arXiv subjects

Yuan Liao

Publications and source records attributed to Yuan Liao.

At least 37 records · Page 2Linked to original sources

arXiv2025

Towards Routing and Edge Computing in Satellite-Terrestrial Networks: A Column Generation Approach

Edge computing that enables satellites to process raw data locally is expected to bring further timeliness and flexibility to satellite-terrestrial networks (STNs). In this letter, we propose a three-layer edge computing protocol, where raw data collected by the satellites can be processed locally, or transmitted to other satellites or the ground station via multi-hop routing for further processing. The overall computing capacity of the proposed framework is maximized by determining the offloading strategy and routing formation, subject to channel capacity and hop constraints. Given that the problem scale grows exponentially with the number of satellites and maximum-allowed hops, the column generation approach is employed to obtain the global optimal solution by activating only a subset of variables. Numerical results reveal that the proposed three-layer computing protocol, when tolerating a 5-hop routing latency, achieves a 60% improvement in computation capacity compared to the single-layer local computing configuration.

eess.SY↗

arXiv2025

Frequency-Based Alignment of EEG and Audio Signals Using Contrastive Learning and SincNet for Auditory Attention Detection

Humans exhibit a remarkable ability to focus auditory attention in complex acoustic environments, such as cocktail parties. Auditory attention detection (AAD) aims to identify the attended speaker by analyzing brain signals, such as electroencephalography (EEG) data. Existing AAD algorithms often leverage deep learning's powerful nonlinear modeling capabilities, few consider the neural mechanisms underlying auditory processing in the brain. In this paper, we propose SincAlignNet, a novel network based on an improved SincNet and contrastive learning, designed to align audio and EEG features for auditory attention detection. The SincNet component simulates the brain's processing of audio during auditory attention, while contrastive learning guides the model to learn the relationship between EEG signals and attended speech. During inference, we calculate the cosine similarity between EEG and audio features and also explore direct inference of the attended speaker using EEG data. Cross-trial evaluations results demonstrate that SincAlignNet outperforms state-of-the-art AAD methods on two publicly available datasets, KUL and DTU, achieving average accuracies of 78.3% and 92.2%, respectively, with a 1-second decision window. The model exhibits strong interpretability, revealing that the left and right temporal lobes are more active during both male and female speaker scenarios. Furthermore, we found that using data from only six electrodes near the temporal lobes maintains similar or even better performance compared to using 64 electrodes. These findings indicate that efficient low-density EEG online decoding is achievable, marking an important step toward the practical implementation of neuro-guided hearing aids in real-world applications. Code is available at: https://github.com/LiaoEuan/SincAlignNet.

eess.SP↗

arXiv2025

The Uncertainty of Machine Learning Predictions in Asset Pricing

Machine learning in asset pricing typically predicts expected returns as point estimates, ignoring uncertainty. We develop new methods to construct forecast confidence intervals for expected returns obtained from neural networks. We show that neural network forecasts of expected returns share the same asymptotic distribution as classic nonparametric methods, enabling a closed-form expression for their standard errors. We also propose a computationally feasible bootstrap to obtain the asymptotic distribution. We incorporate these forecast confidence intervals into an uncertainty-averse investment framework. This provides an economic rationale for shrinkage implementations of portfolio selection. Empirically, our methods improve out-of-sample performance.

econ.EM↗

arXiv2025

The Effect of Limited Mobility on the Experienced Segregation of Foreign-born Minorities

Segregation is a key challenge in promoting more diverse and inclusive cities. Research based on large-scale mobility data indicates that segregation between majority and minority groups persists in daily activities beyond residential areas, like visiting shops and restaurants. Aspects including lifestyle differences, homophily, and mobility constraints have been proposed as drivers of this phenomenon, but their contributions remain poorly quantified. Here, we elucidate how different mechanisms influence segregation outside home, looking at the distinctive segregation experienced by native and foreign-born individuals. Our study is based on the movement of ~320,000 individual smartphone devices collected in Sweden, where immigration creates profound divides. We find that while day-to-day activities lead to mixing for native-born individuals, foreign-born individuals remain segregated in their out-of-home activities. Using counterfactual simulations, we show that this heterogeneous effect of mobility on experienced segregation results mainly from two mechanisms: homophily and limited travel, i.e. foreign-born individuals (i) tend to visit destinations visited by similar individuals, and (ii) have limited mobility ranges. We show that homophily, as represented by destination preference, plays a minor role, while limited mobility, associated with reduced transport access, limits opportunities for foreign-born minorities to diversify their encounters. Our findings suggest that enhancing transport accessibility in foreign-born concentrated areas could reduce social segregation.

cs.SI↗

arXiv2024

Socio-spatial segregation and human mobility: A review of empirical evidence

Socio-spatial segregation is the physical separation of different social, economic, or demographic groups within a geographic space, often resulting in unequal access to resources, services, and opportunities. The literature has traditionally focused on residential segregation, examining how individuals' residential locations are distributed differently across neighborhoods based on various social attributes, e.g., race, ethnicity, and income. However, this approach overlooks the complexity of spatial segregation in people's daily activities, which often extend far beyond residential areas. Since the 2010s, emerging mobility data sources have enabled a new understanding of socio-spatial segregation by considering daily activities such as work, school, shopping, and leisure visits. From traditional surveys to GPS trajectories, diverse data sources reveal that daily mobility can result in spatial segregation levels that differ from those observed in residential segregation. This literature review focuses on three critical questions: (a) What are the strengths and limitations of segregation research incorporating extensive mobility data? (b) How do human mobility patterns relate to individuals' residential vs. experienced segregation levels? and (c) What key factors explain the relationship between one's mobility patterns and experienced segregation? Our literature review enhances the understanding of socio-spatial segregation at the individual level and clarifies core concepts and methodological challenges in the field. Our review explores studies of key themes: segregation, activity space, co-presence, and the built environment. By synthesizing their findings, we aim to offer actionable insights for reducing segregation.

cs.SI↗

arXiv2024

Mobile Phone Application Data for Activity Plan Generation

Activity-based models in transport are crucial for providing a comprehensive and realistic understanding of individuals' activity-travel patterns. Traditionally, travel surveys have been used to develop these models, but they are often costly and have small sample sizes. Mobile phone application data, one example of emerging data sources, offers an alternative with wider population coverage over extended periods for developing activity-based models. However, the challenges of using these data include sampling biases in the population coverage and individual-level data sparsity due to intermittent and irregular data collection. To synthesise activity-travel plans, we propose a novel model that combines mobile phone application data with travel survey data, addressing their limitations. Our generative model simulates multiple average weekday activity schedules for over 263,000 individuals living in Sweden, approximately 2.6% of Sweden's population. We also introduce a temporal-score approach to improve home and work location identification approaches. We assess the model's performance against an existing large-scale agent-based model of Sweden (SySMo) and a dummy model using only mobile application data. The generated activity-travel plans are comparable to the SySMo model's output and significantly surpass the dummy model's results, suggesting the proposed model's capability to generate reasonable activity-travel schedules. The proposed model is adaptable to other regions with similar travel surveys and emerging data sources, like call detail records, advancing the use of these data for activity-based models in a cost-effective, easily updated manner.

cs.SI↗

arXiv2024

Inference for Low-rank Models without Estimating the Rank

This paper studies the inference about linear functionals of high-dimensional low-rank matrices. While most existing inference methods would require consistent estimation of the true rank, our procedure is robust to rank misspecification, making it a promising approach in applications where rank estimation can be unreliable. We estimate the low-rank spaces using pre-specified weighting matrices, known as diversified projections. A novel statistical insight is that, unlike the usual statistical wisdom that overfitting mainly introduces additional variances, the over-estimated low-rank space also gives rise to a non-negligible bias due to an implicit ridge-type regularization. We develop a new inference procedure and show that the central limit theorem holds as long as the pre-specified rank is no smaller than the true rank. In one of our applications, we study multiple testing with incomplete data in the presence of confounding factors and show that our method remains valid as long as the number of controlled confounding factors is at least as large as the true number, even when no confounding factors are present.

econ.EM↗

arXiv2024

Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learned

While the field of NL2SQL has made significant advancements in translating natural language instructions into executable SQL scripts for data querying and processing, achieving full automation within the broader data science pipeline - encompassing data querying, analysis, visualization, and reporting - remains a complex challenge. This study introduces SageCopilot, an advanced, industry-grade system system that automates the data science pipeline by integrating Large Language Models (LLMs), Autonomous Agents (AutoAgents), and Language User Interfaces (LUIs). Specifically, SageCopilot incorporates a two-phase design: an online component refining users' inputs into executable scripts through In-Context Learning (ICL) and running the scripts for results reporting & visualization, and an offline preparing demonstrations requested by ICL in the online phase. A list of trending strategies such as Chain-of-Thought and prompt-tuning have been used to augment SageCopilot for enhanced performance. Through rigorous testing and comparative analysis against prompt-based solutions, SageCopilot has been empirically validated to achieve superior end-to-end performance in generating or executing scripts and offering results with visualization, backed by real-world datasets. Our in-depth ablation studies highlight the individual contributions of various components and strategies used by SageCopilot to the end-to-end correctness for data sciences.

cs.AI↗

arXiv2024

CLDTA: Contrastive Learning based on Diagonal Transformer Autoencoder for Cross-Dataset EEG Emotion Recognition

Recent advances in non-invasive EEG technology have broadened its application in emotion recognition, yielding a multitude of related datasets. Yet, deep learning models struggle to generalize across these datasets due to variations in acquisition equipment and emotional stimulus materials. To address the pressing need for a universal model that fluidly accommodates diverse EEG dataset formats and bridges the gap between laboratory and real-world data, we introduce a novel deep learning framework: the Contrastive Learning based Diagonal Transformer Autoencoder (CLDTA), tailored for EEG-based emotion recognition. The CLDTA employs a diagonal masking strategy within its encoder to extracts full-channel EEG data's brain network knowledge, facilitating transferability to the datasets with fewer channels. And an information separation mechanism improves model interpretability by enabling straightforward visualization of brain networks. The CLDTA framework employs contrastive learning to distill subject-independent emotional representations and uses a calibration prediction process to enable rapid adaptation of the model to new subjects with minimal samples, achieving accurate emotion recognition. Our analysis across the SEED, SEED-IV, SEED-V, and DEAP datasets highlights CLDTA's consistent performance and proficiency in detecting both task-specific and general features of EEG signals related to emotions, underscoring its potential to revolutionize emotion recognition research.

eess.SP↗

arXiv2024

Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design

The development of model compression is continuously motivated by the evolution of various neural network accelerators with ASIC or FPGA. On the algorithm side, the ultimate goal of quantization or pruning is accelerating the expensive DNN computations on low-power hardware. However, such a "design-and-deploy" workflow faces under-explored challenges in the current hardware-algorithm co-design community. First, although the state-of-the-art quantization algorithm can achieve low precision with negligible degradation of accuracy, the latest deep learning framework (e.g., PyTorch) can only support non-customizable 8-bit precision, data format, and parameter extraction. Secondly, the objective of quantization is to enable the computation with low-precision data. However, the current SoTA algorithm treats the quantized integer as an intermediate result, while the final output of the quantizer is the "discretized" floating-point values, ignoring the practical needs and adding additional workload to hardware designers for integer parameter extraction and layer fusion. Finally, the compression toolkits designed by the industry are constrained to their in-house product or a handful of algorithms. The limited degree of freedom in the current toolkit and the under-explored customization hinder the prototype ASIC or FPGA-based accelerator design. To resolve these challenges, we propose Torch2Chip, an open-sourced, fully customizable, and high-performance toolkit that supports user-designed compression followed by automatic model fusion and parameter extraction. Torch2Chip incorporates the hierarchical design workflow, and the user-customized compression algorithm will be directly packed into the deployment-ready format for prototype chip verification with either CNN or vision transformer (ViT). The code is available at https://github.com/SeoLabCornell/torch2chip.

cs.AR↗

arXiv2023

Swarm of Robotic Aerial Base Stations for mmWave Multi-Hop Backhauling

Robotic aerial base stations (RABSs) that are able to anchor at tall urban landforms are expected to bring further flexibility to millimeter-wave (mmWave) multi-hop backhaul networks in highly dense urban environments. In this paper, a swarm of RABSs are deployed to construct a dynamic mmWave backhaul network according to the traffic spatial distribution, and relocate their positions in subsequent time epochs according to the traffic temporal dynamic. The overall energy efficiency of the proposed framework is maximized by determining the RABS deployment, relocation and route formation under the channel capacity and hop constraints. The problem is formulated as a mixed-integer linear fractional programming (MILFP) and a two-stage method is developed to overcome the computational complexity. A wide set of numerical investigations reveal that compared to fixed small cells, only half as many RABSs are required to cover the same volume of traffic demand.

eess.SY↗

arXiv2023

Fast Inference for Quantile Regression with Tens of Millions of Observations

Big data analytics has opened new avenues in economic research, but the challenge of analyzing datasets with tens of millions of observations is substantial. Conventional econometric methods based on extreme estimators require large amounts of computing resources and memory, which are often not readily available. In this paper, we focus on linear quantile regression applied to "ultra-large" datasets, such as U.S. decennial censuses. A fast inference framework is presented, utilizing stochastic subgradient descent (S-subGD) updates. The inference procedure handles cross-sectional data sequentially: (i) updating the parameter estimate with each incoming "new observation", (ii) aggregating it as a $\textit{Polyak-Ruppert}$ average, and (iii) computing a pivotal statistic for inference using only a solution path. The methodology draws from time-series regression to create an asymptotically pivotal statistic through random scaling. Our proposed test statistic is calculated in a fully online fashion and critical values are calculated without resampling. We conduct extensive numerical studies to showcase the computational merits of our proposed inference. For inference problems as large as $(n, d) \sim (10^7, 10^3)$, where $n$ is the sample size and $d$ is the number of regressors, our method generates new insights, surpassing current inference methods in computation. Our method specifically reveals trends in the gender gap in the U.S. college wage premium using millions of observations, while controlling over $10^3$ covariates to mitigate confounding effects.

econ.EM↗

arXiv2023

SGMM: Stochastic Approximation to Generalized Method of Moments

We introduce a new class of algorithms, Stochastic Generalized Method of Moments (SGMM), for estimation and inference on (overidentified) moment restriction models. Our SGMM is a novel stochastic approximation alternative to the popular Hansen (1982) (offline) GMM, and offers fast and scalable implementation with the ability to handle streaming datasets in real time. We establish the almost sure convergence, and the (functional) central limit theorem for the inefficient online 2SLS and the efficient SGMM. Moreover, we propose online versions of the Durbin-Wu-Hausman and Sargan-Hansen tests that can be seamlessly integrated within the SGMM framework. Extensive Monte Carlo simulations show that as the sample size increases, the SGMM matches the standard (offline) GMM in terms of estimation accuracy and gains over computational efficiency, indicating its practical value for both large-scale and online datasets. We demonstrate the efficacy of our approach by a proof of concept using two well known empirical examples with large sample sizes.

econ.EM↗

arXiv2023

Inference for Low-rank Completion without Sample Splitting with Application to Treatment Effect Estimation

This paper studies the inferential theory for estimating low-rank matrices. It also provides an inference method for the average treatment effect as an application. We show that the least square estimation of eigenvectors following the nuclear norm penalization attains the asymptotic normality. The key contribution of our method is that it does not require sample splitting. In addition, this paper allows dependent observation patterns and heterogeneous observation probabilities. Empirically, we apply the proposed procedure to estimating the impact of the presidential vote on allocating the U.S. federal budget to the states.

econ.EM↗

arXiv2023

Robust Deployment and Resource Allocation for Robotic Aerial Base Station Enabled OFDM Integrated Sensing and Communication

The envisioned robotic aerial base station (RABS) concept is expected to bring further flexibility to integrated sensing and communication (ISAC) systems. In this letter, characterizing the spatial traffic distribution on a grid-based model, the RABS-assisted ISAC system is formulated as a robust optimization problem to maximize the minimum satisfaction rate (SR) under a cardinality constrained uncertainty set. The problem is reformulated as a mixed-integer linear programming (MILP) and solved approximately by the iterative linear programming rounding algorithm. Numerical investigations show that the minimum SR can be improved by 28.61% on average compared to fixed small cells.

cs.NI↗

arXiv2023

Distributed and Deep Vertical Federated Learning with Big Data

In recent years, data are typically distributed in multiple organizations while the data security is becoming increasingly important. Federated Learning (FL), which enables multiple parties to collaboratively train a model without exchanging the raw data, has attracted more and more attention. Based on the distribution of data, FL can be realized in three scenarios, i.e., horizontal, vertical, and hybrid. In this paper, we propose to combine distributed machine learning techniques with Vertical FL and propose a Distributed Vertical Federated Learning (DVFL) approach. The DVFL approach exploits a fully distributed architecture within each party in order to accelerate the training process. In addition, we exploit Homomorphic Encryption (HE) to protect the data against honest-but-curious participants. We conduct extensive experimentation in a large-scale cluster environment and a cloud environment in order to show the efficiency and scalability of our proposed approach. The experiments demonstrate the good scalability of our approach and the significant efficiency advantage (up to 6.8 times with a single server and 15.1 times with multiple servers in terms of the training time) compared with baseline frameworks.

cs.DC↗

arXiv2023

Inference for Low-Rank Models

This paper studies inference in linear models with a high-dimensional parameter matrix that can be well-approximated by a ``spiked low-rank matrix.'' A spiked low-rank matrix has rank that grows slowly compared to its dimensions and nonzero singular values that diverge to infinity. We show that this framework covers a broad class of models of latent-variables which can accommodate matrix completion problems, factor models, varying coefficient models, and heterogeneous treatment effects. For inference, we apply a procedure that relies on an initial nuclear-norm penalized estimation step followed by two ordinary least squares regressions. We consider the framework of estimating incoherent eigenvectors and use a rotation argument to argue that the eigenspace estimation is asymptotically unbiased. Using this framework we show that our procedure provides asymptotically normal inference and achieves the semiparametric efficiency bound. We illustrate our framework by providing low-level conditions for its application in a treatment effects context where treatment assignment might be strongly dependent.

math.ST↗

arXiv2023

Inference on Time Series Nonparametric Conditional Moment Restrictions Using General Sieves

General nonlinear sieve learnings are classes of nonlinear sieves that can approximate nonlinear functions of high dimensional variables much more flexibly than various linear sieves (or series). This paper considers general nonlinear sieve quasi-likelihood ratio (GN-QLR) based inference on expectation functionals of time series data, where the functionals of interest are based on some nonparametric function that satisfy conditional moment restrictions and are learned using multilayer neural networks. While the asymptotic normality of the estimated functionals depends on some unknown Riesz representer of the functional space, we show that the optimally weighted GN-QLR statistic is asymptotically Chi-square distributed, regardless whether the expectation functional is regular (root-$n$ estimable) or not. This holds when the data are weakly dependent beta-mixing condition. We apply our method to the off-policy evaluation in reinforcement learning, by formulating the Bellman equation into the conditional moment restriction framework, so that we can make inference about the state-specific value functional using the proposed GN-QLR method with time series data. In addition, estimating the averaged partial means and averaged partial derivatives of nonparametric instrumental variables and quantile IV models are also presented as leading examples. Finally, a Monte Carlo study shows the finite sample performance of the procedure

stat.ML↗