Searcharxiv⌕ Search

arXiv subjects

Chao Yang

Publications and source records attributed to Chao Yang.

At least 163 records · Page 9Linked to original sources

Individual Bus Trip Chain Prediction and Pattern Identification Considering Similarities

Predicting future bus trip chains for an existing user is of great significance for operators of public transit systems. Existing methods always treat this task as a time-series prediction problem, but the 1-dimensional time series structure cannot express the complex relationship between trips. To better capture the inherent patterns in bus travel behavior, this paper proposes a novel approach that synthesizes future bus trip chains based on those from similar days. Key similarity patterns are defined and tested using real-world data, and a similarity function is then developed to capture these patterns. Afterwards, a graph is constructed where each day is represented as a node and edge weight reflects the similarity between days. Besides, the trips on a given day can be regarded as labels for each node, transferring the bus trip chain prediction problem to a semi-supervised classification problem on a graph. To address this, we propose several methods and validate them on a real-world dataset of 10000 bus users, achieving state-of-the-art prediction results. Analyzing the parameters of similarity function reveals some interesting bus usage patterns, allowing us can to cluster bus users into three types: repeat-dominated, evolve-dominate and repeat-evolve balanced. In summary, our work demonstrates the effectiveness of similarity-based prediction for bus trip chains and provides a new perspective for analyzing individual bus travel patterns. The code for our prediction model is publicly available.

cs.LG↗

TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning

Recently, numerous new benchmarks have been established to evaluate the performance of large language models (LLMs) via either computing a holistic score or employing another LLM as a judge. However, these approaches suffer from data leakage due to the open access of the benchmark and inflexible evaluation process. To address this issue, we introduce $\textbf{TreeEval}$, a benchmark-free evaluation method for LLMs that let a high-performance LLM host an irreproducible evaluation session and essentially avoids the data leakage. Moreover, this LLM performs as an examiner to raise up a series of questions under a topic with a tree planing strategy, which considers the current evaluation status to decide the next question generation and ensures the completeness and efficiency of the evaluation process. We evaluate $6$ models of different parameter sizes, including $7$B, $13$B, and $33$B, and ultimately achieved the highest correlation coefficient with AlpacaEval2.0 using only around $45$ questions. We also conduct more analysis to show the robustness and reliability of TreeEval. Our code can be accessed via the provided https://github.com/Ashura5/TreeEval.

cs.CL↗

A first measurement of galaxy merger rate increasing in dynamically colder protoclusters at cosmic noon

The process of galaxy cluster formation likely leaves an imprint on the properties of its individual member galaxies. Understanding this process is essential for uncovering the evolutionary connections between galaxies and cosmic structures. Here we study a sample of ten protoclusters at z~2-3 in different dynamical states that we estimate based on spectroscopic data of their members. We combine the dynamical information with HST imaging to measure galaxy sizes and pair fractions. Our analysis reveals a clear anti-correlation between the velocity dispersion of the protocluster and its galaxy pair fractions (indicative of merger rates). The velocity dispersion also anti-correlates with the dispersion in size among of the member galaxies. These correlations may be explained by protoclusters in colder dynamical states maintaining a velocity dispersion and galaxy number density that boosts galaxy mergers, which in turn contributes to the structural expansion and compaction of galaxies. Our findings offer constraints for cosmological models regarding the evolution of galaxy morphology across different stages in the assembly of protoclusters.

astro-ph.GA↗

Quantum Chemical Density Matrix Renormalization Group Method Boosted by Machine Learning

Accurate electronic structure calculations are essential in modern materials science, but strongly correlated systems pose a significant challenge due to their computational cost. Traditional methods, such as complete active space self-consistent field (CASSCF), scale exponentially with system size, while alternative methods like the density matrix renormalization group (DMRG) scale more favorably, yet remain limited for large systems. In this work, we demonstrate how a simple machine learning model can enhance quantum chemical DMRG calculations, improving their accuracy to chemical precision, even for systems that would otherwise require considerably higher computational resources. The systems under study are polycyclic aromatic hydrocarbons, which are typical candidates for DMRG calculations and are highly relevant for advanced technological applications.

physics.chem-ph↗

Predicting nonequilibrium Green's function dynamics and photoemission spectra via nonlinear integral operator learning

Understanding the dynamics of nonequilibrium quantum many-body systems is an important research topic in a wide range of fields across condensed matter physics, quantum optics, and high-energy physics. However, numerical studies of large-scale nonequilibrium phenomena in realistic materials face serious challenges due to intrinsic high-dimensionality of quantum many-body problems. The nonequilibrium properties of many-body systems can be described by the dynamics of the Green's function of the system, whose time evolution is given by a high-dimensional system of integro-differential equations, known as the Kadanoff-Baym equations (KBEs). The time-convolution term in KBEs, which needs to be recalculated at each time step, makes it difficult to perform long-time simulations. In this paper, we develop an operator-learning framework based on Recurrent Neural Networks (RNNs) to address this challenge. The proposed framework utilizes RNNs to learn the nonlinear mapping between Green's functions and convolution integrals in KBEs. By using the learned operators as a surrogate model in the KBE solver, we obtain a general machine-learning scheme for predicting the dynamics of nonequilibrium Green's functions. This new methodology reduces the temporal computational complexity from $O(N_t^3)$ to $O(N_t)$, where $N_t$ is the total time steps taken in a simulation, thereby making it possible to study large many-body problems which are currently infeasible with conventional KBE solvers. Through different numerical examples, we demonstrate the effectiveness of the operator-learning based approach in providing accurate predictions of physical observables such as the reduced density matrix and time-resolved photoemission spectra. Moreover, our framework exhibits clear numerical convergence and can be easily parallelized, thereby facilitating many possible further developments and applications.

cond-mat.str-el↗

Dissipation-assisted preparation of topological boundary states

Robust states emerging at the boundaries of a system are an important hallmark of topological matter. Here, using the Su-Schrieffer-Heeger model and the Kitaev chain as examples, we study the impact of a type of experimentally realizable bond dissipation on topological systems by calculating the steady-state density matrix, and demonstrate that such dissipation applied near the system boundary can assist in preparing topological edge states of the parent Hamiltonian, irrespective of the initial state or filling. This effect stems from the matching between the phase distribution encoded in the topological edge states and the target state prepared through bond dissipation. This work provides new insights into the preparation of topological edge states, particularly in the context of Majorana zero modes.

cond-mat.mes-hall↗

Cross-modal Medical Image Generation Based on Pyramid Convolutional Attention Network

The integration of multimodal medical imaging can provide complementary and comprehensive information for the diagnosis of Alzheimer's disease (AD). However, in clinical practice, since positron emission tomography (PET) is often missing, multimodal images might be incomplete. To address this problem, we propose a method that can efficiently utilize structural magnetic resonance imaging (sMRI) image information to generate high-quality PET images. Our generation model efficiently utilizes pyramid convolution combined with channel attention mechanism to extract multi-scale local features in sMRI, and injects global correlation information into these features using self-attention mechanism to ensure the restoration of the generated PET image on local texture and global structure. Additionally, we introduce additional loss functions to guide the generation model in producing higher-quality PET images. Through experiments conducted on publicly available ADNI databases, the generated images outperform previous research methods in various performance indicators (average absolute error: 0.0194, peak signal-to-noise ratio: 29.65, structural similarity: 0.9486) and are close to real images. In promoting AD diagnosis, the generated images combined with their corresponding sMRI also showed excellent performance in AD diagnosis tasks (classification accuracy: 94.21 %), and outperformed previous research methods of the same type. The experimental results demonstrate that our method outperforms other competing methods in quantitative metrics, qualitative visualization, and evaluation criteria.

cs.CE↗

BESTAnP: Bi-Step Efficient and Statistically Optimal Estimator for Acoustic-n-Point Problem

We consider the acoustic-n-point (AnP) problem, which estimates the pose of a 2D forward-looking sonar (FLS) according to n 3D-2D point correspondences. We explore the nature of the measured partial spherical coordinates and reveal their inherent relationships to translation and orientation. Based on this, we propose a bi-step efficient and statistically optimal AnP (BESTAnP) algorithm that decouples the estimation of translation and orientation. Specifically, in the first step, the translation estimation is formulated as the range-based localization problem based on distance-only measurements. In the second step, the rotation is estimated via eigendecomposition based on azimuth-only measurements and the estimated translation. BESTAnP is the first AnP algorithm that gives a closed-form solution for the full six-degree pose. In addition, we conduct bias elimination for BESTAnP such that it owns the statistical property of consistency. Through simulation and real-world experiments, we demonstrate that compared with the state-of-the-art (SOTA) methods, BESTAnP is over ten times faster and features real-time capacity in resource-constrained platforms while exhibiting comparable accuracy. Moreover, for the first time, we embed BESTAnP into a sonar-based odometry which shows its effectiveness for trajectory estimation.

cs.RO↗

Quasi-Lindblad pseudomode theory for open quantum systems

We introduce a new framework to study the dynamics of open quantum systems with linearly coupled Gaussian baths. Our approach replaces the continuous bath with an auxiliary discrete set of pseudomodes with dissipative dynamics, but we further relax the complete positivity requirement in the Lindblad master equation and formulate a quasi-Lindblad pseudomode theory. We show that this quasi-Lindblad pseudomode formulation directly leads to a representation of the bath correlation function in terms of a complex weighted sum of complex exponentials, an expansion that is known to be rapidly convergent in practice and thus leads to a compact set of pseudomodes. The pseudomode representation is not unique and can differ by a gauge choice. When the global dynamics can be simulated exactly, the system dynamics is unique and independent of the specific pseudomode representation. However, the gauge choice may affect the stability of the global dynamics, and we provide an analysis of why and when the global dynamics can retain stability despite losing positivity. We showcase the performance of this formulation across various spectral densities in both bosonic and fermionic problems, finding significant improvements over conventional pseudomode formulations.

quant-ph↗

Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models

Large language models are usually fine-tuned to align with human preferences. However, fine-tuning a large language model can be challenging. In this work, we introduce $\textit{weak-to-strong search}$, framing the alignment of a large language model as a test-time greedy search to maximize the log-probability difference between small tuned and untuned models while sampling from the frozen large model. This method serves both as (1) a compute-efficient model up-scaling strategy that avoids directly tuning the large model and as (2) an instance of weak-to-strong generalization that enhances a strong model with weak test-time guidance. Empirically, we demonstrate the flexibility of weak-to-strong search across different tasks. In controlled-sentiment generation and summarization, we use tuned and untuned $\texttt{gpt2}$s to improve the alignment of large models without additional training. Crucially, in a more difficult instruction-following benchmark, AlpacaEval 2.0, we show that reusing off-the-shelf small models (e.g., $\texttt{zephyr-7b-beta}$ and its untuned version) can improve the length-controlled win rates of both white-box and black-box large models against $\texttt{gpt-4-turbo}$ (e.g., $34.4\% \rightarrow 37.9\%$ for $\texttt{Llama-3-70B-Instruct}$ and $16.0\% \rightarrow 20.1\%$ for $\texttt{gpt-3.5-turbo-instruct}$), despite the small models' low win rates $\approx 10.0\%$.

cs.CL↗

Association between built environment characteristics and school run traffic congestion in Beijing, China

School-escorted trips are a significant contributor to traffic congestion. Existing studies mainly compare road traffic during student pick-up/drop-off hours with off-peak times, often overlooking the fact that school-run traffic congestion is unevenly distributed across areas with different built environment characteristics. We examine the relationship between the built environment and school-run traffic congestion, using Beijing, China, as a case study. First, we use multi-source geospatial data to assess the built environment characteristics around schools across five dimensions: spatial concentration, transportation infrastructure, street topology, spatial richness, and scenescapes. Second, employing a generalized ordered logit model, we analyze how traffic congestion around schools varies during peak hours on school days, regular non-school days, and national college entrance exam days. Lastly, we identify the built environment factors contributing to school-run traffic congestion through multivariable linear regression and Shapley value explanations. Our findings reveal that: (1) School runs significantly exacerbate traffic congestion around schools, reducing the likelihood of free-flow by 8.34\% during school run times; (2) School-run traffic congestion is more severe in areas with multiple schools, bus stops, and scenescapes related to business and financial functions. These insights can inform the planning of new schools and urban upgrade strategies aimed at reducing traffic congestion.

stat.AP↗

GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent

Ensuring that the outputs of neural networks satisfy specific constraints is crucial for applying neural networks to real-life decision-making problems. In this paper, we consider making a batch of neural network outputs satisfy bounded and general linear constraints. We first reformulate the neural network output projection problem as an entropy-regularized linear programming problem. We show that such a problem can be equivalently transformed into an unconstrained convex optimization problem with Lipschitz continuous gradient according to the duality theorem. Then, based on an accelerated gradient descent algorithm with numerical performance enhancement, we present our architecture, GLinSAT, to solve the problem. To the best of our knowledge, this is the first general linear satisfiability layer in which all the operations are differentiable and matrix-factorization-free. Despite the fact that we can explicitly perform backpropagation based on automatic differentiation mechanism, we also provide an alternative approach in GLinSAT to calculate the derivatives based on implicit differentiation of the optimality condition. Experimental results on constrained traveling salesman problems, partial graph matching with outliers, predictive portfolio allocation and power system unit commitment demonstrate the advantages of GLinSAT over existing satisfiability layers. Our implementation is available at \url{https://github.com/HunterTracer/GLinSAT}.

cs.AI↗

Incorporating Long-term Data in Training Short-term Traffic Prediction Model

Short-term traffic volume prediction is crucial for intelligent transportation system and there are many researches focusing on this field. However, most of these existing researches concentrated on refining model architecture and ignored amount of training data. Therefore, there remains a noticeable gap in thoroughly exploring the effect of augmented dataset, especially extensive historical data in training. In this research, two datasets containing taxi and bike usage spanning over eight years in New York were used to test such effects. Experiments were conducted to assess the precision of models trained with data in the most recent 12, 24, 48, and 96 months. It was found that the training set encompassing 96 months, at times, resulted in diminished accuracy, which might be owing to disparities between historical traffic patterns and present ones. An analysis was subsequently undertaken to discern potential sources of inconsistent patterns, which may include both covariate shift and concept shift. To address these shifts, we proposed an innovative approach that aligns covariate distributions using a weighting scheme to manage covariate shift, coupled with an environment aware learning method to tackle the concept shift. Experiments based on real word datasets demonstrate the effectiveness of our method which can significantly decrease testing errors and ensure an improvement in accuracy when training with large-scale historical data. As far as we know, this work is the first attempt to assess the impact of contiguously expanding training dataset on the accuracy of traffic prediction models. Besides, our training method is able to be incorporated into most existing short-term traffic prediction models and make them more suitable for long term historical training dataset.

cs.LG↗

Leveraging Intra-Period and Inter-Period Features for Enhanced Passenger Flow Prediction of Subway Stations

Accurate short-term passenger flow prediction of subway stations plays a vital role in enabling subway station personnel to proactively address changes in passenger volume. Despite existing literature in this field, there is a lack of research on effectively integrating features from different periods, particularly intra-period and inter-period features, for subway station passenger flow prediction. In this paper, we propose a novel model called \textbf{M}uti \textbf{P}eriod \textbf{S}patial \textbf{T}emporal \textbf{N}etwork \textbf{MPSTN}) that leverages features from different periods by transforming one-dimensional time series data into two-dimensional matrices based on periods. The folded matrices exhibit structural characteristics similar to images, enabling the utilization of image processing techniques, specifically convolutional neural networks (CNNs), to integrate features from different periods. Therefore, our MPSTN model incorporates a CNN module to extract temporal information from different periods and a graph neural network (GNN) module to integrate spatial information from different stations. We compared our approach with various state-of-the-art methods for spatiotemporal data prediction using a publicly available dataset and achieved minimal prediction errors. The code for our model is publicly available in the following repository: https://github.com/xiannanhuang/MPSTN

cs.LG↗

Exploring Multifractal Critical Phases in Two-Dimensional Quasiperiodic Systems

The multifractal critical phase (MCP) fundamentally differs from extended and localized phases, exhibiting delocalized distributions in both position and momentum spaces. The investigation on the MCP has largely focused on one-dimensional quasiperiodic systems. Here, we introduce a two-dimensional (2D) quasiperiodic model with a MCP. We present its phase diagram and investigate the characteristics of the 2D system's MCP in terms of wave packet diffusion and transport based on this model. We further investigate the movement of the phase boundary induced by the introduction of next-nearest-neighbor hopping by calculating the fidelity susceptibility. Finally, we consider how to realize our studied model in superconducting circuits. Our work opens the door to exploring MCP in 2D systems.

cond-mat.dis-nn↗

Undecidability of Translational Tiling of the 4-dimensional Space with a Set of 4 Polyhypercubes

Recently, Greenfeld and Tao disprove the conjecture that translational tilings of a single tile can always be periodic [Ann. Math. 200(2024), 301-363]. In another paper [to appear in J. Eur. Math. Soc.], they also show that if the dimension $n$ is part of the input, the translational tiling for subsets of $\mathbb{Z}^n$ with one tile is undecidable. These two results are very strong pieces of evidence for the conjecture that translational tiling of $\mathbb{Z}^n$ with a monotile is undecidable, for some fixed $n$. This paper shows that translational tiling of the $3$-dimensional space with a set of $5$ polycubes is undecidable. By introducing a technique that lifts a set of polycubes and its tiling from $3$-dimensional space to $4$-dimensional space, we manage to show that translational tiling of the $4$-dimensional space with a set of $4$ tiles is undecidable. This is a step towards the attempt to settle the conjecture of the undecidability of translational tiling of the $n$-dimensional space with a monotile, for some fixed $n$.

math.CO↗

SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning

Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured explanations demand models to perform intricately structured reasoning, which poses great challenges. Most existing methods focus on single-step reasoning through supervised learning, ignoring logical dependencies between steps. Moreover, existing reinforcement learning (RL) based methods overlook the structured relationships, underutilizing the potential of RL in structured reasoning. In this paper, we propose SEER, a novel method that maximizes a structure-based return to facilitate structured reasoning and explanation. Our proposed structure-based return precisely describes the hierarchical and branching structure inherent in structured reasoning, effectively capturing the intricate relationships between different reasoning steps. In addition, we introduce a fine-grained reward function to meticulously delineate diverse reasoning steps. Extensive experiments show that SEER significantly outperforms state-of-the-art methods, achieving an absolute improvement of 6.9% over RL-based methods on EntailmentBank, a 4.4% average improvement on STREET benchmark, and exhibiting outstanding efficiency and cross-dataset generalization performance. Our code is available at https://github.com/Chen-GX/SEER.

cs.CL↗

Inference-Time Language Model Alignment via Integrated Value Guidance

Large language models are typically fine-tuned to align with human preferences, but tuning large models is computationally intensive and complex. In this work, we introduce $\textit{Integrated Value Guidance}$ (IVG), a method that uses implicit and explicit value functions to guide language model decoding at token and chunk-level respectively, efficiently aligning large language models purely at inference time. This approach circumvents the complexities of direct fine-tuning and outperforms traditional methods. Empirically, we demonstrate the versatility of IVG across various tasks. In controlled sentiment generation and summarization tasks, our method significantly improves the alignment of large models using inference-time guidance from $\texttt{gpt2}$-based value functions. Moreover, in a more challenging instruction-following benchmark AlpacaEval 2.0, we show that both specifically tuned and off-the-shelf value functions greatly improve the length-controlled win rates of large models against $\texttt{gpt-4-turbo}$ (e.g., $19.51\% \rightarrow 26.51\%$ for $\texttt{Mistral-7B-Instruct-v0.2}$ and $25.58\% \rightarrow 33.75\%$ for $\texttt{Mixtral-8x7B-Instruct-v0.1}$ with Tulu guidance).

cs.CL↗