Dian Zhou
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
Research Subjects
Dian Zhou has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
- Xuan Zeng
Fudan University
35 shared publications - Changhao Yan
Fudan University, Shanghai, Shanghai, China
19 shared publications - Fan Yang
School of Microelectronics, Fudan University
18 shared publications - Zhaori Bi
Fudan University, Shanghai, Shanghai, China
17 shared publications - Jun Tao
State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China
7 shared publications - Jiangli Huang
Microelectronics Department, State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai, China
5 shared publications
Latest Publications
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP  (02780070) , 1
VSTherm: A Virtual Path-based Stochastic Solver for Full-Chip Leakage-Aware Nonlinear Thermal Simulation
The continuous advancement of semiconductor processes has led to increasingly prominent leakage power issues in integrated circuits (ICs), making leakage-aware nonlinear thermal simulation a critical challenge in modern chip design. Traditional deterministic field solvers provide high accuracy but suffer from significant computational inefficiencies when handling large-scale mesh structures. Conversely, stochastic methods offer rapid computation speeds but are inherently limited to single-point solutions, preventing them from effectively addressing nonlinear thermal problems. To address this challenge, we propose a virtual path-based stochastic solver that enables efficient leakage-aware thermal simulation. The virtual path algorithm decomposes each real path in Brownian motion into virtual paths, extending stochastic solvers from single-point solutions to regional solutions, allowing a stochastic method to achieve full-chip thermal simulation for the first time, thus enabling the handling of nonlinearity. Additionally, we further accelerate the iteration process by reusing the path trajectories from the first solution process. Extensive experimental evaluations demonstrate that our method achieves a speedup of 20.17× to 52.23× compared to the state-of-the-art solver 3D-ICE on 4 GPUs across various scenarios while maintaining comparable accuracy.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP  (02780070) , 1
VSTherm: A Virtual Path-based Stochastic Solver for Full-Chip Leakage-Aware Nonlinear Thermal Simulation
The continuous advancement of semiconductor processes has led to increasingly prominent leakage power issues in integrated circuits (ICs), making leakage-aware nonlinear thermal simulation a critical challenge in modern chip design. Traditional deterministic field solvers provide high accuracy but suffer from significant computational inefficiencies when handling large-scale mesh structures. Conversely, stochastic methods offer rapid computation speeds but are inherently limited to single-point solutions, preventing them from effectively addressing nonlinear thermal problems. To address this challenge, we propose a virtual path-based stochastic solver that enables efficient leakage-aware thermal simulation. The virtual path algorithm decomposes each real path in Brownian motion into virtual paths, extending stochastic solvers from single-point solutions to regional solutions, allowing a stochastic method to achieve full-chip thermal simulation for the first time, thus enabling the handling of nonlinearity. Additionally, we further accelerate the iteration process by reusing the path trajectories from the first solution process. Extensive experimental evaluations demonstrate that our method achieves a speedup of 20.17× to 52.23× compared to the state-of-the-art solver 3D-ICE on 4 GPUs across various scenarios while maintaining comparable accuracy.
- Open Access
- 17 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 31  (2) , 1-19
Variation-aware Analog Circuit Design via Contextual Modeling and Robust Optimization
Robust analog circuit design is becoming increasingly challenging due to process, voltage, and temperature (PVT) variations at advanced technology nodes. In this article, we formulate analog circuit synthesis as a robust optimization problem, and propose a Contextual Robust OptimiZAtion (CROZA) method for variation-aware analog circuit design. The proposed method uses Contextual Gaussian process to model both the design parameters and perturbation parameters, and a hybrid strategy of adversarially robust optimization and stochastically perturbed robust optimization to find robust solutions. Compared to state-of-the-art methods, our proposed approach achieves significant simulation and runtime speedups while delivering superior optimization results.
- 17 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 31  (2) , 1-19
Open AccessVariation-aware Analog Circuit Design via Contextual Modeling and Robust Optimization
Robust analog circuit design is becoming increasingly challenging due to process, voltage, and temperature (PVT) variations at advanced technology nodes. In this article, we formulate analog circuit synthesis as a robust optimization problem, and propose a Contextual Robust OptimiZAtion (CROZA) method for variation-aware analog circuit design. The proposed method uses Contextual Gaussian process to model both the design parameters and perturbation parameters, and a hybrid strategy of adversarially robust optimization and stochastically perturbed robust optimization to find robust solutions. Compared to state-of-the-art methods, our proposed approach achieves significant simulation and runtime speedups while delivering superior optimization results.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Components, Packaging and Manufacturing Technology
- Vol. 16  (2) , 351-364
An Accurate and Efficient Stochastic Solver for Transient Thermal Analysis With Mixed Boundary Conditions
Transient thermal analysis captures the high accuracy and time-varying temperature distribution of chip components. However, during the early thermal design iterations of 3D ICs and chiplets, time-consuming transient thermal simulations lead to prolonged waiting times for engineers. Existing widely adopted deterministic methods or innovative neural network-based methods face significant challenges in reducing the thermal simulation time when geometric structures change iteratively. With prior knowledge of the chip’s regions of interest, localized stochastic methods may present a promising solution. In this work, we propose a novel high-precision and efficient stochastic solver for transient thermal analysis of ICs, based on the probabilistic solution of the heat equation obtained from the Feynman- Kac formula. As a field solver for the heat equation, the proposed method adopts the spacetime walk-on-sphere (WOS) scheme and enhances it with the novel boundary treatment integrated to guarantee the accuracy of addressing mixed boundary conditions, particularly Robin boundary conditions. A time-dependent fixed random walk is also combined to handle heat-source regions. Experimental results show that the proposed solver maintains high accuracy with average absolute error within 0.27 K and maximum absolute error within 1 K, achieves a speedup of 26.8-211× at a single point compared to the 3D-ICE simulator of similar accuracy, has general geometry applicability as a field solver, and exhibits excellent parallel efficiency.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Components, Packaging and Manufacturing Technology
- Vol. 16  (2) , 351-364
An Accurate and Efficient Stochastic Solver for Transient Thermal Analysis With Mixed Boundary Conditions
Transient thermal analysis captures the high accuracy and time-varying temperature distribution of chip components. However, during the early thermal design iterations of 3D ICs and chiplets, time-consuming transient thermal simulations lead to prolonged waiting times for engineers. Existing widely adopted deterministic methods or innovative neural network-based methods face significant challenges in reducing the thermal simulation time when geometric structures change iteratively. With prior knowledge of the chip’s regions of interest, localized stochastic methods may present a promising solution. In this work, we propose a novel high-precision and efficient stochastic solver for transient thermal analysis of ICs, based on the probabilistic solution of the heat equation obtained from the Feynman- Kac formula. As a field solver for the heat equation, the proposed method adopts the spacetime walk-on-sphere (WOS) scheme and enhances it with the novel boundary treatment integrated to guarantee the accuracy of addressing mixed boundary conditions, particularly Robin boundary conditions. A time-dependent fixed random walk is also combined to handle heat-source regions. Experimental results show that the proposed solver maintains high accuracy with average absolute error within 0.27 K and maximum absolute error within 1 K, achieves a speedup of 26.8-211× at a single point compared to the 3D-ICE simulator of similar accuracy, has general geometry applicability as a field solver, and exhibits excellent parallel efficiency.
- Top Cited Papers
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45  (1) , 31-44
Atelier: An Automated Analog Circuit Design Framework via Multiple Large Language Model-Based Agents
This paper introduces Atelier, a large language model (LLM)-based framework for analog circuit design to address the issues of data scarcity and the substantial domain-specific knowledge required in this field. Atelier integrates general-purpose LLMs with a high-quality, compact knowledge base to fulfill the considerable knowledge requirements of analog circuit design, obviating the need for extensive domain-specific training or fine-tuning. The knowledge base is meticulously curated to be task-oriented and encapsulates critical information from pertinent literature within user-defined templates, leveraging the LLMs’ capabilities in text comprehension and summarization. The framework comprises several LLM agents, structured in a graph-of-thoughts architecture, with each agent specialized in a distinct task in analog circuit design, including circuit analysis, topology selection, topology modification, parameter tuning, and design decision. This collaborative multi-agent system, enriched with access to the compact knowledge base and advanced mechanisms such as self-reflection, backtracking, and tool integration, automates the analog circuit design process. It significantly enhances design quality and efficiency while ensuring interpretability. Experimental results highlight Atelier’s superiority over state-of-the-art black-box methods, general-purpose LLMs, and LLM-based methods, demonstrating notable improvements in success rates, design quality, and runtime.
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45  (1) , 31-44
Top Cited PapersAtelier: An Automated Analog Circuit Design Framework via Multiple Large Language Model-Based Agents
This paper introduces Atelier, a large language model (LLM)-based framework for analog circuit design to address the issues of data scarcity and the substantial domain-specific knowledge required in this field. Atelier integrates general-purpose LLMs with a high-quality, compact knowledge base to fulfill the considerable knowledge requirements of analog circuit design, obviating the need for extensive domain-specific training or fine-tuning. The knowledge base is meticulously curated to be task-oriented and encapsulates critical information from pertinent literature within user-defined templates, leveraging the LLMs’ capabilities in text comprehension and summarization. The framework comprises several LLM agents, structured in a graph-of-thoughts architecture, with each agent specialized in a distinct task in analog circuit design, including circuit analysis, topology selection, topology modification, parameter tuning, and design decision. This collaborative multi-agent system, enriched with access to the compact knowledge base and advanced mechanisms such as self-reflection, backtracking, and tool integration, automates the analog circuit design process. It significantly enhances design quality and efficiency while ensuring interpretability. Experimental results highlight Atelier’s superiority over state-of-the-art black-box methods, general-purpose LLMs, and LLM-based methods, demonstrating notable improvements in success rates, design quality, and runtime.
- 25 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 33  (1) , 140-153
An RISC-V PPA-Fusion Cooperative Optimization Framework Based on Hybrid Strategies
The optimization of RISC-V designs, encompassing both microarchitecture and CAD tool parameters, is a great challenge due to an extensive and high-dimensional search space. Conventional optimization methods, such as case-specific approaches and black-box optimization approaches, often fall short of addressing the diverse and complex nature of RISC-V designs. To achieve optimal results across various RISC-V designs, we propose the cooperative optimization framework (COF) that integrates multiple black-box optimizers, each specializing in different optimization problems. The COF introduces the landscape knowledge exchange mechanism (LKEM) to direct the optimizers to share their knowledge of the optimization problem. Moreover, the COF employs the dynamic computational resource allocation (DCRA) strategies to dynamically allocate computational resources to the optimizers. The DCRA strategies are guided by the optimizer efficiency evaluation (OEE) mechanism and a time series forecasting (TSF) model. The OEE provides real-time performance evaluations. The TSF model forecasts the optimization progress made by the optimizers, given the allocated computational resources. In our experiments, the COF reduced the cycle per instruction (CPI) of the Berkeley out-of-order machine (BOOM) by 15.36% and the power of Rocket-Chip by 12.84% without constraint violation compared to the respective initial designs.
- 25 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 33  (1) , 140-153
An RISC-V PPA-Fusion Cooperative Optimization Framework Based on Hybrid Strategies
The optimization of RISC-V designs, encompassing both microarchitecture and CAD tool parameters, is a great challenge due to an extensive and high-dimensional search space. Conventional optimization methods, such as case-specific approaches and black-box optimization approaches, often fall short of addressing the diverse and complex nature of RISC-V designs. To achieve optimal results across various RISC-V designs, we propose the cooperative optimization framework (COF) that integrates multiple black-box optimizers, each specializing in different optimization problems. The COF introduces the landscape knowledge exchange mechanism (LKEM) to direct the optimizers to share their knowledge of the optimization problem. Moreover, the COF employs the dynamic computational resource allocation (DCRA) strategies to dynamically allocate computational resources to the optimizers. The DCRA strategies are guided by the optimizer efficiency evaluation (OEE) mechanism and a time series forecasting (TSF) model. The OEE provides real-time performance evaluations. The TSF model forecasts the optimization progress made by the optimizers, given the allocated computational resources. In our experiments, the COF reduced the cycle per instruction (CPI) of the Berkeley out-of-order machine (BOOM) by 15.36% and the power of Rocket-Chip by 12.84% without constraint violation compared to the respective initial designs.
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Revisiting sensitivity-based analog sizing with derivative-aware Bayesian optimization and error-suppressed adjoint analysis
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessRevisiting sensitivity-based analog sizing with derivative-aware Bayesian optimization and error-suppressed adjoint analysis
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44  (4) , 1489-1502
pPIRW: An Efficient and Accurate Precalculation Path Integral Random Walk Solver for Steady-State Thermal Simulation With Robin Boundary Conditions
With the rapid increase of the transistor number in VLSI, rapidly rising power density and temperatures make heat dissipation a major challenge in IC design and manufacturing. However, conventional deterministic thermal analysis methods have difficulties in obtaining local temperature solutions efficiently, and the existing stochastic method is inaccurate when dealing with thermal analysis problems involving Robin boundary conditions (BCs). In this article, a highly parallelized path integral random walk (PIRW) solver is innovatively proposed for steady-state thermal analysis with mixed BCs, especially Robin BCs. The rigorous calculation of the local time and the Feynman-Kac functional$\hat {e}_{c}(t)$ are adopted to accurately handle Neumann and Robin BCs for the first time. Furthermore, based on the PIRW, we propose an accurate and microsecond-level precalculation PIRW (pPIRW) predictor, which precalculates time-consuming random walks, obtains temperatures by simple vector multiplication, and therefore is suitable for proactive thermal management. The pPIRW essentially calculates a partial inverse of large-scale matrices constructed from the finite difference-based compact thermal models (CTMs). Experimental results show that compared with 3D-ICE, the PIRW solver maintains high accuracy with a negligible error within$0.5~^{\circ }$ C, achieves$136\times $ –$209\times $ speedup and$8.53\times $ –$11.1\times $ storage space reduction with all three kinds of BCs, and decreases to$1\times $ –$1.53\times $ speedup for lacking the absorbing Dirichlet boundary. The pPIRW further has speed improvement of 2.5e$4\times $ –6.7e$6\times $ and memory reduction of$36.6\times $ –$42.5\times $ over PIRW without loss of accuracy. Integrated within a thermal management strategy, the pPIRW predictor can eliminate all thermal conflicts while maintaining the highest working frequency. Meanwhile, pPIRW achieves$29.2\times $ speedup and$634\times $ memory reduction over the CTM during the offline precalculation stage.- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44  (4) , 1489-1502
pPIRW: An Efficient and Accurate Precalculation Path Integral Random Walk Solver for Steady-State Thermal Simulation With Robin Boundary Conditions
With the rapid increase of the transistor number in VLSI, rapidly rising power density and temperatures make heat dissipation a major challenge in IC design and manufacturing. However, conventional deterministic thermal analysis methods have difficulties in obtaining local temperature solutions efficiently, and the existing stochastic method is inaccurate when dealing with thermal analysis problems involving Robin boundary conditions (BCs). In this article, a highly parallelized path integral random walk (PIRW) solver is innovatively proposed for steady-state thermal analysis with mixed BCs, especially Robin BCs. The rigorous calculation of the local time and the Feynman-Kac functional$\hat {e}_{c}(t)$ are adopted to accurately handle Neumann and Robin BCs for the first time. Furthermore, based on the PIRW, we propose an accurate and microsecond-level precalculation PIRW (pPIRW) predictor, which precalculates time-consuming random walks, obtains temperatures by simple vector multiplication, and therefore is suitable for proactive thermal management. The pPIRW essentially calculates a partial inverse of large-scale matrices constructed from the finite difference-based compact thermal models (CTMs). Experimental results show that compared with 3D-ICE, the PIRW solver maintains high accuracy with a negligible error within$0.5~^{\circ }$ C, achieves$136\times $ –$209\times $ speedup and$8.53\times $ –$11.1\times $ storage space reduction with all three kinds of BCs, and decreases to$1\times $ –$1.53\times $ speedup for lacking the absorbing Dirichlet boundary. The pPIRW further has speed improvement of 2.5e$4\times $ –6.7e$6\times $ and memory reduction of$36.6\times $ –$42.5\times $ over PIRW without loss of accuracy. Integrated within a thermal management strategy, the pPIRW predictor can eliminate all thermal conflicts while maintaining the highest working frequency. Meanwhile, pPIRW achieves$29.2\times $ speedup and$634\times $ memory reduction over the CTM during the offline precalculation stage.- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44  (3) , 1193-1198
ATOM: An Automatic Topology Synthesis Framework for Operational Amplifiers
Bayesian optimization (BO) is more efficient in automatically synthesizing operational amplifier (opamp) topologies compared to conventional methods. However, the design space for behavior-level opamp topologies involves numerous connections that are difficult to comprehend, and evaluating each topology incurs substantial computational costs. To tackle these challenges, this brief introduces ATOM, an automatic opamp topology synthesis framework. We construct a concise design space for behavior-level opamp topologies, consisting of topologies that designers can easily understand. We propose an opamp topology optimization method that incorporates freeze-thaw BO. This method efficiently explores the design space and expedites the evaluation process. Experimental studies demonstrate that ATOM outperforms state-of-the-art topology synthesis methods in terms of success rate and optimization results while reducing the number of required simulations by up to 8.15 times. The source code for ATOM is available at https://github.com/Jinyi-Shen/ATOM.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44  (3) , 1193-1198
ATOM: An Automatic Topology Synthesis Framework for Operational Amplifiers
Bayesian optimization (BO) is more efficient in automatically synthesizing operational amplifier (opamp) topologies compared to conventional methods. However, the design space for behavior-level opamp topologies involves numerous connections that are difficult to comprehend, and evaluating each topology incurs substantial computational costs. To tackle these challenges, this brief introduces ATOM, an automatic opamp topology synthesis framework. We construct a concise design space for behavior-level opamp topologies, consisting of topologies that designers can easily understand. We propose an opamp topology optimization method that incorporates freeze-thaw BO. This method efficiently explores the design space and expedites the evaluation process. Experimental studies demonstrate that ATOM outperforms state-of-the-art topology synthesis methods in terms of success rate and optimization results while reducing the number of required simulations by up to 8.15 times. The source code for ATOM is available at https://github.com/Jinyi-Shen/ATOM.
- 6 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44  (3) , 818-831
VTSMOC: An Efficient Voronoi Tree Search Boosted Multiobjective Bayesian Optimization With Constraints for High-Dimensional Analog Circuit Synthesis
Optimizing multiple competitive black-box objectives with tight constraints poses a common challenge in analog circuit design. Multiobjective Bayesian optimization (MOBO) is a sample-efficient approach to identify the optimal tradeoffs, namely, the Pareto front (PF). However, existing MOBO methods exhibit limitations in handling high-dimensional design space, large sample budgets, many objectives and tight constraints. This article introduces VTSMOC, a sample-efficient and computationally lightweight approach for addressing high-dimensional constrained multiobjective optimization problems. VTSMOC decomposes the design space into Voronoi cells, dynamically constructing a hierarchical Voronoi tree through clustering observations with dominance relationships. Promising leaf nodes in the Voronoi tree are pinpointed by traversing the tree with gradient bandit. The diversity of PF is ensured by parallel sampling within different promising cells, selected using a diffusive strategy. We also propose the expected PF improvement (EPFI) and probability of PF improvement (PPFI) acquisition functions to facilitate the PF efficiently along the radial direction of PF surface. Compared to state-of-the-art methods, VTSMOC achieves significant improvements in both sample and computational efficiency.
- 6 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44  (3) , 818-831
VTSMOC: An Efficient Voronoi Tree Search Boosted Multiobjective Bayesian Optimization With Constraints for High-Dimensional Analog Circuit Synthesis
Optimizing multiple competitive black-box objectives with tight constraints poses a common challenge in analog circuit design. Multiobjective Bayesian optimization (MOBO) is a sample-efficient approach to identify the optimal tradeoffs, namely, the Pareto front (PF). However, existing MOBO methods exhibit limitations in handling high-dimensional design space, large sample budgets, many objectives and tight constraints. This article introduces VTSMOC, a sample-efficient and computationally lightweight approach for addressing high-dimensional constrained multiobjective optimization problems. VTSMOC decomposes the design space into Voronoi cells, dynamically constructing a hierarchical Voronoi tree through clustering observations with dominance relationships. Promising leaf nodes in the Voronoi tree are pinpointed by traversing the tree with gradient bandit. The diversity of PF is ensured by parallel sampling within different promising cells, selected using a diffusive strategy. We also propose the expected PF improvement (EPFI) and probability of PF improvement (PPFI) acquisition functions to facilitate the PF efficiently along the radial direction of PF surface. Compared to state-of-the-art methods, VTSMOC achieves significant improvements in both sample and computational efficiency.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
HiMOSS: A Novel High-dimensional Multi-objective Optimization Method via Adaptive Gradient-Based Subspace Sampling for Analog Circuit Sizing
This study presents a novel high-dimensional multi-objective optimization method via adaptive gradient-based subspace sampling for analog circuit sizing. To handle constrained multi-objective optimization, we exploit promising regions from a non-crowded Pareto front, with lightweight Bayesian optimization (BO) based on a novel approximate constrained expected hypervolume improvement. This lightweight BO is computational efficient with constant complexity concerning simulation numbers. To tackle high-dimensional challenges, we reduce the effective dimensionality around promising regions by sampling candidates in an adaptive subspace. The subspace is constructed with gradients and previous success steps with their significance decaying over iterations. The gradients are approximated by sparse regression without additional simulations. The experiments on synthetic benchmarks and analog circuits illustrate advantages of the proposed method over Bayesian and evolutionary baselines.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessHiMOSS: A Novel High-dimensional Multi-objective Optimization Method via Adaptive Gradient-Based Subspace Sampling for Analog Circuit Sizing
This study presents a novel high-dimensional multi-objective optimization method via adaptive gradient-based subspace sampling for analog circuit sizing. To handle constrained multi-objective optimization, we exploit promising regions from a non-crowded Pareto front, with lightweight Bayesian optimization (BO) based on a novel approximate constrained expected hypervolume improvement. This lightweight BO is computational efficient with constant complexity concerning simulation numbers. To tackle high-dimensional challenges, we reduce the effective dimensionality around promising regions by sampling candidates in an adaptive subspace. The subspace is constructed with gradients and previous success steps with their significance decaying over iterations. The gradients are approximated by sparse regression without additional simulations. The experiments on synthetic benchmarks and analog circuits illustrate advantages of the proposed method over Bayesian and evolutionary baselines.