arXiv subjects

Peng Chen

Publications and source records attributed to Peng Chen.

At least 199 records · Page 11Linked to original sources

arXiv2024

skscope: Fast Sparsity-Constrained Optimization in Python

Applying iterative solvers on sparsity-constrained optimization (SCO) requires tedious mathematical deduction and careful programming/debugging that hinders these solvers' broad impact. In the paper, the library skscope is introduced to overcome such an obstacle. With skscope, users can solve the SCO by just programming the objective function. The convenience of skscope is demonstrated through two examples in the paper, where sparse linear regression and trend filtering are addressed with just four lines of code. More importantly, skscope's efficient implementation allows state-of-the-art solvers to quickly attain the sparse solution regardless of the high dimensionality of parameter space. Numerical experiments reveal the available solvers in skscope can achieve up to 80x speedup on the competing relaxation solutions obtained via the benchmarked convex solver. skscope is published on the Python Package Index (PyPI) and Conda, and its source code is available at: https://github.com/abess-team/skscope.

stat.ML↗

arXiv2024

Sequential infinite-dimensional Bayesian optimal experimental design with derivative-informed latent attention neural operator

We develop a new computational framework to solve sequential Bayesian optimal experimental design (SBOED) problems constrained by large-scale partial differential equations with infinite-dimensional random parameters. We propose an adaptive terminal formulation of the optimality criteria for SBOED to achieve adaptive global optimality. We also establish an equivalent optimization formulation to achieve computational simplicity enabled by Laplace and low-rank approximations of the posterior. To accelerate the solution of the SBOED problem, we develop a derivative-informed latent attention neural operator (LANO), a new neural network surrogate model that leverages (1) derivative-informed dimension reduction for latent encoding, (2) an attention mechanism to capture the dynamics in the latent space, (3) an efficient training in the latent space augmented by projected Jacobian, which collectively leads to an efficient, accurate, and scalable surrogate in computing not only the parameter-to-observable (PtO) maps but also their Jacobians. We further develop the formulation for the computation of the MAP points, the eigenpairs, and the sampling from posterior by LANO in the reduced spaces and use these computations to solve the SBOED problem. We demonstrate the superior accuracy of LANO compared to two other neural architectures and the high accuracy of LANO compared to the finite element method (FEM) for the computation of MAP points and eigenvalues in solving the SBOED problem with application to the experimental design of the time to take MRI images in monitoring tumor growth. We show that the proposed computational framework achieves an amortized $180\times$ speedup.

cs.CE↗

arXiv2024

On maximal functions generated by Hörmander-type spectral multipliers

Let $(X,d,μ)$ be a metric space with doubling measure and $L$ be a nonnegative self-adjoint operator on $L^2(X)$ whose heat kernel satisfies the Gaussian upper bound. We assume that there exists an $L$-harmonic function $h$ such that the semigroup $\exp(-tL)$, after applying the Doob transform related to $h$, satisfies the upper and lower Gaussian estimates. In this paper we apply the Doob transform and some techniques as in Grafakos-Honzík-Seeger \cite{GHS2006} to obtain an optimal $\sqrt{\log(1+N)}$ bound in $L^p$ for the maximal function $\sup_{1\leq i\leq N}|m_i(L)f|$ for multipliers $m_i,1\leq i\leq N,$ with uniform estimates. Based on this, we establish sufficient conditions on the bounded Borel function $m$ such that the maximal function $M_{m,L}f(x) = \sup_{t>0} |m(tL)f(x)|$ is bounded on $L^p(X)$. The applications include Schrödinger operators with inverse square potential, Scattering operators, Bessel operators and Laplace-Beltrami operators.

math.CA↗

arXiv2024

Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case

Recently, large language model (LLM)-based agents have made significant advances across various fields. One of the most popular research areas involves applying these agents to video games. Traditionally, these methods have relied on game APIs to access in-game environmental and action data. However, this approach is limited by the availability of APIs and does not reflect how humans play games. With the advent of vision language models (VLMs), agents now have enhanced visual understanding capabilities, enabling them to interact with games using only visual inputs. Despite these advances, current approaches still face challenges in action-oriented tasks, particularly in action role-playing games (ARPGs), where reinforcement learning methods are prevalent but suffer from poor generalization and require extensive training. To address these limitations, we select an ARPG, ``Black Myth: Wukong'', as a research platform to explore the capability boundaries of existing VLMs in scenarios requiring visual-only input and complex action output. We define 12 tasks within the game, with 75% focusing on combat, and incorporate several state-of-the-art VLMs into this benchmark. Additionally, we will release a human operation dataset containing recorded gameplay videos and operation logs, including mouse and keyboard actions. Moreover, we propose a novel VARP (Vision Action Role-Playing) agent framework, consisting of an action planning system and a visual trajectory system. Our framework demonstrates the ability to perform basic tasks and succeed in 90% of easy and medium-level combat scenarios. This research aims to provide new insights and directions for applying multimodal agents in complex action game environments. The code and datasets will be made available at https://varp-agent.github.io/.

cs.AI↗

arXiv2024

Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

Transformers for time series forecasting mainly model time series from limited or fixed scales, making it challenging to capture different characteristics spanning various scales. We propose Pathformer, a multi-scale Transformer with adaptive pathways. It integrates both temporal resolution and temporal distance for multi-scale modeling. Multi-scale division divides the time series into different temporal resolutions using patches of various sizes. Based on the division of each scale, dual attention is performed over these patches to capture global correlations and local details as temporal dependencies. We further enrich the multi-scale Transformer with adaptive pathways, which adaptively adjust the multi-scale modeling process based on the varying temporal dynamics of the input, improving the accuracy and generalization of Pathformer. Extensive experiments on eleven real-world datasets demonstrate that Pathformer not only achieves state-of-the-art performance by surpassing all current models but also exhibits stronger generalization abilities under various transfer scenarios. The code is made available at https://github.com/decisionintelligence/pathformer.

cs.LG↗

arXiv2024

Mirror symmetry breaking of superradiance in a dipolar BEC

Dicke superradiance occurs when two or more emitters cooperatively interact via the electromagnetic field. This collective light scattering process has been extensively studied across various platforms, from atoms to quantum dots and organic molecules. Despite extensive research, the precise role of direct interactions between emitters in superradiance remains elusive, particularly in many-body systems where the complexity of interactions poses significant challenges. In this study, we investigate the effect of dipole-dipole interaction between 18,000 atoms in dipolar Bose-Einstein condensates (BECs) on the superradiance process. In dipolar BECs, we simplify the complex effect of anisotropic magnetic dipole-dipole interaction with Bogoliubov transformation. We observe that anisotropic Bogoliubov excitation breaks the mirror symmetry in decay modes of superradiance.

cond-mat.quant-gas↗

arXiv2024

Latent-EnSF: A Latent Ensemble Score Filter for High-Dimensional Data Assimilation with Sparse Observation Data

Accurate modeling and prediction of complex physical systems often rely on data assimilation techniques to correct errors inherent in model simulations. Traditional methods like the Ensemble Kalman Filter (EnKF) and its variants as well as the recently developed Ensemble Score Filters (EnSF) face significant challenges when dealing with high-dimensional and nonlinear Bayesian filtering problems with sparse observations, which are ubiquitous in real-world applications. In this paper, we propose a novel data assimilation method, Latent-EnSF, which leverages EnSF with efficient and consistent latent representations of the full states and sparse observations to address the joint challenges of high dimensionlity in states and high sparsity in observations for nonlinear Bayesian filtering. We introduce a coupled Variational Autoencoder (VAE) with two encoders to encode the full states and sparse observations in a consistent way guaranteed by a latent distribution matching and regularization as well as a consistent state reconstruction. With comparison to several methods, we demonstrate the higher accuracy, faster convergence, and higher efficiency of Latent-EnSF for two challenging applications with complex models in shallow water wave propagation and medium-range weather forecasting, for highly sparse observations in both space and time.

cs.LG↗

arXiv2024

Compressed Sensing based Detection Schemes for Differential Spatial Modulation in Visible Light Communication Systems

Differential spatial modulation (DSM) exploits the time dimension to facilitate the differential modulation, which can perfectly avoid the challenge in acquiring of heavily entangled channel state information of visible light communication (VLC) system. However, it has huge search space and high complexity for large number of transmitters. In this paper, a novel vector correction (VC)-based orthogonal matching pursuit (OMP) detection algorithm is proposed to reduce the complexity, which exploits the sparsity and relativity of all transmitters, and then employs a novel correction criterion by correcting the index vectors of the error estimation for improving the demodulation performance. To overcome the local optimum dilemma in the atoms searching, an OMP-assisted genetic algorithm is also proposed to further improve the bit error rate (BER) performance of the VLC-DSM system. Simulation results demonstrate that the proposed schemes can significantly reduce the computational complexity at least by 62.5% while achieving an excellent BER performance as compared with traditional maximum likelihood based receiver.

eess.SP↗

arXiv2024

Accurate, scalable, and efficient Bayesian optimal experimental design with derivative-informed neural operators

We consider optimal experimental design (OED) problems in selecting the most informative observation sensors to estimate model parameters in a Bayesian framework. Such problems are computationally prohibitive when the parameter-to-observable (PtO) map is expensive to evaluate, the parameters are high-dimensional, and the optimization for sensor selection is combinatorial and high-dimensional. To address these challenges, we develop an accurate, scalable, and efficient computational framework based on derivative-informed neural operators (DINO). We propose to use derivative-informed dimension reduction to reduce the parameter dimensions, based on which we train DINO with derivative information as an accurate and efficient surrogate for the PtO map and its derivative. Moreover, we derive DINO-enabled efficient formulations in computing the maximum a posteriori (MAP) point, the eigenvalues of approximate posterior covariance, and three commonly used optimality criteria for the OED problems. Furthermore, we provide detailed error analysis for the approximations of the MAP point, the eigenvalues, and the optimality criteria. We also propose a modified swapping greedy algorithm for the sensor selection optimization and demonstrate that the proposed computational framework is scalable to preserve the accuracy for increasing parameter dimensions and achieves high computational efficiency, with an over 1000$\times$ speedup accounting for both offline construction and online evaluation costs, compared to high-fidelity Bayesian OED solutions for a three-dimensional nonlinear convection-diffusion-reaction example with tens of thousands of parameters.

cs.CE↗

arXiv2024

Learning to Discover Forgery Cues for Face Forgery Detection

Locating manipulation maps, i.e., pixel-level annotation of forgery cues, is crucial for providing interpretable detection results in face forgery detection. Related learning objects have also been widely adopted as auxiliary tasks to improve the classification performance of detectors whereas they require comparisons between paired real and forged faces to obtain manipulation maps as supervision. This requirement restricts their applicability to unpaired faces and contradicts real-world scenarios. Moreover, the used comparison methods annotate all changed pixels, including noise introduced by compression and upsampling. Using such maps as supervision hinders the learning of exploitable cues and makes models prone to overfitting. To address these issues, we introduce a weakly supervised model in this paper, named Forgery Cue Discovery (FoCus), to locate forgery cues in unpaired faces. Unlike some detectors that claim to locate forged regions in attention maps, FoCus is designed to sidestep their shortcomings of capturing partial and inaccurate forgery cues. Specifically, we propose a classification attentive regions proposal module to locate forgery cues during classification and a complementary learning module to facilitate the learning of richer cues. The produced manipulation maps can serve as better supervision to enhance face forgery detectors. Visualization of the manipulation maps of the proposed FoCus exhibits superior interpretability and robustness compared to existing methods. Experiments on five datasets and four multi-task models demonstrate the effectiveness of FoCus in both in-dataset and cross-dataset evaluations.

cs.CV↗

arXiv2024

Multi-channel frequency router based on valley-Hall metacrystals

Topological photonics has revolutionized manipulations of electromagnetic waves by leveraging various topological phases proposed originally in condensed matters, leading to robust and error-immune signal processing. Despite considerable efforts, a critical challenge remains in devising frequency routers operating at a broadband frequency range with limited crosstalk. Previous designs usually relied on fine tuning of parameters and are difficult to be integrated efficiently and compactly. Here, targeting the demand for frequency-selective applications in on-chip photonics, we explore a topological approach to photonic frequency router via valley-Hall metacrystals. Diverging from the majority of studies which focuses on zigzag interfaces, our research shifts the attention to armchair interfaces within an ABA sandwich-like structure, where a single column of type-B metacrystal acts as a perturbation in the background type-A metacrystal. Essentially, through tuning a single geometric parameter of the type-B metacrystal, this configuration gives rise to interface states within a customized frequency band, enabling signal routing with limited crosstalk to meet specified demands. Moreover, this concept is practically demonstrated through a photonic frequency router with three distinct channels, experimentally exhibiting robust wave transmissions with excellent agreement with the design. This investigation manifests possible applications of the armchair interfaces in valley-Hall photonic systems and advances development of photonic devices that are both compact and efficient. Notably, the approach is naturally compatible with on-chip photonics and integration, which could benefit telecommunications and optical computing applications.

physics.app-ph↗

arXiv2024

Gaussian mixture Taylor approximations of risk measures constrained by PDEs with Gaussian random field inputs

This work considers the computation of risk measures for quantities of interest governed by PDEs with Gaussian random field parameters using Taylor approximations. While efficient, Taylor approximations are local to the point of expansion, and hence may degrade in accuracy when the variances of the input parameters are large. To address this challenge, we approximate the underlying Gaussian measure by a mixture of Gaussians with reduced variance in a dominant direction of parameter space. Taylor approximations are constructed at the means of each Gaussian mixture component, which are then combined to approximate the risk measures. The formulation is presented in the setting of infinite-dimensional Gaussian random parameters for risk measures including the mean, variance, and conditional value-at-risk. We also provide detailed analysis of the approximations errors arising from two sources: the Gaussian mixture approximation and the Taylor approximations. Numerical experiments are conducted for a semilinear advection-diffusion-reaction equation with a random diffusion coefficient field and for the Helmholtz equation with a random wave speed field. For these examples, the proposed approximation strategy can achieve less than $1\%$ relative error in estimating CVaR with only $\mathcal{O}(10)$ state PDE solves, which is comparable to a standard Monte Carlo estimate with $\mathcal{O}(10^4)$ samples, thus achieving significant reduction in computational cost. The proposed method can therefore serve as a way to rapidly and accurately estimate risk measures under limited computational budgets.

math.NA↗

arXiv2024

Mitigating biases in big mobility data: a case study of monitoring large-scale transit systems

Big mobility datasets (BMD) have shown many advantages in studying human mobility and evaluating the performance of transportation systems. However, the quality of BMD remains poorly understood. This study evaluates biases in BMD and develops mitigation methods. Using Google and Apple mobility data as examples, this study compares them with benchmark data from governmental agencies. Spatio-temporal discrepancies between BMD and benchmark are observed and their impacts on transportation applications are investigated, emphasizing the urgent need to address these biases to prevent misguided policymaking. This study further proposes and tests a bias mitigation method. It is shown that the mitigated BMD could generate valuable insights into large-scale public transit systems across 100+ US counties, revealing regional disparities of the recovery of transit systems from the COVID-19. This study underscores the importance of caution when using BMD in transportation research and presents effective mitigation strategies that would benefit practitioners.

physics.soc-ph↗

arXiv2024

Quantitative diffusion approximation for the Neutral $r$-Alleles Wright-Fisher Model with Mutations

We apply a Lindeberg principle under the Markov process setting to approximate the Wright-Fisher model with neutral $r$-alleles using a diffusion process, deriving an error rate based on a function class distance involving fourth-order bounded differentiable functions. This error rate consists of a linear combination of the maximum mutation rate and the reciprocal of the population size. Our result improves the error bound in the seminal work [PNAS,1977], where only the special case $r=2$ was studied.

math.PR↗

arXiv2024

A Two-stage Evolutionary Framework For Multi-objective Optimization

In the field of evolutionary multi-objective optimization, the approximation of the Pareto front (PF) is achieved by utilizing a collection of representative candidate solutions that exhibit desirable convergence and diversity. Although several multi-objective evolutionary algorithms (MOEAs) have been designed, they still have difficulties in keeping balance between convergence and diversity of population. To better solve multi-objective optimization problems (MOPs), this paper proposes a Two-stage Evolutionary Framework For Multi-objective Optimization (TEMOF). Literally, algorithms are divided into two stages to enhance the search capability of the population. During the initial half of evolutions, parental selection is exclusively conducted from the primary population. Additionally, we not only perform environmental selection on the current population, but we also establish an external archive to store individuals situated on the first PF. Subsequently, in the second stage, parents are randomly chosen either from the population or the archive. In the experiments, one classic MOEA and two state-of-the-art MOEAs are integrated into the framework to form three new algorithms. The experimental results demonstrate the superior and robust performance of the proposed framework across a wide range of MOPs. Besides, the winner among three new algorithms is compared with several existing MOEAs and shows better results. Meanwhile, we conclude the reasons that why the two-stage framework is effect for the existing benchmark functions.

cs.NE↗

arXiv2024

Vision Transformer with Key-select Routing Attention for Single Image Dehazing

We present Ksformer, utilizing Multi-scale Key-select Routing Attention (MKRA) for intelligent selection of key areas through multi-channel, multi-scale windows with a top-k operator, and Lightweight Frequency Processing Module (LFPM) to enhance high-frequency features, outperforming other dehazing methods in tests.

cs.CV↗

arXiv2024

TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent Editing

Editing objects within a scene is a critical functionality required across a broad spectrum of applications in computer vision and graphics. As 3D Gaussian Splatting (3DGS) emerges as a frontier in scene representation, the effective modification of 3D Gaussian scenes has become increasingly vital. This process entails accurately retrieve the target objects and subsequently performing modifications based on instructions. Though available in pieces, existing techniques mainly embed sparse semantics into Gaussians for retrieval, and rely on an iterative dataset update paradigm for editing, leading to over-smoothing or inconsistency issues. To this end, this paper proposes a systematic approach, namely TIGER, for coherent text-instructed 3D Gaussian retrieval and editing. In contrast to the top-down language grounding approach for 3D Gaussians, we adopt a bottom-up language aggregation strategy to generate a denser language embedded 3D Gaussians that supports open-vocabulary retrieval. To overcome the over-smoothing and inconsistency issues in editing, we propose a Coherent Score Distillation (CSD) that aggregates a 2D image editing diffusion model and a multi-view diffusion model for score distillation, producing multi-view consistent editing with much finer details. In various experiments, we demonstrate that our TIGER is able to accomplish more consistent and realistic edits than prior work.

cs.CV↗

arXiv2024

The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition

In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sensor malfunctions, and environmental unpredictability can severely impact the performance of autonomous systems. The 2024 RoboDrive Challenge was crafted to propel the development of driving perception technologies that can withstand and adapt to these real-world variabilities. Focusing on four pivotal tasks -- BEV detection, map segmentation, semantic occupancy prediction, and multi-view depth estimation -- the competition laid down a gauntlet to innovate and enhance system resilience against typical and atypical disturbances. This year's challenge consisted of five distinct tracks and attracted 140 registered teams from 93 institutes across 11 countries, resulting in nearly one thousand submissions evaluated through our servers. The competition culminated in 15 top-performing solutions, which introduced a range of innovative approaches including advanced data augmentation, multi-sensor fusion, self-supervised learning for error correction, and new algorithmic strategies to enhance sensor robustness. These contributions significantly advanced the state of the art, particularly in handling sensor inconsistencies and environmental variability. Participants, through collaborative efforts, pushed the boundaries of current technologies, showcasing their potential in real-world scenarios. Extensive evaluations and analyses provided insights into the effectiveness of these solutions, highlighting key trends and successful strategies for improving the resilience of driving perception systems. This challenge has set a new benchmark in the field, providing a rich repository of techniques expected to guide future research in this field.

cs.CV↗