result, our algorithm demonstrates better scaling in terms of $m$ when compared to the mixsqp method (Kim et al., 2020). The computed NPMLE can be directly applied to denoising the observations in the framework of empirical Bayes. We propose new denoising estimands in this context along with their consistent estimates. Extensive numerical experiments are conducted to illustrate the efficiency of our ALM. In particular, we employ our method to analyze two astronomy data sets: (i) Gaia-TGAS Catalog (Anderson et al., 2018) containing approximately $1.4 \times 10^6$ data points in two dimensions, and (ii) a data set from the APOGEE survey (Majewski et al., 2017) with approximately $2.7 \times 10^4$ data points. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2024. ( edit, beta )

PDF Details

AAAI Conference 2024 Conference Paper

PointAttN: You Only Need Attention for Point Cloud Completion

Jun Wang
Ying Cui
Dongyan Guo
Junxia Li
Qingshan Liu
Chunhua Shen

Point cloud completion referring to completing 3D shapes from partial 3D point clouds is a fundamental problem for 3D point cloud analysis tasks. Benefiting from the development of deep neural networks, researches on point cloud completion have made great progress in recent years. However, the explicit local region partition like kNNs involved in existing methods makes them sensitive to the density distribution of point clouds. Moreover, it serves limited receptive fields that prevent capturing features from long-range context information. To solve the problems, we leverage the cross-attention and self-attention mechanisms to design novel neural network for point cloud completion with implicit local region partition. Two basic units Geometric Details Perception (GDP) and Self-Feature Augment (SFA) are proposed to establish the structural relationships directly among points in a simple yet effective way via attention mechanism. Then based on GDP and SFA, we construct a new framework with popular encoder-decoder architecture for point cloud completion. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes and predict complete point clouds with detailed geometry. Experimental results demonstrate that our PointAttN outperforms state-of-the-art methods on multiple challenging benchmarks. Code is available at: https://github.com/ohhhyeahhh/PointAttN

PDF Details DOI

ECAI Conference 2024 Conference Paper

TDCL: Dense Semantic Contrastive Learning for Vision-Language Tracking

Zheng Wang
Xiankang He
Kaiyang Lan
Ying Cui
Dongyan Guo

Traditional single-object tracking tasks are undergoing a new wave of transformation, especially with the emergence of the lack of semantics, which has led to the rise of the vision-language tracking task. However, previous approaches that combine the visual tracker with natural language descriptions tend to rely on a global representation of the text description, considering less about the fine-grained connections between the text description and the visual appearance. This paper proposes to utilize a bi-directional cross-attention module to capture the connections between language and visual features, which are further projected as dense semantic representations for alignment. In order to keep the semantic consistency between the search region and the coupled natural language and align the fused feature, this paper proposes a novel dense semantic contrastive learning loss to bridge the semantic gap between text and visual modalities and align them in a dense form. The proposed framework achieves promising results in tracking datasets that contain natural language descriptions, such as TNL2K, and OTB99-LANG. Our approach provides a novel solution for representing and aligning cross-modal information for the single object tracking task and may inspire further research in this field.

Details

EAAI Journal 2024 Journal Article

Trustworthy multi-phase liver tumor segmentation via evidence-based uncertainty

Chuanfei Hu
Tianyi Xia
Ying Cui
Quchen Zou
Yuancheng Wang
Wenbo Xiao
Shenghong Ju
Xinde Li

Multi-phase liver contrast-enhanced computed tomography (CECT) images convey the complementary multi-phase information for liver tumor segmentation (LiTS), which are crucial to assist the diagnosis of liver cancer clinically. However, the performances of existing multi-phase liver tumor segmentation (MPLiTS)-based methods suffer from redundancy and weak interpretability, resulting in the implicit unreliability of clinical applications. In this paper, we propose a novel trustworthy multi-phase liver tumor segmentation (TMPLiTS), which is a unified framework jointly conducting segmentation and uncertainty estimation. The trustworthy results could assist the clinicians to make a reliable diagnosis. Specifically, Dempster–Shafer Evidence Theory (DST) is introduced to parameterize the segmentation and uncertainty with evidence following Dirichlet distribution. The reliability of segmentation results among multi-phase CECT images is quantified explicitly. Meanwhile, a multi-expert mixture scheme (MEMS) is proposed to fuse the multi-phase evidences, which can guarantee the effect of fusion procedure based on theoretical analysis. Experimental results demonstrate the superiority of TMPLiTS compared with the state-of-the-art methods. Meanwhile, the robustness of TMPLiTS is verified, where the reliable performance can be guaranteed against the perturbations.

Details DOI

YNICL Journal 2021 Journal Article

Multiscale neural modeling of resting-state fMRI reveals executive-limbic malfunction as a core mechanism in major depressive disorder

Guoshi Li
Yujie Liu
Yanting Zheng
Ye Wu
Danian Li
Xinyu Liang
Yaoping Chen
Ying Cui

Major depressive disorder (MDD) represents a grand challenge to human health and society, but the underlying pathophysiological mechanisms remain elusive. Previous neuroimaging studies have suggested that MDD is associated with abnormal interactions and dynamics in two major neural systems including the default mode - salience (DMN-SAL) network and the executive - limbic (EXE-LIM) network, but it is not clear which network plays a central role and which network plays a subordinate role in MDD pathophysiology. To address this question, we refined a newly developed Multiscale Neural Model Inversion (MNMI) framework and applied it to test whether MDD is more affected by impaired circuit interactions in the DMN-SAL network or the EXE-LIM network. The model estimates the directed connection strengths between different neural populations both within and between brain regions based on resting-state fMRI data collected from normal healthy subjects and patients with MDD. Results show that MDD is primarily characterized by abnormal circuit interactions in the EXE-LIM network rather than the DMN-SAL network. Specifically, we observe reduced frontoparietal effective connectivity that potentially contributes to hypoactivity in the dorsolateral prefrontal cortex (dlPFC), and decreased intrinsic inhibition combined with increased excitation from the superior parietal cortex (SPC) that potentially lead to amygdala hyperactivity, together resulting in activation imbalance in the PFC-amygdala circuit that pervades in MDD. Moreover, the model reveals reduced PFC-to-hippocampus excitation but decreased SPC-to-thalamus inhibition in MDD population that potentially lead to hypoactivity in the hippocampus and hyperactivity in the thalamus, consistent with previous experimental data. Overall, our findings provide strong support for the long-standing limbic-cortical dysregulation model in major depression but also offer novel insights into the multiscale pathophysiology of this debilitating disease.

Details DOI