STSiyu Tao

Siyu Tao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Siyu Tao has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Scalable Objective-Driven Batch Sampling in Simulation-Based Design for Models With Heteroscedastic Noise

    by Wei Chen, Anton Van Beek, Umar Farooq Ghumman, Siyu Tao, Matthew Plumlee, Daniel W. Apley, Teyu Chien, Joydeep Munshi, Ganesh Balasubramanian

    Objective-driven adaptive sampling is a widely used tool for the optimization of deterministic black-box functions. However, the optimization of stochastic simulation models as can be found in the material, biological, and social sciences is still an elusive task. In this work, we propose a scalable adaptive batch sampling scheme for the optimization of stochastic simulation models

  • Open Access

    Data-Driven Multiscale Topology Optimization Using Multi-Response Latent Variable Gaussian Process

    by Liwei Wang, Siyu Tao, Ping Zhu, Wei Chen

    *The data-driven approach is emerging as a promising method for the topological design of the multiscale structure with greater efficiency. However, existing data-driven methods mostly focus on a single class of unit cells without considering multiple classes to accommodate spatially varying desired properties. The key challenge is the lack of inherent ordering or “distance”

  • Open Access

    Bayesian Optimization for Simulation-Based Design of Multi-Model Systems

    by Siyu Tao, Anton Van Beek, Daniel W. Apley, Wei Chen

    We address the problem of simulation-based design using multiple interconnected expensive simulation models, each modeling a different subsystem. Our goal is to find the globally optimal design with minimal model evaluation costs. To our knowledge, the best existing approach is to treat the whole system as a single expensive model and apply an existing Bayesian optimization (BO)


  • Multi-Model Bayesian Optimization for Simulation-Based Design

    by Siyu Tao, Anton van Beek, Daniel W. Apley, Wei Chen

    We enhance the Bayesian optimization (BO) approach for simulation-based design of engineering systems consisting of multiple interconnected expensive simulation models. The goal is to find the global optimum design with minimal model evaluation costs. A commonly used approach is to treat the whole system as a single expensive model and apply an existing BO algorithm. This approach is inefficient due to the need to evaluate all the component models in each iteration. We propose a multi-model BO approach that dynamically and selectively evaluates one component model per iteration based on the uncertainty quantification of linked emulators (metamodels) and the knowledge gradient of system response as the acquisition function. Building on our basic formulation, we further solve problems with constraints and feedback couplings that often occur in real complex engineering design by penalizing the objective emulator and reformulating the original problem into a decoupled one. The superior efficiency of our approach is demonstrated through solving two analytical problems and the design optimization of a multidisciplinary electronic packaging system.


  • Scalable Adaptive Batch Sampling in Simulation-Based Design With Heteroscedastic Noise

    by Anton van Beek, Umar Farooq Ghumman, Joydeep Munshi, Siyu Tao, TeYu Chien, Ganesh Balasubramanian, Matthew Plumlee, Daniel Apley, Wei Chen

    In this study, we propose a scalable batch sampling scheme for optimization of simulation models with spatially varying noise. The proposed scheme has two primary advantages: (i) reduced simulation cost by recommending batches of samples at carefully selected spatial locations and (ii) improved scalability by actively considering replicating at previously observed sampling locations. Replication improves the scalability of the proposed sampling scheme as the computational cost of adaptive sampling schemes grow cubicly with the number of unique sampling locations. Our main consideration for the allocation of computational resources is the minimization of the uncertainty in the optimal design. We analytically derive the relationship between the “exploration versus replication decision” and the posterior variance of the spatial random process used to approximate the simulation model’s mean response. Leveraging this reformulation in a novel objective-driven adaptive sampling scheme, we show that we can identify batches of samples that minimize the prediction uncertainty only in the regions of the design space expected to contain the global optimum. Finally, the proposed sampling scheme adopts a modified preposterior analysis that uses a zeroth-order interpolation of the spatially varying simulation noise to identify sampling batches. Through the optimization of three numerical test functions and one engineering problem, we demonstrate (i) the efficacy and of the proposed sampling scheme to deal with a wide array of stochastic functions, (ii) the superior performance of the proposed method on all test functions compared to existing methods, (iii) the empirical validity of using a zeroth-order approximation for the allocation of sampling batches, and (iv) its applicability to molecular dynamics simulations by optimizing the performance of an organic photovoltaic cell as a function of its processing settings.


  • Data-Driven Topology Optimization With Multiclass Microstructures Using Latent Variable Gaussian Process

    by Liwei Wang, Siyu Tao, Ping Zhu, Wei Chen

    The data-driven approach is emerging as a promising method for the topological design of multiscale structures with greater efficiency. However, existing data-driven methods mostly focus on a single class of microstructures without considering multiple classes to accommodate spatially varying desired properties. The key challenge is the lack of an inherent ordering or “distance” measure between different classes of microstructures in meeting a range of properties. To overcome this hurdle, we extend the newly developed latent-variable Gaussian process (LVGP) models to create multi-response LVGP (MR-LVGP) models for the microstructure libraries of metamaterials, taking both qualitative microstructure concepts and quantitative microstructure design variables as mixed-variable inputs. The MR-LVGP model embeds the mixed variables into a continuous design space based on their collective effects on the responses, providing substantial insights into the interplay between different geometrical classes and material parameters of microstructures. With this model, we can easily obtain a continuous and differentiable transition between different microstructure concepts that can render gradient information for multiscale topology optimization. We demonstrate its benefits through multiscale topology optimization with aperiodic microstructures. Design examples reveal that considering multiclass microstructures can lead to improved performance due to the consistent load-transfer paths for micro- and macro-structures.


  • Data centric nanocomposites design via mixed-variable Bayesian optimization

    by Akshay Iyer, Yichi Zhang, Aditya Prasad, Praveen Gupta, Siyu Tao, Yixing Wang, Prajakta Prabhune, Linda S. Schadler, L. Catherine Brinson, Wei Chen

    With an unprecedented combination of mechanical and electrical properties, polymer nanocomposites have the potential to be widely used across multiple industries. Tailoring nanocomposites to meet application specific requirements remains a challenging task, owing to the vast, mixed-variable design space that includes composition (i.e. choice of polymer, nanoparticle, and surface modification) and microstructures (i.e. dispersion and geometric arrangement of particles) of the nanocomposite material. Modeling properties of the interphase, the region surrounding a nanoparticle, introduces additional complexity to the design process and requires computationally expensive simulations. As a result, previous attempts at designing polymer nanocomposites have focused on finding the optimal microstructure for only a fixed combination of constituents. In this article, we propose a data centric design framework to concurrently identify optimal composition and microstructure using mixed-variable Bayesian optimization. This framework integrates experimental data with state-of-the-art techniques in interphase modeling, microstructure characterization and reconstructions and machine learning. Latent variable Gaussian processes (LVGPs) quantifies the lack-of-data uncertainty over the mixed-variable design space that consists of qualitative and quantitative material design variables. The design of electrically insulating nanocomposites is cast as a multicriteria optimization problem with the goal of maximizing dielectric breakdown strength while minimizing dielectric permittivity and dielectric loss. Within tens of simulations, our method identifies a diverse set of designs on the Pareto frontier indicating the tradeoff between dielectric properties. These findings project data centric design, effectively integrating experimental data with simulations for Bayesian Optimization, as an effective approach for design of engineered material systems.


  • Integration of Normative Decision-Making and Batch Sampling for Global Metamodeling

    by Anton van Beek, Siyu Tao, Matthew Plumlee, Daniel W. Apley, Wei Chen

    The cost of adaptive sampling for global metamodeling depends on the total number of costly function evaluations and to which degree these evaluations are performed in parallel. Conventionally, samples are taken through a greedy sampling strategy that is optimal for either a single sample or a handful of samples. The limitation of such an approach is that they compromise optimality when more samples are taken. In this paper, we propose a thrifty adaptive batch sampling (TABS) approach that maximizes a multistage reward function to find an optimal sampling policy containing the total number of sampling stages, the number of samples per stage, and the spatial location of each sample. Consequently, the first batch identified by TABS is optimal with respect to all potential future samples, the available resources, and is consistent with a modeler’s preference and risk attitude. Moreover, we propose two heuristic-based strategies that reduce numerical complexity with a minimal reduction in optimality. Through numerical examples, we show that TABS outperforms or is comparable with greedy sampling strategies. In short, TABS provides modelers with a flexible adaptive sampling tool for global metamodeling that effectively reduces sampling costs while maintaining prediction accuracy.


  • Top Cited Papers

    A Latent Variable Approach to Gaussian Process Modeling with Qualitative and Quantitative Factors

    by Yichi Zhang, Siyu Tao, Wei Chen, Daniel W. Apley

    Computer simulations often involve both qualitative and numerical inputs. Existing Gaussian process (GP) methods for handling this mainly assume a different response surface for each combination of levels of the qualitative factors and relate them via a multi-response cross-covariance matrix. We introduce a substantially different approach that maps each qualitative factor to underlying numerical latent variables (LVs), with the mapped values estimated similarly to the other correlation parameters, and then uses any standard GP covariance function for numerical variables. This provides a parsimonious GP parameterization that treats qualitative factors the same as numerical variables and views them as affecting the response via similar physical mechanisms. This has strong physical justification, as the effects of a qualitative factor in any physics-based simulation model must always be due to some underlying numerical variables. Even when the underlying variables are many, sufficient dimension reduction arguments imply that their effects can be represented by a low-dimensional LV. This conjecture is supported by the superior predictive performance observed across a variety of examples. Moreover, the mapped LVs provide substantial insight into the nature and effects of the qualitative factors. Supplementary materials for the paper are available online.