arXiv subjects

Yuan Sun

Publications and source records attributed to Yuan Sun.

At least 91 records · Page 5Linked to original sources

arXiv2024

Adaptive Stabilization Based on Machine Learning for Column Generation

Column generation (CG) is a well-established method for solving large-scale linear programs. It involves iteratively optimizing a subproblem containing a subset of columns and using its dual solution to generate new columns with negative reduced costs. This process continues until the dual values converge to the optimal dual solution to the original problem. A natural phenomenon in CG is the heavy oscillation of the dual values during iterations, which can lead to a substantial slowdown in the convergence rate. Stabilization techniques are devised to accelerate the convergence of dual values by using information beyond the state of the current subproblem. However, there remains a significant gap in obtaining more accurate dual values at an earlier stage. To further narrow this gap, this paper introduces a novel approach consisting of 1) a machine learning approach for accurate prediction of optimal dual solutions and 2) an adaptive stabilization technique that effectively capitalizes on accurate predictions. On the graph coloring problem, we show that our method achieves a significantly improved convergence rate compared to traditional methods.

math.OC↗

arXiv2024

DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation

Multi-person pose estimation (MPPE) presents a formidable yet crucial challenge in computer vision. Most existing methods predominantly concentrate on isolated interaction either between instances or joints, which is inadequate for scenarios demanding concurrent localization of both instances and joints. This paper introduces a novel CNN-based single-stage method, named Dual-path Hierarchical Relation Network (DHRNet), to extract instance-to-joint and joint-to-instance interactions concurrently. Specifically, we design a dual-path interaction modeling module (DIM) that strategically organizes cross-instance and cross-joint interaction modeling modules in two complementary orders, enriching interaction information by integrating merits from different correlation modeling branches. Notably, DHRNet excels in joint localization by leveraging information from other instances and joints. Extensive evaluations on challenging datasets, including COCO, CrowdPose, and OCHuman datasets, showcase DHRNet's state-of-the-art performance. The code will be released at https://github.com/YHDang/dhrnet-multi-pose-estimation.

cs.CV↗

arXiv2024

Machine Learning-Enhanced Ant Colony Optimization for Column Generation

Column generation (CG) is a powerful technique for solving optimization problems that involve a large number of variables or columns. This technique begins by solving a smaller problem with a subset of columns and gradually generates additional columns as needed. However, the generation of columns often requires solving difficult subproblems repeatedly, which can be a bottleneck for CG. To address this challenge, we propose a novel method called machine learning enhanced ant colony optimization (MLACO), to efficiently generate multiple high-quality columns from a subproblem. Specifically, we train a ML model to predict the optimal solution of a subproblem, and then integrate this ML prediction into the probabilistic model of ACO to sample multiple high-quality columns. Our experimental results on the bin packing problem with conflicts show that the MLACO method significantly improves the performance of CG compared to several state-of-the-art methods. Furthermore, when our method is incorporated into a Branch-and-Price method, it leads to a significant reduction in solution time.

cs.NE↗

arXiv2024

Evolutionary Multi-Objective Optimisation for Fairness-Aware Self Adjusting Memory Classifiers in Data Streams

This paper introduces a novel approach, evolutionary multi-objective optimisation for fairness-aware self-adjusting memory classifiers, designed to enhance fairness in machine learning algorithms applied to data stream classification. With the growing concern over discrimination in algorithmic decision-making, particularly in dynamic data stream environments, there is a need for methods that ensure fair treatment of individuals across sensitive attributes like race or gender. The proposed approach addresses this challenge by integrating the strengths of the self-adjusting memory K-Nearest-Neighbour algorithm with evolutionary multi-objective optimisation. This combination allows the new approach to efficiently manage concept drift in streaming data and leverage the flexibility of evolutionary multi-objective optimisation to maximise accuracy and minimise discrimination simultaneously. We demonstrate the effectiveness of the proposed approach through extensive experiments on various datasets, comparing its performance against several baseline methods in terms of accuracy and fairness metrics. Our results show that the proposed approach maintains competitive accuracy and significantly reduces discrimination, highlighting its potential as a robust solution for fairness-aware data stream classification. Further analyses also confirm the effectiveness of the strategies to trigger evolutionary multi-objective optimisation and adapt classifiers in the proposed approach.

cs.AI↗

arXiv2024

Inference for non-stationary time series quantile regression with inequality constraints

We consider parameter inference for linear quantile regression with non-stationary predictors and errors, where the regression parameters are subject to inequality constraints. We show that the constrained quantile coefficient estimators are asymptotically equivalent to the metric projections of the unconstrained estimator onto the constrained parameter space. Utilizing a geometry-invariant property of this projection operation, we propose inference procedures - the Wald, likelihood ratio, and rank-based methods - that are consistent regardless of whether the true parameters lie on the boundary of the constrained parameter space. We also illustrate the advantages of considering the inequality constraints in analyses through simulations and an application to an electricity demand dataset.

stat.ME↗

arXiv2024

AutoML in The Wild: Obstacles, Workarounds, and Expectations

Automated machine learning (AutoML) is envisioned to make ML techniques accessible to ordinary users. Recent work has investigated the role of humans in enhancing AutoML functionality throughout a standard ML workflow. However, it is also critical to understand how users adopt existing AutoML solutions in complex, real-world settings from a holistic perspective. To fill this gap, this study conducted semi-structured interviews of AutoML users (N=19) focusing on understanding (1) the limitations of AutoML encountered by users in their real-world practices, (2) the strategies users adopt to cope with such limitations, and (3) how the limitations and workarounds impact their use of AutoML. Our findings reveal that users actively exercise user agency to overcome three major challenges arising from customizability, transparency, and privacy. Furthermore, users make cautious decisions about whether and how to apply AutoML on a case-by-case basis. Finally, we derive design implications for developing future AutoML solutions.

cs.HC↗

arXiv2024

Generative AI in the Wild: Prospects, Challenges, and Strategies

Propelled by their remarkable capabilities to generate novel and engaging content, Generative Artificial Intelligence (GenAI) technologies are disrupting traditional workflows in many industries. While prior research has examined GenAI from a techno-centric perspective, there is still a lack of understanding about how users perceive and utilize GenAI in real-world scenarios. To bridge this gap, we conducted semi-structured interviews with (N=18) GenAI users in creative industries, investigating the human-GenAI co-creation process within a holistic LUA (Learning, Using and Assessing) framework. Our study uncovered an intriguingly complex landscape: Prospects-GenAI greatly fosters the co-creation between human expertise and GenAI capabilities, profoundly transforming creative workflows; Challenges-Meanwhile, users face substantial uncertainties and complexities arising from resource availability, tool usability, and regulatory compliance; Strategies-In response, users actively devise various strategies to overcome many of such challenges. Our study reveals key implications for the design of future GenAI tools.

cs.HC↗

arXiv2024

iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching

We present a method named iComMa to address the 6D camera pose estimation problem in computer vision. Conventional pose estimation methods typically rely on the target's CAD model or necessitate specific network training tailored to particular object classes. Some existing methods have achieved promising results in mesh-free object and scene pose estimation by inverting the Neural Radiance Fields (NeRF). However, they still struggle with adverse initializations such as large rotations and translations. To address this issue, we propose an efficient method for accurate camera pose estimation by inverting 3D Gaussian Splatting (3DGS). Specifically, a gradient-based differentiable framework optimizes camera pose by minimizing the residual between the query image and the rendered image, requiring no training. An end-to-end matching module is designed to enhance the model's robustness against adverse initializations, while minimizing pixel-level comparing loss aids in precise pose estimation. Experimental results on synthetic and complex real-world data demonstrate the effectiveness of the proposed approach in challenging conditions and the accuracy of camera pose estimation.

cs.CV↗

arXiv2024

Fast entangling quantum gates with almost-resonant modulated driving

Recently, the method of off-resonant modulated driving (ORMD) with a special category of synthetic analytical pulses has improved the experimental performance of two- and multi-qubit gates and aroused many interests for further investigations. It particularly offers a helpful tool to the cold atom qubit platform and works well with the Rydberg dipole-dipole interaction. In order to explore more possibilities and wider ranges of options in constructing fast-speed and high-fidelity quantum logic gates, we design and analyze the entangling quantum gates via the almost-resonant modulated driving (ARMD) method. Apart from the apparent distinctions in resonance conditions, the ARMD gate protocols also have its different mechanisms in quantum physics compared with ORMD gate protocols. ARMD gates usually have abrupt phase changes and at certain points during the time evolution. In other words, whilst the modulation forms the key concept of high-fidelity Rydberg blockade gates, the on-off resonance condition can lead to nontrivial nuances in the styles of dynamics. From a more fundamental point of view, the ORMD and the ARMD methods all together belong to the unitary operation family of fast modulated driving with respect to precisely characterized inter-qubit interactions, which usually allows the quantum logic gate to concludes within one continuous pulse.

quant-ph↗

arXiv2024

Genetic-based Constraint Programming for Resource Constrained Job Scheduling

Resource constrained job scheduling is a hard combinatorial optimisation problem that originates in the mining industry. Off-the-shelf solvers cannot solve this problem satisfactorily in reasonable timeframes, while other solution methods such as many evolutionary computation methods and matheuristics cannot guarantee optimality and require low-level customisation and specialised heuristics to be effective. This paper addresses this gap by proposing a genetic programming algorithm to discover efficient search strategies of constraint programming for resource-constrained job scheduling. In the proposed algorithm, evolved programs represent variable selectors to be used in the search process of constraint programming, and their fitness is determined by the quality of solutions obtained for training instances. The novelties of this algorithm are (1) a new representation of variable selectors, (2) a new fitness evaluation scheme, and (3) a pre-selection mechanism. Tests with a large set of random and benchmark instances, the evolved variable selectors can significantly improve the efficiency of constraining programming. Compared to highly customised metaheuristics and hybrid algorithms, evolved variable selectors can help constraint programming identify quality solutions faster and proving optimality is possible if sufficiently large run-times are allowed. The evolved variable selectors are especially helpful when solving instances with large numbers of machines.

cs.NE↗

arXiv2024

Cross-modal Active Complementary Learning with Self-refining Correspondence

Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities. However, most existing methods implicitly assume the training pairs are well-aligned while ignoring the ubiquitous annotation noise, a.k.a noisy correspondence (NC), thereby inevitably leading to a performance drop. Although some methods attempt to address such noise, they still face two challenging problems: excessive memorizing/overfitting and unreliable correction for NC, especially under high noise. To address the two problems, we propose a generalized Cross-modal Robust Complementary Learning framework (CRCL), which benefits from a novel Active Complementary Loss (ACL) and an efficient Self-refining Correspondence Correction (SCC) to improve the robustness of existing methods. Specifically, ACL exploits active and complementary learning losses to reduce the risk of providing erroneous supervision, leading to theoretically and experimentally demonstrated robustness against NC. SCC utilizes multiple self-refining processes with momentum correction to enlarge the receptive field for correcting correspondences, thereby alleviating error accumulation and achieving accurate and stable corrections. We carry out extensive experiments on three image-text benchmarks, i.e., Flickr30K, MS-COCO, and CC152K, to verify the superior robustness of our CRCL against synthetic and real-world noisy correspondences.

cs.CV↗

arXiv2023

CamPro: Camera-based Anti-Facial Recognition

The proliferation of images captured from millions of cameras and the advancement of facial recognition (FR) technology have made the abuse of FR a severe privacy threat. Existing works typically rely on obfuscation, synthesis, or adversarial examples to modify faces in images to achieve anti-facial recognition (AFR). However, the unmodified images captured by camera modules that contain sensitive personally identifiable information (PII) could still be leaked. In this paper, we propose a novel approach, CamPro, to capture inborn AFR images. CamPro enables well-packed commodity camera modules to produce images that contain little PII and yet still contain enough information to support other non-sensitive vision applications, such as person detection. Specifically, CamPro tunes the configuration setup inside the camera image signal processor (ISP), i.e., color correction matrix and gamma correction, to achieve AFR, and designs an image enhancer to keep the image quality for possible human viewers. We implemented and validated CamPro on a proof-of-concept camera, and our experiments demonstrate its effectiveness on ten state-of-the-art black-box FR models. The results show that CamPro images can significantly reduce face identification accuracy to 0.3\% while having little impact on the targeted non-sensitive vision application. Furthermore, we find that CamPro is resilient to adaptive attackers who have re-trained their FR models using images generated by CamPro, even with full knowledge of privacy-preserving ISP parameters.

cs.CV↗

arXiv2023

Some remarks on selectively star-ccc spaces

In this paper, the author represent a unification and extension of concepts previously studied by several authors. By establish connections between the chain condition, selectively star-ccc properties and star-Lindelöf properties, the author provide that selectively $3$-star-ccc equals weakly strongly star-Lindelöf for normal spaces, which gives a negative answer to Question 4.10 raised by Xuan and Song in \cite{xuan2}, and use a different method from Xuan and Song to provide that the CCC implies selectively $2$-star-ccc, which gives a positive answer to Problem 4.4 in \cite{bal}. Finally, an example is given to distinguish these properties.

math.GN↗

arXiv2023

Extended two-body Rydberg blockade interaction with off-resonant modulated driving

Connectivity has an essential and indispensable role in the cold atom qubit platform. Whilst the two-qubit Rydberg blockade gate recently receives rapid progress on the fidelity side, a pressing challenge is to improve the connectivity in pursuit of genuine scalability, with the ultimate prospect of fully-connected cold atom qubit array. It turns out that a solid step along this direction can be made by introducing extra buffer atom to extend two-qubit Rydberg blockade gate beyond a purely nearest-neighbor two-body interaction. Through Rydberg dipole-dipole interactions, the buffer atom couples with the two qubit atoms which do not directly exert any physical influence on each other. The established method of off-resonant modulated driving is not only convenient but also lays down the groundwork for this latest development. Although the atomic linkage structure here exhibits nontrivial complications compared to previous cases of mere two-body system, the population can satisfyingly return to the ground state after the ground-Rydberg transition with properly designed modulation waveforms. It can be instantiated via one-photon and two-photon ground-Rydberg transitions in common practices. Furthermore, with buffer atom relay or similar structures, it is possible to realize two-qubit entangling gate between two far-away qubit atoms. Besides the core issue that such solutions are attainable, the representative modulation patterns are also analyzed, demonstrating the versatility of buffer-atom-mediated two-qubit gate. Put in a broader perspective, these efforts bring the cold atom qubit platform closer to the notions of wires and junctions in solid state electronics.

quant-ph↗

arXiv2023

Towards High-quality HDR Deghosting with Conditional Diffusion Models

High Dynamic Range (HDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. Despite the remarkable progress, DNN-based methods still generate ghosting artifacts when LDR images have saturation and large motion, which hinders potential applications in real-world scenarios. To address this challenge, we formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition, consisting of the feature condition generator and the noise predictor. Feature condition generator employs attention and Domain Feature Alignment (DFA) layer to transform the intermediate features to avoid ghosting artifacts. With the learned features as conditions, the noise predictor leverages a stochastic iterative denoising process for diffusion models to generate an HDR image by steering the sampling process. Furthermore, to mitigate semantic confusion caused by the saturation problem of LDR images, we design a sliding window noise estimator to sample smooth noise in a patch-based manner. In addition, an image space loss is proposed to avoid the color distortion of the estimated HDR results. We empirically evaluate our model on benchmark datasets for HDR imaging. The results demonstrate that our approach achieves state-of-the-art performances and well generalization to real-world images.

cs.CV↗

arXiv2023

Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms

Recently, advancements in deep learning-based superpixel segmentation methods have brought about improvements in both the efficiency and the performance of segmentation. However, a significant challenge remains in generating superpixels that strictly adhere to object boundaries while conveying rich visual significance, especially when cross-surface color correlations may interfere with objects. Drawing inspiration from neural structure and visual mechanisms, we propose a biological network architecture comprising an Enhanced Screening Module (ESM) and a novel Boundary-Aware Label (BAL) for superpixel segmentation. The ESM enhances semantic information by simulating the interactive projection mechanisms of the visual cortex. Additionally, the BAL emulates the spatial frequency characteristics of visual cortical cells to facilitate the generation of superpixels with strong boundary adherence. We demonstrate the effectiveness of our approach through evaluations on both the BSDS500 dataset and the NYUv2 dataset.

cs.CV↗

arXiv2023

Holographic renormalized Entanglement and entropic $c-$function

We compute holographic entanglement entropy (EE) and the renormalized EE in AdS solitons with gauge potential for various dimensions. The renormalized EE is a cutoff-independent universal component of EE. Via Kaluza-Klein compactification of $S^1$ and considering the low-energy regime, we deduce the $(d-1)$-dimensional renormalized EE from the odd-dimensional counterpart. This corresponds to the shrinking circle of AdS solitons, probed at large $l$. The minimal surface transitions from disk to cylinder dominance as $l$ increases. The quantum phase transition occurs at a critical subregion size, with renormalized EE showing non-monotonic behavior around this size. Across dimensions, massive modes decouple at lower energy, while degrees of freedom with Wilson lines contribute at smaller energy scales.

hep-th↗

arXiv2023

Suppression of high-frequency components in off-resonant modulated driving protocols for Rydberg blockade gate

In the rapid development of cold atom qubit platform, the two-qubit Controlled-PHASE Rydberg blockade gate via off-resonant modulated driving has been making significant progress recently. In pursuit of higher fidelity, faster operation and better robustness, a major upgrade about suppression of high-frequency components in the modulation is called for, and a systematic method has been established here for this purpose. The quintessence of this newly constructed method can be interpreted as filtering out the relatively high frequency ingredients embedded in basis functions to generate the modulation waveforms and then analyzing whether they fulfill the requirement of gate condition. It turns out that appropriate waveforms of two-qubit entangling gate protocols can be successfully established via these frequency-adjusted basis functions, with the help of numerical optimization procedures. Moreover, this timely upgrade version can be further enhanced with adaptions to specific finite Rydberg blockade strength values and dual-pulse technique to overcome residual thermal motion of qubit atoms. Besides theoretical derivations, we also thoroughly investigate the representative modulation patterns, demonstrating the versatility of off-resonant modulated driving method in the design of two-qubit entangling Rydberg blockade gate.

quant-ph↗