Author name cluster

Lin Zhao

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.

23 papers

2 author rows

YNICL Journal 2026 Journal Article

Distinct neurologic state in patients with traumatic brain injury and hemorrhagic stroke during the stage of acute disorders of consciousness and the correlation with the neurological prognosis: A multi-modal PET/rs-fMRI study

Danjing Yu
Kemeng Gao
Xiefeng Wang
Lin Zhao
Yi Sun
Zhiyan Shen
Yu Wang
Ying Wang

PURPOSE: The exact mechanisms underlying the distinct neurological outcomes between Traumatic Brain Injury (TBI) and Hemorrhagic Stroke (HS) remain unclear. Our objective is to assess distinct features of neurologic state between comatose patients with TBI and HS during the stage of acute disorder of consciousness (aDoC) and to identify the correlation of neurologic features with prognosis. METHODS: Data were analyzed from TBI and HS patients examined by positron emission tomography (PET) and resting-state functional magnetic resonance imaging (rs-fMRI) simultaneously. Primary clinical outcomes consisted of the state of consciousness and neurological prognosis. The regional neural activity was assessed by the amplitude of fractional low-frequency fluctuation (fALFF) and regional homogeneity (ReHo) on rs-fMRI scans. The standardized uptake value (SUV) on PET scans quantified neural metabolism. Functional connectivity (FC) and graph theoretic approach (GTA) were employed to compare the FC patterns between TBI and HS. Correlations of PET/rs-fMRI indicators with the prognosis of HS and TBI were identified. RESULTS: Muti-modal PET/rs-fMRI analysis showed more active local neurological state in TBI patients than HS patients, specifically in the right precentral gyrus (PreCG.R), right postcentral gyrus (PoCG.R), right superior temporal gyrus (STG.R) and right middle temporal gyrus (MTG.R). TBI patients demonstrated significantly higher clustering coefficient and nodal efficiency of the sensorimotor network (SMN) along with lower connectivity and network efficiency in the default network (DMN) compared to HS patients. PET/rs-fMRI indicators significantly correlated with the neurological prognosis of TBI and HS. CONCLUSIONS: This study elucidated the underlying mechanisms contributing to the distinct neurologic prognosis between comatose TBI and HS patients, and may contribute to the development of early targeted intervention strategies for specific diseases.

Details DOI

TMLR Journal 2026 Journal Article

Prompt-based Adaptation in Large-scale Vision Models: A Survey

Xi Xiao
Yunbei Zhang
Lin Zhao
Yiyang Liu
Xiaoying Liao
Zheda Mai
Xingjian Li
Xiao Wang

In computer vision, Visual Prompting (VP) and Visual Prompt Tuning (VPT) have recently emerged as lightweight and effective alternatives to full fine-tuning for adapting large-scale vision models within the ``pretrain-then-finetune'' paradigm. However, despite rapid progress, their conceptual boundaries remain blurred, as VP and VPT are frequently used interchangeably in current research, reflecting a lack of systematic distinction between these techniques and their respective applications. In this survey, we revisit the designs of VP and VPT from first principles, and conceptualize them within a unified framework termed Prompt-based Adaptation (PA). Within this framework, we distinguish methods based on their injection granularity: VP operates at the pixel level, while VPT injects prompts at the token level. We further categorize these methods by their generation mechanism into fixed, learnable, and generated prompts. Beyond the core methodologies, we examine PA’s integrations across diverse domains, including medical imaging, 3D point clouds, and vision-language tasks, as well as its role in test-time adaptation and trustworthy AI. We also summarize current benchmarks and identify key challenges and future directions. To the best of our knowledge, we are the first comprehensive survey dedicated to PA's methodologies and applications in light of their distinct characteristics. Our survey aims to provide a clear roadmap for researchers and practitioners in all area to understand and explore the evolving landscape of PA-related research.

PDF Details

IROS Conference 2025 Conference Paper

DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion Models

Ziyu Wan
Lin Zhao

This paper proposes the DnD Filter, a differentiable filter that utilizes diffusion models for state estimation of dynamic systems. Unlike conventional differentiable filters, which often impose restrictive assumptions on process noise (e. g. , Gaussianity), DnD Filter enables a nonlinear state update without such constraints by conditioning a diffusion model on both the predicted state and observational data, capitalizing on its ability to approximate complex distributions. We validate its effectiveness on both a simulated task and a real-world visual odometry task, where DnD Filter consistently outperforms existing baselines. Specifically, it achieves a 25% improvement in estimation accuracy on the visual odometry task compared to state-of-the-art differentiable filters, and even surpasses differentiable smoothers that utilize future measurements. To the best of our knowledge, DnD Filter represents the first successful attempt to leverage diffusion models for state estimation, offering a flexible and powerful framework for nonlinear estimation under noisy measurements. The code is available at https://github.com/ZiyuNUS/DnDFilter.

Details

AAAI Conference 2025 Conference Paper

FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection

Ke Li
Di Wang
Zhangyuan Hu
Shaofeng Li
Weiping Ni
Lin Zhao
Quan Wang

Infrared-visible object detection (IVOD) seeks to harness the complementary information in infrared and visible images, thereby enhancing the performance of detectors in complex environments. However, existing methods often neglect the frequency characteristics of complementary information, such as the abundant high-frequency details in visible images and the valuable low-frequency thermal information in infrared images, thus constraining detection performance. To solve this problem, we introduce a novel Frequency-Driven Feature Decomposition Network for IVOD, called FD2-Net, which effectively captures the unique frequency representations of complementary information across multimodal visual spaces. Speciﬁcally, we propose a feature decomposition encoder, wherein the high-frequency unit (HFU) utilizes discrete cosine transform to capture representative high-frequency features, while the low-frequency unit (LFU) employs dynamic receptive ﬁelds to model the multi-scale context of diverse objects. Next, we adopt a parameter-free complementary strengths strategy to enhance multimodal features through seamless inter-frequency recoupling. Furthermore, we innovatively design a multimodal reconstruction mechanism that recovers image details lost during feature extraction, further leveraging the complementary information from infrared and visible images to enhance overall representational capacity. Extensive experiments demonstrate that FD2-Net outperforms state-of-the-art (SoTA) models across various IVOD benchmarks, i.e. LLVIP (96.2% mAP), FLIR (82.9% mAP), and M3FD (83.5% mAP).

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion

Xiaojian Ding
Lin Zhao
Xian Li
Xiaoying Zhu

Incomplete multi-view data, where certain views are entirely missing for some samples, poses significant challenges for traditional multi-view clustering methods. Existing deep incomplete multi-view clustering approaches often rely on static fusion strategies or two-stage pipelines, leading to suboptimal fusion results and error propagation issues. To address these limitations, this paper proposes a novel incomplete multi-view clustering framework based on Hierarchical Semantic Alignment and Cooperative Completion (HSACC). HSACC achieves robust cross-view fusion through a dual-level semantic space design. In the low-level semantic space, consistency alignment is ensured by maximizing mutual information across views. In the high-level semantic space, adaptive view weights are dynamically assigned based on the distributional affinity between individual views and an initial fused representation, followed by weighted fusion to generate a unified global representation. Additionally, HSACC implicitly recovers missing views by projecting aligned latent representations into high-dimensional semantic spaces and jointly optimizes reconstruction and clustering objectives, enabling cooperative learning of completion and clustering. Experimental results demonstrate that HSACC significantly outperforms state-of-the-art methods on five benchmark datasets. Ablation studies validate the effectiveness of the hierarchical alignment and dynamic weighting mechanisms, while parameter analysis confirms the model's robustness to hyperparameter variations. The code is available at \url{https: //github. com/XiaojianDing/2025-NeurIPS-HSACC}.

PDF Details

AAAI Conference 2025 Conference Paper

Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy

Shaoyan Pan
Yikang Liu
Lin Zhao
Eric Z. Chen
Xiao Chen
Terrence Chen
Shanhui Sun

The accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. Although deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, ensuring a diverse range of visibility in the synthesized image. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.

PDF Details DOI

ICML Conference 2025 Conference Paper

On the Convergence of Continuous Single-timescale Actor-critic

Xuyang Chen
Lin Zhao

Actor-critic algorithms have been instrumental in boosting the performance of numerous challenging applications involving continuous control, such as highly robust and agile robot motion control. However, their theoretical understanding remains largely underdeveloped. Existing analyses mostly focus on finite state-action spaces and on simplified variants of actor-critic, such as double-loop updates with i. i. d. sampling, which are often impractical for real-world applications. We consider the canonical and widely adopted single-timescale updates with Markovian sampling in continuous state-action space. Specifically, we establish finite-time convergence by introducing a novel Lyapunov analysis framework, which provides a unified convergence characterization of both the actor and the critic. Our approach is less conservative than previous methods and offers new insights into the coupled dynamics of actor-critic updates.

Details

AAAI Conference 2025 Conference Paper

Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation

Xiaoqi An
Lin Zhao
Chen Gong
Jun Li
Jian Yang

With the rapid development of autonomous driving, LiDAR-based 3D Human Pose Estimation (3D HPE) is becoming a research focus. However, due to the noise and sparsity of LiDAR-captured point clouds, robust human pose estimation remains challenging. Most of the existing methods use temporal information, multi-modal fusion, or SMPL optimization to correct biased results. In this work, we try to obtain sufficient information for 3D HPE only by modeling the intrinsic properties of low-quality point clouds. Hence, a simple yet powerful method is proposed, which provides insights both on modeling and augmentation of point clouds. Specifically, we first propose a concise and effective density-aware pose transformer (DAPT) to get stable keypoint representations. By using a set of joint anchors and a carefully designed exchange module, valid information is extracted from point clouds with different densities. Then 1D heatmaps are utilized to represent the precise locations of the keypoints. Secondly, a comprehensive LiDAR human synthesis and augmentation method is proposed to pre-train the model, enabling it to acquire a better human body prior. We increase the diversity of point clouds by randomly sampling human positions and orientations and by simulating occlusions through the addition of laser-level masks. Extensive experiments have been conducted on multiple datasets, including IMU-annotated LidarHuman26M, SLOPER4D, and manually annotated Waymo Open Dataset v2.0 (Waymo), HumanM3. Our method demonstrates SOTA performance in all scenarios. In particular, compared with LPFormer on Waymo, we reduce the average MPJPE by 10.0mm. Compared with PRN on SLOPER4D, we notably reduce the average MPJPE by 20.7mm.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection

Zhipeng Zou
Sheng Wan
Guangyu Li
Bo Han
Tongliang Liu
Lin Zhao
Chen Gong

Out-of-distribution (OOD) detection aims to identify the test examples that do not belong to the distribution of training data. The distance-based methods, which identify OOD examples based on their distances from the centroids of in-distribution (ID) examples, have demonstrated promising OOD detection performance. However, the objectives utilized in prior approaches are typically designed for classification and thus might not yield sufficient discriminative power to distinguish between ID and OOD examples. Therefore, this paper proposes a prototype-based contrastive learning framework for OOD detection, which is termed provable Discriminative Hyperspherical Embedding (DHE). The proposed framework provides a theoretical analysis of inter-class dispersion, which is proved to be fundamental in reducing the false positive rate (FPR) on OOD examples. Based on this, we devise an angular spread loss to achieve the maximal dispersion of the prototypes of different classes prior to training. Subsequently, a prototype-enhanced contrastive loss is introduced to align embeddings of ID examples closely with their corresponding prototypes. In our proposed DHE, the maximal prototype dispersion is theoretically proved, thereby avoiding the pitfalls of local optima commonly encountered by most existing methods. Experimental results demonstrate the effectiveness of our proposed DHE, which showcases a remarkable reduction in FPR95 (i.e., 5.37% on CIFAR-100) and more than doubling the computational efficiency when compared with the state-of-the-art methods.

PDF Details DOI

ICML Conference 2025 Conference Paper

Taming Diffusion for Dataset Distillation with High Representativeness

Lin Zhao
Yushu Wu
Xinru Jiang
Jianyang Gu
Yanzhi Wang 0001
Xiaolin Xu 0001
Pu Zhao 0001
Xue Lin 0001

Recent deep learning models demand larger datasets, driving the need for dataset distillation to create compact, cost-efficient datasets while maintaining performance. Due to the powerful image generation capability of diffusion, it has been introduced to this field for generating distilled images. In this paper, we systematically investigate issues present in current diffusion-based dataset distillation methods, including inaccurate distribution matching, distribution deviation with random noise, and separate sampling. Building on this, we propose D$^3$HR, a novel diffusion-based framework to generate distilled datasets with high representativeness. Specifically, we adopt DDIM inversion to map the latents of the full dataset from a low-normality latent domain to a high-normality Gaussian domain, preserving information and ensuring structural consistency to generate representative latents for the distilled dataset. Furthermore, we propose an efficient sampling scheme to better align the representative latents with the high-normality Gaussian distribution. Our comprehensive experiments demonstrate that D$^3$HR can achieve higher accuracy across different model architectures compared with state-of-the-art baselines in dataset distillation. Source code: https: //github. com/lin-zhao-resoLve/D3HR.

Details

JBHI Journal 2024 Journal Article

Brain Structural Connectivity Guided Vision Transformers for Identification of Functional Connectivity Characteristics in Preterm Neonates

Wei Mao
Yuzhong Chen
Zhibin He
Zifan Wang
Zhenxiang Xiao
Yusong Sun
Liang He
Jingchao Zhou

Preterm birth is the leading cause of death in children under five years old, and is associated with a wide sequence of complications in both short and long term. In view of rapid neurodevelopment during the neonatal period, preterm neonates may exhibit considerable functional alterations compared to term ones. However, the identified functional alterations in previous studies merely achieve moderate classification performance, while more accurate functional characteristics with satisfying discrimination ability for better diagnosis and therapeutic treatment is underexplored. To address this problem, we propose a novel brain structural connectivity (SC) guided Vision Transformer (SCG-ViT) to identify functional connectivity (FC) differences among three neonatal groups: preterm, preterm with early postnatal experience, and term. Particularly, inspired by the neuroscience-derived information, a novel patch token of SC/FC matrix is defined, and the SC matrix is then adopted as an effective mask into the ViT model to screen out input FC patch embeddings with weaker SC, and to focus on stronger ones for better classification and identification of FC differences among the three groups. The experimental results on multi-modal MRI data of 437 neonatal brains from publicly released Developing Human Connectome Project (dHCP) demonstrate that SCG-ViT achieves superior classification ability compared to baseline models, and successfully identifies holistically different FC patterns among the three groups. Moreover, these different FCs are significantly correlated with the differential gene expressions of the three groups. In summary, SCG-ViT provides a powerfully brain-guided pipeline of adopting large-scale and data-intensive deep learning models for medical imaging-based diagnosis.

Details DOI

AIIM Journal 2024 Journal Article

CHNet: A multi-task global–local Collaborative Hybrid Network for KRAS mutation status prediction in colorectal cancer

Meiling Cai
Lin Zhao
Yan Qiang
Long Wang
Juanjuan Zhao

Accurate prediction of Kirsten rat sarcoma (KRAS) mutation status is crucial for personalized treatment of advanced colorectal cancer patients. However, despite the excellent performance of deep learning models in certain aspects, they often overlook the synergistic promotion among multiple tasks and the consideration of both global and local information, which can significantly reduce prediction accuracy. To address these issues, this paper proposes an innovative method called the Multi-task Global–Local Collaborative Hybrid Network (CHNet) aimed at more accurately predicting patients’ KRAS mutation status. CHNet consists of two branches that can extract global and local features from segmentation and classification tasks, respectively, and exchange complementary information to collaborate in executing these tasks. Within the two branches, we have designed a Channel-wise Hybrid Transformer (CHT) and a Spatial-wise Hybrid Transformer (SHT). These transformers integrate the advantages of both Transformer and CNN, employing cascaded hybrid attention and convolution to capture global and local information from the two tasks. Additionally, we have created an Adaptive Collaborative Attention (ACA) module to facilitate the collaborative fusion of segmentation and classification features through guidance. Furthermore, we introduce a novel Class Activation Map (CAM) loss to encourage CHNet to learn complementary information between the two tasks. We evaluate CHNet on the T2-weighted MRI dataset, and achieve an accuracy of 88. 93% in KRAS mutation status prediction, which outperforms the performance of representative KRAS mutation status prediction methods. The results suggest that our CHNet can more accurately predict KRAS mutation status in patients via a multi-task collaborative facilitation and considering global–local information way, which can assist doctors in formulating more personalized treatment strategies for patients.

Details DOI

IJCAI Conference 2024 Conference Paper

Global Optimality of Single-Timescale Actor-Critic under Continuous State-Action Space: A Study on Linear Quadratic Regulator

Xuyang Chen
Jingliang Duan
Lin Zhao

Actor-critic methods have achieved state-of-the-art performance in various challenging tasks. However, theoretical understandings of their performance remain elusive and challenging. Existing studies mostly focus on practically uncommon variants such as double-loop or two-timescale stepsize actor-critic algorithms for simplicity. These results certify local convergence on finite state- or action- space only. We push the boundary to investigate the classic single-sample single-timescale actor-critic on continuous (infinite) state-action space, where we employ the canonical linear quadratic regulator (LQR) problem as a case study. We show that the popular single-timescale actor-critic can attain an epsilon-optimal solution with an order of epsilon to -2 sample complexity for solving LQR on the demanding continuous state-action space. Our work provides new insights into the performance of single-timescale actor-critic, which further bridges the gap between theory and practice.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction

Chen-Long Duan
Yong Li
Xiu-Shen Wei
Lin Zhao

Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model parameters, often fall short when confronted with long-tailed distributions, especially in detection tasks. This is largely due to extreme data imbalance and the issue of simplicity bias. In this paper, we introduce a novel pre-training framework for object detection, called Dynamic Rebalancing Contrastive Learning with Dual Reconstruction (2DRCL). Our method builds on a Holistic-Local Contrastive Learning mechanism, which aligns pre-training with object detection by capturing both global contextual semantics and detailed local patterns. To tackle the imbalance inherent in long-tailed data, we design a dynamic rebalancing strategy that adjusts the sampling of underrepresented instances throughout the pre-training process, ensuring better representation of tail classes. Moreover, Dual Reconstruction addresses simplicity bias by enforcing a reconstruction task aligned with the self-consistency principle, specifically benefiting underrepresented tail classes. Experiments on COCO and LVIS v1. 0 datasets demonstrate the effectiveness of our method, particularly in improving the mAP/AP scores for tail classes.

PDF Details DOI

AAAI Conference 2024 Conference Paper

SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation

Xiaoqi An
Lin Zhao
Chen Gong
Nannan Wang
Di Wang
Jian Yang

High-resolution representation is essential for achieving good performance in human pose estimation models. To obtain such features, existing works utilize high-resolution input images or fine-grained image tokens. However, this dense high-resolution representation brings a significant computational burden. In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?" Based on dynamic transformer models, we propose a framework that only uses Sparse High-resolution Representations for human Pose estimation (SHaRPose). In detail, SHaRPose consists of two stages. At the coarse stage, the relations between image regions and keypoints are dynamically mined while a coarse estimation is generated. Then, a quality predictor is applied to decide whether the coarse estimation results should be refined. At the fine stage, SHaRPose builds sparse high-resolution representations only on the regions related to the keypoints and provides refined high-precision human pose estimations. Extensive experiments demonstrate the outstanding performance of the proposed method. Specifically, compared to the state-of-the-art method ViTPose, our model SHaRPose-Base achieves 77.4 AP (+0.5 AP) on the COCO validation set and 76.7 AP (+0.5 AP) on the COCO test-dev set, and infers at a speed of 1.4x faster than ViTPose-Base. Code is available at https://github.com/AnxQ/sharpose.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Coupling Artificial Neurons in BERT and Biological Neurons in the Human Brain

Xu Liu
Mengyue Zhou
Gaosheng Shi
Yu Du
Lin Zhao
Zihao Wu
David Liu
Tianming Liu

Linking computational natural language processing (NLP) models and neural responses to language in the human brain on the one hand facilitates the effort towards disentangling the neural representations underpinning language perception, on the other hand provides neurolinguistics evidence to evaluate and improve NLP models. Mappings of an NLP model’s representations of and the brain activities evoked by linguistic input are typically deployed to reveal this symbiosis. However, two critical problems limit its advancement: 1) The model’s representations (artificial neurons, ANs) rely on layer-level embeddings and thus lack fine-granularity; 2) The brain activities (biological neurons, BNs) are limited to neural recordings of isolated cortical unit (i.e., voxel/region) and thus lack integrations and interactions among brain functions. To address those problems, in this study, we 1) define ANs with fine-granularity in transformer-based NLP models (BERT in this study) and measure their temporal activations to input text sequences; 2) define BNs as functional brain networks (FBNs) extracted from functional magnetic resonance imaging (fMRI) data to capture functional interactions in the brain; 3) couple ANs and BNs by maximizing the synchronization of their temporal activations. Our experimental results demonstrate 1) The activations of ANs and BNs are significantly synchronized; 2) the ANs carry meaningful linguistic/semantic information and anchor to their BN signatures; 3) the anchored BNs are interpretable in a neurolinguistic context. Overall, our study introduces a novel, general, and effective framework to link transformer-based NLP models and neural activities in response to language and may provide novel insights for future studies such as brain-inspired evaluation and development of NLP models.

PDF Details DOI

EAAI Journal 2023 Journal Article

Deep learning approach for predicting lymph node metastasis in non-small cell lung cancer by fusing image–gene data

Guojie Hou
Liye Jia
Yanan Zhang
Wei Wu
Lin Zhao
Juanjuan Zhao
Long Wang
Yan Qiang

The determination of lymph node metastasis is critical to the selection of treatment options for non-small cell lung cancer. Invasive pathological examinations cannot be performed frequently in clinical practice, thus non-invasive and reproducible methods are needed. The current research on non-invasive prediction methods based on image and genetic information has shortcomings such as small data sample size, high data dimension, and poor multimodal fusion effect. In this research, we propose a method for predicting lymph node metastasis in non-small cell lung cancer by fusing imaging data and genetic data to overcome these challenges. An attention-based multimodal information fusion module is designed to fuse image data and genetic data in the mid-fusion, and a bilinear fusion module based on Tucker decomposition is inserted into the model for late fusion, which significantly improves the performance of multimodal fusion. The 3D spiral transformation method is used to extract 2D images from 3D data, and the transformed images inherit and retain the spatial correlation of the original texture and edge information while increasing the image data sample size for subsequent prediction. The random forest method of important measurement is used for feature selection, and redundant data in gene information is eliminated. The experiments are carried out on the NSCLC-Radiogenomics dataset. The accuracy and AUC of the proposed model are 0. 968 and 0. 963, respectively. The experimental results show that the model is ideal performance in predicting lymph node metastasis, providing a new method for non-invasive lymph node metastasis prediction, which is beneficial to the application of precision medicine.

Details DOI

NeurIPS Conference 2023 Conference Paper

Finite-Time Analysis of Single-Timescale Actor-Critic

Xuyang Chen
Lin Zhao

Actor-critic methods have achieved significant success in many challenging applications. However, its finite-time convergence is still poorly understood in the most practical single-timescale form. Existing works on analyzing single-timescale actor-critic have been limited to i. i. d. sampling or tabular setting for simplicity. We investigate the more practical online single-timescale actor-critic algorithm on continuous state space, where the critic assumes linear function approximation and updates with a single Markovian sample per actor step. Previous analysis has been unable to establish the convergence for such a challenging scenario. We demonstrate that the online single-timescale actor-critic method provably finds an $\epsilon$-approximate stationary point with $\widetilde{\mathcal{O}}(\epsilon^{-2})$ sample complexity under standard assumptions, which can be further improved to $\mathcal{O}(\epsilon^{-2})$ under the i. i. d. sampling. Our novel framework systematically evaluates and controls the error propagation between the actor and critic. It offers a promising approach for analyzing other single-timescale reinforcement learning algorithms as well.

PDF Details

AAAI Conference 2023 Conference Paper

Global Convergence of Two-Timescale Actor-Critic for Solving Linear Quadratic Regulator

Xuyang Chen
Jingliang Duan
Yingbin Liang
Lin Zhao

The actor-critic (AC) reinforcement learning algorithms have been the powerhouse behind many challenging applications. Nevertheless, its convergence is fragile in general. To study its instability, existing works mostly consider the uncommon double-loop variant or basic models with finite state and action space. We investigate the more practical single-sample two-timescale AC for solving the canonical linear quadratic regulator (LQR) problem, where the actor and the critic update only once with a single sample in each iteration on an unbounded continuous state and action space. Existing analysis cannot conclude the convergence for such a challenging case. We develop a new analysis framework that allows establishing the global convergence to an epsilon-optimal solution with at most an order of epsilon to -2.5 sample complexity. To our knowledge, this is the first finite-time convergence analysis for the single sample two-timescale AC for solving LQR with global optimality. The sample complexity improves those of other variants by orders, which sheds light on the practical wisdom of single sample algorithms. We also further validate our theoretical findings via comprehensive simulation comparisons.

PDF Details DOI

NeurIPS Conference 2021 Conference Paper

Faster Non-asymptotic Convergence for Double Q-learning

Lin Zhao
Huaqing Xiong
Yingbin Liang

Double Q-learning (Hasselt, 2010) has gained significant success in practice due to its effectiveness in overcoming the overestimation issue of Q-learning. However, the theoretical understanding of double Q-learning is rather limited. The only existing finite-time analysis was recently established in (Xiong et al. 2020), where the polynomial learning rate adopted in the analysis typically yields a slower convergence rate. This paper tackles the more challenging case of a constant learning rate, and develops new analytical tools that improve the existing convergence rate by orders of magnitude. Specifically, we show that synchronous double Q-learning attains an $\epsilon$-accurate global optimum with a time complexity of $\tilde{\Omega}\left(\frac{\ln D}{(1-\gamma)^7\epsilon^2} \right)$, and the asynchronous algorithm achieves a time complexity of $\tilde{\Omega}\left(\frac{L}{(1-\gamma)^7\epsilon^2} \right)$, where $D$ is the cardinality of the state-action space, $\gamma$ is the discount factor, and $L$ is a parameter related to the sampling strategy for asynchronous double Q-learning. These results improve the existing convergence rate by the order of magnitude in terms of its dependence on all major parameters $(\epsilon, 1-\gamma, D, L)$. This paper presents a substantial step toward the full understanding of the fast convergence of double-Q learning.

PDF Details

NeurIPS Conference 2020 Conference Paper

Finite-Time Analysis for Double Q-learning

Huaqing Xiong
Lin Zhao
Yingbin Liang
Wei Zhang

Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values incurred by random sampling. The double Q-learning algorithm proposed in~\citet{hasselt2010double} overcomes such an overestimation issue by randomly switching the update between two Q-estimators, and has thus gained significant popularity in practice. However, the theoretical understanding of double Q-learning is rather limited. So far only the asymptotic convergence has been established, which does not characterize how fast the algorithm converges. In this paper, we provide the first non-asymptotic (i. e. , finite-time) analysis for double Q-learning. We show that both synchronous and asynchronous double Q-learning are guaranteed to converge to an $\epsilon$-accurate neighborhood of the global optimum by taking $\tilde{\Omega}\left(\left( \frac{1}{(1-\gamma)^6\epsilon^2}\right)^{\frac{1}{\omega}} +\left(\frac{1}{1-\gamma}\right)^{\frac{1}{1-\omega}}\right)$ iterations, where $\omega\in(0, 1)$ is the decay parameter of the learning rate, and $\gamma$ is the discount factor. Our analysis develops novel techniques to derive finite-time bounds on the difference between two inter-connected stochastic processes, which is new to the literature of stochastic approximation.

PDF Details

AAAI Conference 2020 Conference Paper

JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds

Lin Zhao
Wenbing Tao

In this paper, we propose a novel joint instance and semantic segmentation approach, which is called JSNet, in order to address the instance and semantic segmentation of 3D point clouds simultaneously. Firstly, we build an effective backbone network to extract robust features from the raw point clouds. Secondly, to obtain more discriminative features, a point cloud feature fusion module is proposed to fuse the different layer features of the backbone network. Furthermore, a joint instance semantic segmentation module is developed to transform semantic features into instance embedding space, and then the transformed features are further fused with instance features to facilitate instance segmentation. Meanwhile, this module also aggregates instance features into semantic feature space to promote semantic segmentation. Finally, the instance predictions are generated by applying a simple mean-shift clustering on instance embeddings. As a result, we evaluate the proposed JSNet on a large-scale 3D indoor point cloud dataset S3DIS and a part dataset ShapeNet, and compare it with existing approaches. Experimental results demonstrate our approach outperforms the state-of-theart method in 3D instance segmentation with a signiﬁcant improvement in 3D semantic prediction and our method is also beneﬁcial for part segmentation. The source code for this work is available at https: //github. com/dlinzhao/JSNet.

PDF Details

EAAI Journal 2014 Journal Article

Transcale LQG tracking control for a class of discrete stochastic systems

Lin Zhao
Yingmin Jia

A wavelet-based real-time transcale linear-quadratic-Gaussian (LQG) tracking control algorithm is presented and discussed, which extends the classical single-scale system control tool to a multiscale scenario. The new strategy determines the control law at the finest scale such that it can reflect the control laws at different coarser scales and guarantee the corresponding performance indexes of coarser scales to be minimized. Simulation result shows that significant improvements in computational efficiency are achieved.

Details DOI