arXiv subjects

Nan Lin

Publications and source records attributed to Nan Lin.

At least 19 recordsLinked to original sources

arXiv2026

Adaptive Iterative Hard Thresholding for Online High-dimensional Quantile Regression

Online high-dimensional regression requires algorithms that can update sequentially while preserving structural sparsity. We propose \textit{Adaptive Iterative Hard Thresholding (AIHT)}, an online sparse-regression framework that alternates stochastic subgradient updates with adaptively scheduled hard-thresholding steps. The key idea is to separate support discovery from local refinement: early in the learning process, AIHT delays thresholding so that weak but informative coordinates have time to accumulate signal, while later it increases the projection frequency to stabilize the sparse estimator and exploit local curvature. We develop the theory for high-dimensional online quantile regression, a challenging setting in which the loss is nonsmooth and the data may exhibit heterogeneity or heavy-tailed noise. Under restricted curvature and gradient-leakage conditions, AIHT remains in an inflated sparse cone, exhibits a two-phase convergence behavior, and attains logarithmic regret for the sliding-window objective. Simulations for online quantile regression, together with threshold-scheduling ablations, support the proposed mechanism and illustrate its advantage over standard online sparse-learning baselines.

stat.ML↗

arXiv2026

Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints

Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, multimodal action distributions, they suffer from two critical limitations: their stochastic reverse processes render entropy intractable (necessitating heuristic exploration), and computing policy gradients through long denoising chains is expensive and unstable. In this work, we show that ODE-based flow matching inherently resolves these issues by enabling both simulation-free policy optimization and tractable entropy computation. Building on this, we introduce Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints (FMER). Our framework exploits this insight in three ways. First, we theoretically establish that minimizing an advantage-weighted conditional flow matching loss acts as a simulation-free surrogate for policy mirror descent. This steers the velocity field toward high-value regions while entirely avoiding backpropagation through the ODE solver. Second, we derive an analytic entropy objective that corrects for the density distortion caused by the $\tanh$ transformation (mapping an unbounded latent space to bounded actions), thereby facilitating principled maximum-entropy optimization. Finally, we dynamically tune the mirror descent temperature based on the effective sample size to enforce a robust trust region during training. Empirical evaluations demonstrate that FMER achieves superior performance on the challenging sparse-reward FrankaKitchen environment, while maintaining competitive results across standard dense-reward MuJoCo benchmarks.

cs.LG↗

arXiv2026

SmartMeterFM: Unifying Smart Meter Data Generative Tasks Using Flow Matching Models

Smart meter data is the foundation for planning and operating the distribution network. Unfortunately, such data are not always available due to privacy regulations. Meanwhile, the collected data may be corrupted due to sensor or transmission failure, or it may not have sufficient resolution for downstream tasks. A wide range of generative tasks is formulated to address these issues, including synthetic data generation, missing data imputation, and super-resolution. Despite the success of machine learning models on these tasks, dedicated models need to be designed and trained for each task, leading to redundancy and inefficiency. In this paper, by recognizing the powerful modeling capability of flow matching models, we propose a new approach to unify diverse smart meter data generative tasks with a single model trained for conditional generation. The proposed flow matching models are trained to generate challenging, high-dimensional time series data, specifically monthly smart meter data at a 15 min resolution. By viewing different generative tasks as distinct forms of partial data observations and injecting them into the generation process, we unify tasks such as imputation and super-resolution with a single model, eliminating the need for re-training. The data generated by our model not only are consistent with the given observations but also remain realistic, showing better performance against interpolation and other machine learning based baselines dedicated to the tasks.

cs.LG↗

arXiv2025

Reinforcement Learning for Robotic Safe Control with Force Sensing

For the task with complicated manipulation in unstructured environments, traditional hand-coded methods are ineffective, while reinforcement learning can provide more general and useful policy. Although the reinforcement learning is able to obtain impressive results, its stability and reliability is hard to guarantee, which would cause the potential safety threats. Besides, the transfer from simulation to real world also will lead in unpredictable situations. To enhance the safety and reliability of robots, we introduce the force and haptic perception into reinforcement learning. Force and tactual sensation play key roles in robotic dynamic control and human-robot interaction. We demonstrate that the force-based reinforcement learning method can be more adaptive to environment, especially in sim-to-real transfer. Experimental results show in object pushing task, our strategy is safer and more efficient in both simulation and real world, thus it holds prospects for a wide variety of robotic applications.

cs.RO↗

arXiv2025

Discovering Semantic Subdimensions through Disentangled Conceptual Representations

Understanding the core dimensions of conceptual semantics is fundamental to uncovering how meaning is organized in language and the brain. Existing approaches often rely on predefined semantic dimensions that offer only broad representations, overlooking finer conceptual distinctions. This paper proposes a novel framework to investigate the subdimensions underlying coarse-grained semantic dimensions. Specifically, we introduce a Disentangled Continuous Semantic Representation Model (DCSRM) that decomposes word embeddings from large language models into multiple sub-embeddings, each encoding specific semantic information. Using these sub-embeddings, we identify a set of interpretable semantic subdimensions. To assess their neural plausibility, we apply voxel-wise encoding models to map these subdimensions to brain activation. Our work offers more fine-grained interpretable semantic subdimensions of conceptual meaning. Further analyses reveal that semantic dimensions are structured according to distinct principles, with polarity emerging as a key factor driving their decomposition into subdimensions. The neural correlates of the identified subdimensions support their cognitive and neuroscientific plausibility.

cs.CL↗

arXiv2024

Comparative Analysis of Zero-Shot Capability of Time-Series Foundation Models in Short-Term Load Prediction

Short-term load prediction (STLP) is critical for modern power distribution system operations, particularly as demand and generation uncertainties grow with the integration of low-carbon technologies, such as electric vehicles and photovoltaics. In this study, we evaluate the zero-shot prediction capabilities of five Time-Series Foundation Models (TSFMs)-a new approach for STLP where models perform predictions without task-specific training-against two classical models, Gaussian Process (GP) and Support Vector Regression (SVR), which are trained on task-specific datasets. Our findings indicate that even without training, TSFMs like Chronos, TimesFM, and TimeGPT can surpass the performance of GP and SVR. This finding highlights the potential of TSFMs in STLP.

eess.SY↗

arXiv2024

EnergyDiff: Universal Time-Series Energy Data Generation using Diffusion Models

High-resolution time series data are crucial for the operation and planning of energy systems such as electrical power systems and heating systems. Such data often cannot be shared due to privacy concerns, necessitating the use of synthetic data. However, high-resolution time series data is difficult to model due to its inherent high dimensionality and complex temporal dependencies. Leveraging the recent development of generative AI, especially diffusion models, we propose EnergyDiff, a universal data generation framework for energy time series data. EnergyDiff builds on state-of-the-art denoising diffusion probabilistic models, utilizing a proposed denoising network dedicated to high-resolution time series data and introducing a novel Marginal Calibration technique. Our extensive experimental results demonstrate that EnergyDiff achieves significant improvement in capturing the temporal dependencies and marginal distributions compared to baselines, particularly at the 1-minute resolution. EnergyDiff's universality is validated across diverse energy domains (e.g., electricity demand, heat pump, PV, multiple time resolutions (1 minute, 15 minutes, 30 minutes and 1 hour), and at both customer and transformer levels.

cs.LG↗

arXiv2024

Computational Models to Study Language Processing in the Human Brain: A Survey

Despite differing from the human language processing mechanism in implementation and algorithms, current language models demonstrate remarkable human-like or surpassing language capabilities. Should computational language models be employed in studying the brain, and if so, when and how? To delve into this topic, this paper reviews efforts in using computational models for brain research, highlighting emerging trends. To ensure a fair comparison, the paper evaluates various computational models using consistent metrics on the same dataset. Our analysis reveals that no single model outperforms others on all datasets, underscoring the need for rich testing datasets and rigid experimental control to draw robust conclusions in studies involving computational models.

cs.CL↗

arXiv2023

PowerFlowNet: Power Flow Approximation Using Message Passing Graph Neural Networks

Accurate and efficient power flow (PF) analysis is crucial in modern electrical networks' operation and planning. Therefore, there is a need for scalable algorithms that can provide accurate and fast solutions for both small and large scale power networks. As the power network can be interpreted as a graph, Graph Neural Networks (GNNs) have emerged as a promising approach for improving the accuracy and speed of PF approximations by exploiting information sharing via the underlying graph structure. In this study, we introduce PowerFlowNet, a novel GNN architecture for PF approximation that showcases similar performance with the traditional Newton-Raphson method but achieves it 4 times faster in the simple IEEE 14-bus system and 145 times faster in the realistic case of the French high voltage network (6470rte). Meanwhile, it significantly outperforms other traditional approximation methods, such as the DC relaxation method, in terms of performance and execution time; therefore, making PowerFlowNet a highly promising solution for real-world PF analysis. Furthermore, we verify the efficacy of our approach by conducting an in-depth experimental evaluation, thoroughly examining the performance, scalability, interpretability, and architectural dependability of PowerFlowNet. The evaluation provides insights into the behavior and potential applications of GNNs in power system analysis.

cs.LG↗

arXiv2023

Language Cognition and Language Computation -- Human and Machine Language Understanding

Language understanding is a key scientific issue in the fields of cognitive and computer science. However, the two disciplines differ substantially in the specific research questions. Cognitive science focuses on analyzing the specific mechanism of the brain and investigating the brain's response to language; few studies have examined the brain's language system as a whole. By contrast, computer scientists focus on the efficiency of practical applications when choosing research questions but may ignore the most essential laws of language. Given these differences, can a combination of the disciplines offer new insights for building intelligent language models and studying language cognitive mechanisms? In the following text, we first review the research questions, history, and methods of language understanding in cognitive and computer science, focusing on the current progress and challenges. We then compare and contrast the research of language understanding in cognitive and computer sciences. Finally, we review existing work that combines insights from language cognition and language computation and offer prospects for future development trends.

cs.CL↗

arXiv2020

NEARL: Non-Explicit Action Reinforcement Learning for Robotic Control

Traditionally, reinforcement learning methods predict the next action based on the current state. However, in many situations, directly applying actions to control systems or robots is dangerous and may lead to unexpected behaviors because action is rather low-level. In this paper, we propose a novel hierarchical reinforcement learning framework without explicit action. Our meta policy tries to manipulate the next optimal state and actual action is produced by the inverse dynamics model. To stabilize the training process, we integrate adversarial learning and information bottleneck into our framework. Under our framework, widely available state-only demonstrations can be exploited effectively for imitation learning. Also, prior knowledge and constraints can be applied to meta policy. We test our algorithm in simulation tasks and its combination with imitation learning. The experimental results show the reliability and robustness of our algorithms.

cs.RO↗

arXiv2019

Divergence control of high-harmonic generation

We show that the divergence of extreme ultraviolet pulses from high harmonic generation, which is directly linked to the shape and size of the refocused beam, can be controlled by the relative delay between the fundamental and its intense orthogonally polarized second harmonic in two-color high-harmonic generation. We find that the divergence is minimized close to the delays were the number of emitted photons is maximized. These findings are rationalized as suppression and enhancement of long and short electron trajectories as function of the phase of the two-color laser field, respectively. The orthogonally polarized second harmonic introduces a lateral momentum component that can select one trajectory whereas it deflects the other. At the same time, the second harmonic profoundly influences the tunnel ionization process that initiates high-harmonic generation, which provides another trajectory gate. Our scheme for controlling the divergence facilitates larger numerical apertures for extreme ultraviolet microscopy. In addition, the associated reduction of the size of the focus is beneficial for extreme ultraviolet nonlinear optics and spectroscopy, as well as imaging and metrology of embedded structures.

physics.optics↗

arXiv2018

Assessing method agreement for paired repeated binary measurements administered by multiple raters

Method comparison studies are essential for development in medical and clinical fields. These studies often compare a cheaper, faster, or less invasive measuring method with a widely used one to see if they have sufficient agreement for interchangeable use. In the clinical and medical context, the response measurement is usually impacted not only by the measuring method but by the rater as well. This paper proposes a model-based approach to assess agreement of two measuring methods for paired repeated binary measurements under the scenario when the agreement between two measuring methods and the agreement among raters are required to be studied in a unified framework. Based upon the generalized linear mixed models (GLMM), the decision on the adequacy of interchangeable use is made by testing the equality of fixed effects of methods. Approaches for assessing method agreement, such as the Bland-Altman diagram and Cohen's kappa, are also developed for repeated binary measurements based upon the latent variables in GLMMs. We assess our novel model-based approach by simulation studies and a real clinical research application, in which patients are evaluated repeatedly for delirium with two validated screening methods: the Confusion Assessment Method and the 3-Minute Diagnostic Interview for Confusion Assessment Method. Both the simulation studies and the real data analyses demonstrate that our new approach can effectively assess method agreement.

stat.ME↗

arXiv2018

Bivariate Causal Discovery and its Applications to Gene Expression and Imaging Data Analysis

The mainstream of research in genetics, epigenetics and imaging data analysis focuses on statistical association or exploring statistical dependence between variables. Despite their significant progresses in genetic research, understanding the etiology and mechanism of complex phenotypes remains elusive. Using association analysis as a major analytical platform for the complex data analysis is a key issue that hampers the theoretic development of genomic science and its application in practice. Causal inference is an essential component for the discovery of mechanical relationships among complex phenotypes. Many researchers suggest making the transition from association to causation. Despite its fundamental role in science, engineering and biomedicine, the traditional methods for causal inference require at least three variables. However, quantitative genetic analysis such as QTL, eQTL, mQTL, and genomic-imaging data analysis requires exploring the causal relationships between two variables. This paper will focus on bivariate causal discovery. We will introduce independence of cause and mechanism (ICM) as a basic principle for causal inference, algorithmic information theory and additive noise model (ANM) as major tools for bivariate causal discovery. Large-scale simulations will be performed to evaluate the feasibility of the ANM for bivariate causal discovery. To further evaluate their performance for causal inference, the ANM will be applied to the construction of gene regulatory networks. Also, the ANM will be applied to trait-imaging data analysis to illustrate three scenarios: presence of both causation and association, presence of association while absence of causation, and presence of causation, while lack of association between two variables.

q-bio.GN↗

arXiv2017

Investigating Inner Properties of Multimodal Representation and Semantic Compositionality with Brain-based Componential Semantics

Multimodal models have been proven to outperform text-based approaches on learning semantic representations. However, it still remains unclear what properties are encoded in multimodal representations, in what aspects do they outperform the single-modality representations, and what happened in the process of semantic compositionality in different input modalities. Considering that multimodal models are originally motivated by human concept representations, we assume that correlating multimodal representations with brain-based semantics would interpret their inner properties to answer the above questions. To that end, we propose simple interpretation methods based on brain-based componential semantics. First we investigate the inner properties of multimodal representations by correlating them with corresponding brain-based property vectors. Then we map the distributed vector space to the interpretable brain-based componential space to explore the inner properties of semantic compositionality. Ultimately, the present paper sheds light on the fundamental questions of natural language understanding, such as how to represent the meaning of words and how to combine word meanings into larger units.

cs.CL↗

arXiv2017

Community Detection by $L_0$-penalized Graph Laplacian

Community detection in network analysis aims at partitioning nodes in a network into $K$ disjoint communities. Most currently available algorithms assume that $K$ is known, but choosing a correct $K$ is generally very difficult for real networks. In addition, many real networks contain outlier nodes not belonging to any community, but currently very few algorithm can handle networks with outliers. In this paper, we propose a novel model free tightness criterion and an efficient algorithm to maximize this criterion for community detection. This tightness criterion is closely related with the graph Laplacian with $L_0$ penalty. Unlike most community detection methods, our method does not require a known $K$ and can properly detect communities in networks with outliers. Both theoretical and numerical properties of the method are analyzed. The theoretical result guarantees that, under the degree corrected stochastic block model, even for networks with outliers, the maximizer of the tightness criterion can extract communities with small misclassification rates even when the number of communities grows to infinity as the network size grows. Simulation study shows that the proposed method can recover true communities more accurately than other methods. Applications to a college football data and a yeast protein-protein interaction data also reveal that the proposed method performs significantly better.

stat.ME↗

arXiv2016

A Quadratically Regularized Functional Canonical Correlation Analysis for Identifying the Global Structure of Pleiotropy with NGS Data

Investigating the pleiotropic effects of genetic variants can increase statistical power, provide important information to achieve deep understanding of the complex genetic structures of disease, and offer powerful tools for designing effective treatments with fewer side effects. However, the current multiple phenotype association analysis paradigm lacks breadth (number of phenotypes and genetic variants jointly analyzed at the same time) and depth (hierarchical structure of phenotype and genotypes). A key issue for high dimensional pleiotropic analysis is to effectively extract informative internal representation and features from high dimensional genotype and phenotype data. To explore multiple levels of representations of genetic variants, learn their internal patterns involved in the disease development, and overcome critical barriers in advancing the development of novel statistical methods and computational algorithms for genetic pleiotropic analysis, we proposed a new framework referred to as a quadratically regularized functional CCA (QRFCCA) for association analysis which combines three approaches: (1) quadratically regularized matrix factorization, (2) functional data analysis and (3) canonical correlation analysis (CCA). Large-scale simulations show that the QRFCCA has a much higher power than that of the nine competing statistics while retaining the appropriate type 1 errors. To further evaluate performance, the QRFCCA and nine other statistics are applied to the whole genome sequencing dataset from the TwinsUK study. We identify a total of 79 genes with rare variants and 67 genes with common variants significantly associated with the 46 traits using QRFCCA. The results show that the QRFCCA substantially outperforms the nine other statistics.

q-bio.GN↗

arXiv2015

A parametrization to test black hole candidates with the spectrum of thin disks

We discuss a parametrization to describe possible deviations from the Kerr metric and test astrophysical black hole candidates with electromagnetic radiation. Our metric is a very simple generalization of the Kerr solution with two main properties: $i)$ the phenomenology is quite rich and, for example, it can describe black holes with high Novikov-Thorne radiative efficiency or black holes of very small size; $ii)$ it is suitable for the numerical calculations required to study the spectrum of thin disks. The latter point is our principal motivation to study such a kind of parametrization, because in the analysis of real data there are usually several parameters to fit and the problem with current non-Kerr metrics is that the calculation times are too long.

gr-qc↗