arXiv subjects

Siqi Du

Publications and source records attributed to Siqi Du.

9 recordsLinked to original sources

arXiv2026

Formalizing Task-Space Complexity for Zero-Shot Generalization

Policies must operate across diverse conditions, yet a single policy is often conservative while fully adaptive schemes can be complex. We study zero-shot generalization in contextual dynamical systems and introduce a performance-centric, directional task dissimilarity--the signed divergence--that upper bounds the generalization gap from a source context to a target context. The signed divergence induces $\varepsilon$-tolerance sets that certify when a source policy class generalizes, and it yields a concrete notion of task-space complexity: the minimum number of source contexts needed so that every target context incurs at most $\varepsilon$ generalization gap. Under a mild local smoothness assumption on performance, the induced tolerance sets admit certified inner/outer balls and instance-dependent volume bounds on task-space complexity. In the finite-oracle setting, source selection reduces to set cover; a greedy strategy inherits the standard $H(n)$ approximation guarantee. Using a Mass-Spring-Damper system with linear-quadratic regulator (LQR) controllers and a nonlinear CartPole system with deep reinforcement learning controllers, we show that greedy selection achieves the same $\varepsilon$-coverage with fewer policies than uniform or random baselines. Our approach delivers a performance-based task similarity measure and practical certificates for building generalizable control with simple policies.

cs.LG↗

arXiv2026

A Controllability Perspective on Steering Follow-the-Regularized-Leader Learners in Games

Follow-the-regularized-leader (FTRL) algorithms have become popular in the context of games, providing easy-to-implement methods for each agent, as well as theoretical guarantees that the strategies of all agents will converge to some equilibrium concept (provided that all agents follow the appropriate dynamics). However, with these methods, each agent ignores the coupling in the game, and treats their payoff vectors as exogenously given. In this paper, we take the perspective of one agent (the controller) deciding their mixed strategies in a finite game, while one or more other agents update their mixed strategies according to continuous-time FTRL. Viewing the learners' dynamics as a nonlinear control system evolving on the relative interior of a simplex or product of simplices, we ask when the controller can steer the learners to a target state, using only its own mixed strategy and without modifying the game's payoff structure. For the two-player case we provide a necessary and sufficient criterion for controllability based on the existence of a fully mixed neutralizing controller strategy and a rank condition on the projected payoff map. For multi-learner interactions we give two sufficient controllability conditions, one based on uniform neutralization and one based on a periodic-drift hypothesis together with a Lie-algebra rank condition. We illustrate these results on canonical examples such as Rock-Paper-Scissors and a construction related to Brockett's integrator.

eess.SY↗

arXiv2025

An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity

In Earth sciences, unobserved factors exhibit non-stationary spatial distributions, causing the relationships between features and targets to display spatial heterogeneity. In geographic machine learning tasks, conventional statistical learning methods often struggle to capture spatial heterogeneity, leading to unsatisfactory prediction accuracy and unreliable interpretability. While approaches like Geographically Weighted Regression (GWR) capture local variations, they fall short of uncovering global patterns and tracking the continuous evolution of spatial heterogeneity. Motivated by this limitation, we propose a novel perspective - that is, simultaneously modeling common features across different locations alongside spatial differences using deep neural networks. The proposed method is a dual-branch neural network with an encoder-decoder structure. In the encoding stage, the method aggregates node information in a spatiotemporal conditional graph using GCN and LSTM, encoding location-specific spatiotemporal heterogeneity as an implicit conditional vector. Additionally, a self-attention-based encoder is used to extract location-invariant common features from the data. In the decoding stage, the approach employs a conditional generation strategy that predicts response variables and interpretative weights based on data features under spatiotemporal conditions. The approach is validated by predicting vegetation gross primary productivity (GPP) using global climate and land cover data from 2001 to 2020. Trained on 50 million samples and tested on 2.8 million, the proposed model achieves an RMSE of 0.836, outperforming LightGBM (1.063) and TabNet (0.944). Visualization analyses indicate that our method can reveal the distribution differences of the dominant factors of GPP across various times and locations.

cs.CV↗

arXiv2024

AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation

Understanding indoor scenes is crucial for urban studies. Considering the dynamic nature of indoor environments, effective semantic segmentation requires both real-time operation and high accuracy.To address this, we propose AsymFormer, a novel network that improves real-time semantic segmentation accuracy using RGB-D multi-modal information without substantially increasing network complexity. AsymFormer uses an asymmetrical backbone for multimodal feature extraction, reducing redundant parameters by optimizing computational resource distribution. To fuse asymmetric multimodal features, a Local Attention-Guided Feature Selection (LAFS) module is used to selectively fuse features from different modalities by leveraging their dependencies. Subsequently, a Cross-Modal Attention-Guided Feature Correlation Embedding (CMA) module is introduced to further extract cross-modal representations. The AsymFormer demonstrates competitive results with 54.1% mIoU on NYUv2 and 49.1% mIoU on SUNRGBD. Notably, AsymFormer achieves an inference speed of 65 FPS (79 FPS after implementing mixed precision quantization) on RTX3090, demonstrating that AsymFormer can strike a balance between high accuracy and efficiency.

cs.CV↗

arXiv2023

Tree-GPT: Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis

This paper introduces a novel framework, Tree-GPT, which incorporates Large Language Models (LLMs) into the forestry remote sensing data workflow, thereby enhancing the efficiency of data analysis. Currently, LLMs are unable to extract or comprehend information from images and may generate inaccurate text due to a lack of domain knowledge, limiting their use in forestry data analysis. To address this issue, we propose a modular LLM expert system, Tree-GPT, that integrates image understanding modules, domain knowledge bases, and toolchains. This empowers LLMs with the ability to comprehend images, acquire accurate knowledge, generate code, and perform data analysis in a local environment. Specifically, the image understanding module extracts structured information from forest remote sensing images by utilizing automatic or interactive generation of prompts to guide the Segment Anything Model (SAM) in generating and selecting optimal tree segmentation results. The system then calculates tree structural parameters based on these results and stores them in a database. Upon receiving a specific natural language instruction, the LLM generates code based on a thought chain to accomplish the analysis task. The code is then executed by an LLM agent in a local environment and . For ecological parameter calculations, the system retrieves the corresponding knowledge from the knowledge base and inputs it into the LLM to guide the generation of accurate code. We tested this system on several tasks, including Search, Visualization, and Machine Learning Analysis. The prototype system performed well, demonstrating the potential for dynamic usage of LLMs in forestry research and environmental sciences.

cs.CV↗

arXiv2023

Multimodal N-of-1 trials: A Novel Personalized Healthcare Design

N-of-1 trials aim to estimate treatment effects on the individual level and can be applied to personalize a wide range of physical and digital interventions in mHealth. In this study, we propose and apply a framework for multimodal N-of-1 trials in order to allow the inclusion of health outcomes assessed through images, audio or videos. We illustrate the framework in a series of N-of-1 trials that investigate the effect of acne creams on acne severity assessed through pictures. For the analysis, we compare an expert-based manual labelling approach with different deep learning-based pipelines where in a first step, we train and fine-tune convolutional neural networks (CNN) on the images. Then, we use a linear mixed model on the scores obtained in the first step in order to test the effectiveness of the treatment. The results show that the CNN-based test on the images provides a similar conclusion as tests based on manual expert ratings of the images, and identifies a treatment effect in one individual. This illustrates that multimodal N-of-1 trials can provide a powerful way to identify individual treatment effects and can enable large-scale studies of a large variety of health outcomes that can be actively and passively assessed using technological advances in order to personalized health interventions.

stat.AP↗

arXiv2021

Calibrated bootstrap for uncertainty quantification in regression models

Obtaining accurate estimates of machine learning model uncertainties on newly predicted data is essential for understanding the accuracy of the model and whether its predictions can be trusted. A common approach to such uncertainty quantification is to estimate the variance from an ensemble of models, which are often generated by the generally applicable bootstrap method. In this work, we demonstrate that the direct bootstrap ensemble standard deviation is not an accurate estimate of uncertainty and propose a calibration method to dramatically improve its accuracy. We demonstrate the effectiveness of this calibration method for both synthetic data and physical datasets from the field of Materials Science and Engineering. The approach is motivated by applications in physical and biological science but is quite general and should be applicable for uncertainty quantification in a wide range of machine learning regression models.

cond-mat.mtrl-sci↗

arXiv2016

Three-dimensional gravity-driven deterministic lateral displacement

We present a simple solution to enhance the separation ability of deterministic lateral displacement (DLD) systems by expanding the two-dimensional nature of these devices and driving the particles into size-dependent, fully three-dimensional trajectories. Specifically, we drive the particles through an array of long cylindrical posts, such that they not only move in the plane perpendicular to the posts as in traditional two-dimensional DLD systems (in-plane motion), but also along the axial direction of the solid posts (out-of-plane motion). We show that the (projected) in-plane motion of the particles is completely analogous to that observed in 2D-DLD systems. In fact, a theoretical model originally developed for force-driven, two-dimensional DLD systems accurately describes the experimental results. More importantly, we analyze the particles out-of-plane motion and observe that, for certain orientations of the driving force, significant differences in the out-of-plane displacement depending on particle size. Therefore, taking advantage of both the in-plane and out-of-plane motion of the particles, it is possible to achieve the simultaneous fractionation of a polydisperse suspension into multiple streams.

cond-mat.soft↗

arXiv2015

Deterministic separation of suspended particles in a reconfigurable obstacle array

We use a macromodel of a flow-driven deterministic lateral displacement (DLD) microfluidic system to investigate conditions leading to size-separation of suspended particles. This model system can be easily reconfigured to establish an arbitrary orientation between the average flow field and the array of obstacles comprising the stationary phase (forcing angle). We also investigate the effect of obstacle size using two arrays with different obstacles but same surface-to-surface distance between them. In all cases, we observe the presence of a locked mode at small forcing angles, in which particles move along a principal direction in the lattice until a locked-to-zigzag transition takes place when the driving force reaches a critical angle. We show that the transition occurs at increasing angles for larger particles, thus enabling particle separation at specific forcing angles. Moreover, we observe a linear correlation between the critical angle and the size of the particles that could be used in the design of microfluidic systems with a fixed orientation of the flow field. Finally, we present a simple model, based on the presence of irreversible interactions between the suspended particles and the obstacles, which describes the observed dependence of the migration angle on the orientation of the average flow.

physics.flu-dyn↗