arXiv subjects

Meng Xiang

Publications and source records attributed to Meng Xiang.

6 recordsLinked to original sources

arXiv2026

Mapping the Fitness Landscape: A Structure-Guided Approach to Multi-Modal Optimization

Multimodal optimization requires finding many optima rather than merely keeping a diverse population. Yet most niching-based evolutionary algorithms rely on distances or density estimators without explicitly recovering the underlying peak--basin organization in the decision space, which can lead to pseudo-multimodality: many distinct individuals ultimately collapse into only a few basins. We introduce Chaotic Landscape-Decoding Evolution (CLDE), a decision-space-centric framework that turns multimodal search into a closed loop of decode--value--allocate--refine. CLDE injects controlled global exploration via a logistic chaotic map with a decaying step size, then builds a $k$-nearest-neighbor graph on a decoding canvas and performs persistence-guided basin growing that merges peaks only when they are not separated by deep valleys. An adaptive persistence threshold continuously tunes the decoding resolution online to avoid over-fragmentation and over-merging. Guided by the decoded structure, CLDE carries out basin-wise selection and refinement to improve solution quality while preserving basin coverage. We instantiate CLDE as CLDE-S and CLDE-M for single- and multi-objective multimodal optimization. Experiments on 20 CEC2013 functions show that CLDE-S achieves strong peak ratio under the same evaluation budget, while on DTLZ and MMMOP suites CLDE-M attains competitive IGD/IGDx, with pronounced gains on strongly multimodal problems.

cs.NE↗

arXiv2026

Distribution-Free Pretraining of Classification Losses via Evolutionary Dynamics

We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited synthetic prediction-label pairs, without accessing real samples during the main loss pretraining stage. EDL parameterizes the loss as a lightweight network and is trained with a semantics-free ranking-consistency objective that assigns larger penalties for more erroneous predictions. To robustly explore the space of loss functions, we optimize EDL via an evolutionary strategy and introduce chaotic mutation to improve exploration under noisy fitness evaluations. Experiments on CIFAR-10 with ResNet backbones show that EDL can serve as a drop-in replacement for cross-entropy and achieves competitive or improved accuracy, while ablation studies confirm that chaotic mutation yields faster convergence and better synthetic pretraining metrics than standard Gaussian mutation.

cs.LG↗

arXiv2026

Quaternion optical computing chip for parallel high-dimensional data processing

Optical computing chips have emerged as a transformative computing technology due to their high computational density, low energy consumption, and compact footprint. While real- and complex-valued computing chips have been well developed, their fundamental limitations in representing high-dimensional data significantly constrain their applicability in modern signal processing. Quaternions enable direct operations on three- and four-dimensional data, powering high-dimensional processing in data analytics and artificial intelligence. Here we demonstrate a quaternion optical computing chip (QOCC) for the first time and benchmark its performance in several typical application scenarios: three-dimensional point cloud processing, RGB chromatic transformation, and quaternion convolutional neural network for color image recognition. The QOCC harnesses high parallelism of light by wavelength-division multiplexing, processing high-dimensional data simultaneously through multiple optical wavelength channels. Compared to the electronic computing counterpart, our QOCC achieves higher computational fidelity (root mean square error < 0.035) and substantially reduced computational load (2/3 lower). It paves the way towards next-generation optical computing, overcoming the limitations of traditional computing systems in high-dimensional data processing.

physics.optics↗

arXiv2024

GARA: A novel approach to Improve Genetic Algorithms' Accuracy and Efficiency by Utilizing Relationships among Genes

Genetic algorithms have played an important role in engineering optimization. Traditional GAs treat each gene separately. However, biophysical studies of gene regulatory networks revealed direct associations between different genes. It inspires us to propose an improvement to GA in this paper, Gene Regulatory Genetic Algorithm (GRGA), which, to our best knowledge, is the first time to utilize relationships among genes for improving GA's accuracy and efficiency. We design a directed multipartite graph encapsulating the solution space, called RGGR, where each node corresponds to a gene in the solution and the edge represents the relationship between adjacent nodes. The edge's weight reflects the relationship degree and is updated based on the idea that the edges' weights in a complete chain as candidate solution with acceptable or unacceptable performance should be strengthened or reduced, respectively. The obtained RGGR is then employed to determine appropriate loci of crossover and mutation operators, thereby directing the evolutionary process toward faster and better convergence. We analyze and validate our proposed GRGA approach in a single-objective multimodal optimization problem, and further test it on three types of applications, including feature selection, text summarization, and dimensionality reduction. Results illustrate that our GARA is effective and promising.

cs.NE↗

arXiv2020

Coherent synthetic aperture imaging for visible remote sensing via reflective Fourier ptychography

Synthetic aperture radar (SAR) can measure the phase with antenna and microwave, which cannot be directly extended to visible light imaging due to phase lost. In this letter, we reported an active remote sensing with visible light via reflective Fourier ptychography (FP), termed coherent synthetic aperture imaging (CSAI), achieving high resolution, wide field-of-view (FOV) and phase recovery. A proof-of-concept experiment was reported with laser scanning and a collimator for the infinite object. Both smooth and rough objects are tested, and the spatial resolution increased from 15.6 um to 3.48 um with a factor of 4.5. The speckle noise can be suppressed by FP unexpectedly. Meanwhile, the CSAI method may replace the adaptive optics to tackle the aberration induced from atmospheric turbulence and optical system by one-step deconvolution.

physics.optics↗

arXiv2017

Single wavelength 480 Gb/s direct detection over 80km SSMF enabled by Stokes Vector Kramers Kronig transceiver

We propose 4D modulation with directed detection employing a novel Stokes-Vector Kramers-Kronig transceiver. It shows that employing Stokes vector receiver, transmitted digital carrier and Kramers-Kronig detection offers an effective way to de-rotate polarization multiplexed complex double side band signal without using a local oscillator at receiver. The impact of system parameters and configurations including carrier-to-signal-power ratio, guard band of the digital carrier, oversampling ratio and real MIMO is experimentally investigated. Finally, a record 480 Gb/s data rate over 80 km SSMF is achieved in a 60 Gbaud PDM-16QAM single carrier experiment with a BER below the threshold of 2.0x10-2

eess.SP↗