Search NASA⌕ Search

SEARCH · Search NASA

Results for “evolutionary algorithms”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7

Evolutionary Computational Methods for Identifying Emergent Behavior in Autonomous Systems

A technique based on Evolutionary Computational Methods (ECMs) was developed that allows for the automated optimization of complex computationally modeled systems, such as autonomous systems. The primary technology, which enables the ECM to find optimal solutions in complex search spaces, derives from evolutionary algorithms such as the genetic algorithm and differential evolution. These methods are based on biological processes, particularly genetics, and define an iterative process that evolves parameter sets into an optimum. Evolutionary computation is a method that operates on a population of existing computational-based engineering models (or simulators) and competes them using biologically inspired genetic operators on large parallel cluster computers. The result is the ability to automatically find design optimizations and trades, and thereby greatly amplify the role of the system engineer.

Terrile, Richard J.↗

Using a Genetic Algorithm to Optimize Configurations in a Data-Driven Application

Users of highly-configurable software systems often want to optimize a particular objective such as improving a functional outcome or increasing system performance. One approach is to use an evolutionary algorithm. However, many applications today are data-driven, meaning they depend on inputs or data which can be complex and varied. Hence, a search needs to be run (and re-run) for all inputs, making optimization a heavy-weight and potentially impractical process. In this paper, we explore this issue on a data-driven highly-configurable scientific application. We build an exhaustive database containing 3,000 configurations and 10,000 inputs, leading to almost 100 million records as our oracle, and then run a genetic algorithm individually on each of the 10,000 inputs. We ask if (1) a genetic algorithm can find configurations to improve functional objectives; (2) whether patterns of best configurations over all input data emerge; and (3) if we can we use sampling to approximate the results. We find that the original (default) configuration is best only 34% of the time, while clear patterns emerge of other best configurations. Out of 3,000 possible configurations, only 112 distinct configurations achieve the optimal result at least once across all 10,000 inputs, suggesting the potential for lighter weight optimization approaches. We show that sampling of the input data finds similar patterns at a lower cost.

Sinha, Urjoshi↗

Genarris 2.0: A Random Structure Generator for Molecular Crystals

Genarris is an open source Python package for generating random molecular crystal structures with physical constraints for seeding crystal structure prediction algorithms and training machine learning models. Here we present a new version of the code, containing several major improvements. A MPI-based parallelization scheme has been implemented, which facilitates the seamless sequential execution of user-defined workflows. A new method for estimating the unit cell volume based on the single molecule structure has been developed using a machine-learned model trained on experimental structures. A new algorithm has been implemented for generating crystal structures with molecules occupying special Wyckoff positions. A new hierarchical structure check procedure has been developed to detect unphysical close contacts efficiently and accurately. New intermolecular distance settings have been implemented for strong hydrogen bonds. To demonstrate these new features, we study two specific cases: benzene and glycine. Genarris finds the experimental structures of the two polymorphs of benzene and the three polymorphs of glycine. Program summary Program Title: Genarris 2.0 Program Files doi: http://dx.doi.org/10.17632/grx6mz4pjn.1 Licensing provisions: BSD-3 Clause Programming language: Python, C External routines/libraries: Spglib, ASE, pymatgen, SciPy, mpi4py, scikit-learn, PyTorch, FHI-aims. Nature of problem: Molecular crystal structure prediction. Solution method: Genarris 2.0 generates molecular crystal structures over the 230 space groups, on general and special Wyckoff positions, using physical constraints. Down-sampling of the generated structures may be performed subsequently, based on molecular crystal packing descriptors and an unsupervised machine learning algorithm. Lastly, ab initio structure relaxation may be performed for the final pool. Depending on the user-defined workflow implemented, Genarris may be used to generate diverse molecular crystal datasets to seed evolutionary algorithms or to train machine learning algorithms or as a standalone crystal structure prediction method. Restrictions: For crystal structure generation, the molecule of interest must be semi-rigid with no bond rotational degrees of freedom. Unusual features: Genarris 2.0 is a highly distributed program, making use of MPI for Python parallelization. The user has the ability to design and implement workflows by executing a user-defined list of procedures. Genarris 2.0 offers new features including a machine learning model for estimating the molecular volume in the solid state from the single molecule structure, structure generation in special Wyckoff positions of space groups, hierarchical structure checks including rigorous treatment of non-orthogonal structures, and clustering and down-selection workflows combining first principles simulations with machine learning. (C) 2020 Elsevier B.V. All rights reserved.

Crystal structure prediction↗

Uncovering Hazards Using a Multi-Objective Optimization to Explore the Faulty State-Space

Considering resilience when designing complex engineered systems is crucial to ensure the system is safe under unexpected hazardous scenarios. Traditional risk-based approaches, such as Failure Modes and Effects Analysis (FMEA) are useful for designing the system to mitigate hazardous scenarios that can be identified by the designer, but often require experience or prior knowledge of system failures to generate. More recently, researchers have developed simulation tools that enable the designer to model large sets of hazardous scenarios (driven by both internal faults and external factors) through simulation. While these tools enable a wider scope of fault modes to be evaluated (e.g., by injecting combined set of fault modes or injecting modes at different times), the resulting assessments (like FMEA) still require knowledge of the specific modes to be evaluated. However, failure to analyze a wide variety of fault scenarios can lead to an incomplete picture of the system resilience, especially to "surprise events'' which may be difficult for the designer to identify and predict beforehand. To overcome this challenge, previous work developed a fault sampling approach for resilience simulations which would procedurally-generate a wide variety of potential faults by systematically perturbing the health states of the system. While the resulting fault modes generated covered a much larger space hazards than would be otherwise considered (and identified many unique failure trajectories which would not have otherwise been identified), it also significantly increased the computational cost of the analysis and resulted in the simulation and analysis of a large set of essentially duplicate scenarios. Additionally, as the number of dimensions in the faulty state-space increases, the full elaboration of possible modes becomes computationally infeasible, justifying the use of a more targeted search. To resolve this limitation, this work proposes the use of a multiobjective optimization algorithm to search the health state space for potential fault modes that are both (1) hazardous and (2) unique. To solve this type of problem, this work proposes the use of a cooperative co-evolutionary algorithm. To demonstrate this approach, it will be applied to a model of an autonomous rover which uses line markings to navigate, focusing on potential hazards in the drive system which could cause the rover to crash. To determine the merit of the approach, it will further be compared with the previously-presented range elaboration approach and a random mode generation approach on the basis of computational efficiency and found modes.

Resilience↗

Evolutionary Computing for Low-thrust Navigation

The development of new mission concepts requires efficient methodologies to analyze, design and simulate the concepts before implementation. New mission concepts are increasingly considering the use of ion thrusters for fuel-efficient navigation in deep space. This paper presents parallel, evolutionary computing methods to design trajectories of spacecraft propelled by ion thrusters and to assess the trade-off between delivered payload mass and required flight time. The developed methods utilize a distributed computing environment in order to speed up computation, and use evolutionary algorithms to find globally Pareto-optimal solutions. The methods are coupled with two main traditional trajectory design approaches, which are called direct and indirect. In the direct approach, thrust control is discretized in either arc time or arc length, and the resulting discrete thrust vectors are optimized. In the indirect approach, a thrust control problem is transformed into a costate control problem, and the initial values of the costate vector are optimized. The developed methods are applied to two problems: 1) an orbit transfer around the Earth and 2) a transfer between two distance retrograde orbits around Europa, the closest to Jupiter of the icy Galilean moons. The optimal solutions found with the present methods are comparable to other state-of-the-art trajectory optimizers and to analytical approximations for optimal transfers, while the required computational time is several orders of magnitude shorter than other optimizers thanks to an intelligent design of control vector discretization, advanced algorithmic parameterization, and parallel computing.

optimization↗

Low Power Hardware-In-The-Loop Neuromorphic Training Accelerator

The training process for spiking neural networks can be very computationally intensive. Approaches such as evolutionary algorithms may require evaluating thousands or millions of candidate solutions. In this work, we propose using neuromorphic cores implemented on a Xilinx Zynq system on chip to accelerate and improve the energy efficiency of the evaluation step of an evolutionary training approach. We demonstrate this can significantly reduce the required energy to evolve a network with some cases showing greater than 10 times improvement as compared to a CPU-only system.

Mitchell, Parker↗

WE-EF-207-01: FEATURED PRESENTATION and BEST IN PHYSICS (IMAGING): Task-Driven Imaging for Cone-Beam CT in Interventional Guidance

Purpose: This work introduces a task-driven imaging framework that utilizes a patient-specific anatomical model, mathematical definition of the imaging task, and a model of the imaging system to prospectively design acquisition and reconstruction techniques that maximize task-based imaging performance. Utility of the framework is demonstrated in the joint optimization of tube current modulation and view-dependent reconstruction kernel in filtered-backprojection reconstruction and non-circular orbit design in model-based reconstruction. Methods: The system model is based on a cascaded systems analysis of cone-beam CT capable of predicting the spatially varying noise and resolution characteristics as a function of the anatomical model and a wide range of imaging parameters. Detectability index for a non-prewhitening observer model is used as the objective function in a task-driven optimization. The combination of tube current and reconstruction kernel modulation profiles were identified through an alternating optimization algorithm where tube current was updated analytically followed by a gradient-based optimization of reconstruction kernel. The non-circular orbit is first parameterized as a linear combination of bases functions and the coefficients were then optimized using an evolutionary algorithm. The task-driven strategy was compared with conventional acquisitions without modulation, using automatic exposure control, and in a circular orbit. Results: The task-driven strategy outperformed conventional techniques in all tasks investigated, improving the detectability of a spherical lesion detection task by an average of 50% in the interior of a pelvis phantom. The non-circular orbit design successfully mitigated photon starvation effects arising from a dense embolization coil in a head phantom, improving the conspicuity of an intracranial hemorrhage proximal to the coil. Conclusion: The task-driven imaging framework leverages a knowledge of the imaging task within a patient-specific anatomical model to optimize image acquisition and reconstruction techniques, thereby improving imaging performance beyond that achievable with conventional approaches. 2R01-CA-112163; R01-EB-017226; U01-EB-018758; Siemens Healthcare (Forcheim, Germany)

60 APPLIED LIFE SCIENCES↗

An Optimizing Space Data-Communications Scheduling Method and Algorithm with Interference Mitigation, Generalized for a Broad Class of Optimization Problems

NASA's space data-communications infrastructure-the Space Network and the Ground Network-provide scheduled (as well as some limited types of unscheduled) data-communications services to user spacecraft. The Space Network operates several orbiting geostationary platforms (the Tracking and Data Relay Satellite System (TDRSS)), each with its own servicedelivery antennas onboard. The Ground Network operates service-delivery antennas at ground stations located around the world. Together, these networks enable data transfer between user spacecraft and their mission control centers on Earth. Scheduling data-communications events for spacecraft that use the NASA communications infrastructure-the relay satellites and the ground stations-can be accomplished today with software having an operational heritage dating from the 1980s or earlier. An implementation of the scheduling methods and algorithms disclosed and formally specified herein will produce globally optimized schedules with not only optimized service delivery by the space data-communications infrastructure but also optimized satisfaction of all user requirements and prescribed constraints, including radio frequency interference (RFI) constraints. Evolutionary algorithms, a class of probabilistic strategies for searching large solution spaces, is the essential technology invoked and exploited in this disclosure. Also disclosed are secondary methods and algorithms for optimizing the execution efficiency of the schedule-generation algorithms themselves. The scheduling methods and algorithms as presented are adaptable to accommodate the complexity of scheduling the civilian and/or military data-communications infrastructure within the expected range of future users and space- or ground-based service-delivery assets. Finally, the problem itself, and the methods and algorithms, are generalized and specified formally. The generalized methods and algorithms are applicable to a very broad class of combinatorial-optimization problems that encompasses, among many others, the problem of generating optimal space-data communications schedules.

ground stations↗

Evolutionary inverse design of defects at graphene 2D lateral interfaces

Grain boundaries (GBs) in two-dimensional (2D) materials often have a profound impact on various material properties from mechanical to optical to electronic, yet predicting all possible GB formations is a challenge. Here, we introduce a workflow based on an evolutionary algorithm for exploring possible GBs formed at a lateral 2D interface. In a departure from conventional genetic algorithm based structure optimization methods, we perform genetic operations in the near interface region that allow us to be computationally efficient. We benchmark our method using graphene, which is a well-studied 2D material with a wide range of point defects. An empirical potential was used as the surrogate of the evolutionary search. More than 11.5 × 106 structures in total were evaluated for 128 GB orientations, and for each orientation, the ten best structures are recorded. A subset of low energy GBs predicted by empirical potential based search was relaxed by first-principles calculations and used to validate the energetic rank order. With the validated formation energy, we rank-ordered the best 128 GB structures and performed a detailed statistical analysis of primitive rings to find the correlation between the ring distribution and the formation energy. We found that for low energy GBs (below 0.5eV/Å), Stone–Wales defects will dominate, while structures with a higher energy (0.5–1.1eV/Å) show an increasing population of heptagons and nine-membered rings to form seven-nine defect pairs. For structures with energy higher than 1.1eV/Å, the percentage of octagons and nine-membered rings increases, which indicates that these two types of rings are not energetically favorable. Our proposed methodology is broadly applicable to explore defective low dimensional materials and represents a powerful tool that enables a systematic search of GBs of lateral interfaces for 2D materials.

Zhang, Jianan↗

Parallel general purpose multiobjective optimization framework with application to electron beam dynamics

Particle accelerators are invaluable tools for research in the basic and applied sciences, such as materials science, chemistry, the biosciences, particle physics, nuclear physics and medicine. The design, commissioning, and operation of accelerator facilities is a nontrivial task, due to the large number of control parameters and the complex interplay of several conflicting design goals. The Argonne Wakefield Accelerator facility has some unique challenges resulting from its purpose to carry out advanced accelerator R&D. Individual experiments often have challenging beam requirements, and the physical configuration of the beam lines is often changed to accommodate the variety of supported experiments. The need for rapid deployment of different operational settings further complicates the optimization work that must be done for multiple constraints and challenging operational regimes. One example of this is an independently staged two-beam acceleration experiment which requires the construction of an additional beam line (this is now in progress). The high charge drive beam, well into the space charge regime, must be threaded through small aperture (17.6 mm) decelerating structures. In addition, the bunch length must be sufficiently short to maximize power generation in the decelerator. We propose to tackle this problem by means of multiobjective optimization algorithms which also facilitate a parallel deployment. In order to compute solutions in a meaningful time frame, a fast and scalable software framework is required. In this paper, we present a general-purpose framework for simulation-based multiobjective optimization methods that allows the automatic investigation of optimal sets of machine parameters. Using evolutionary algorithms as the optimizer and opal as the forward solver, validation experiments and results of multiobjective optimization problems in the domain of beam dynamics are presented. Optimized solutions for the new high charge drive beam line found by the framework were used to finish the design of a two beam acceleration experiment. The selected solution along with the associated beam parameters is presented.

43 PARTICLE ACCELERATORS↗

Evolutionary Based Techniques for Fault Tolerant Field Programmable Gate Arrays

The use of SRAM-based Field Programmable Gate Arrays (FPGAs) is becoming more and more prevalent in space applications. Commercial-grade FPGAs are potentially susceptible to permanently debilitating Single-Event Latchups (SELs). Repair methods based on Evolutionary Algorithms may be applied to FPGA circuits to enable successful fault recovery. This paper presents the experimental results of applying such methods to repair four commonly used circuits (quadrature decoder, 3-by-3-bit multiplier, 3-by-3-bit adder, 440-7 decoder) into which a number of simulated faults have been introduced. The results suggest that evolutionary repair techniques can improve the process of fault recovery when used instead of or as a supplement to Triple Modular Redundancy (TMR), which is currently the predominant method for mitigating FPGA faults.

Larchev, Gregory V.↗

A Mixed Integer Efficient Global Optimization Algorithm with Multiple Infill Strategy - Applied to a Wing Topology Optimization Problem

With the advancement in high performance computing and numerical optimization techniques,engineering design optimization problems are becoming more complex, larger scale,higher fidelity, and computationally more demanding, requiring longer run times than ever before. There exists methodologies and techniques that can address some of these challenges but very few can address all, and most are limited in the extent that these concerns can be addressed. With the goal of addressing such challenging engineering problems, we developed anew optimization framework, named AMIEGO, that combines concepts from surrogate-based optimization approaches, gradient-based numerical methods, Partial Least Squares, evolutionary algorithms, and Branch-and-Bound, providing newer capabilities that were not previouslyperceived. However, the original version of this framework, in the process of adaptive samplingto explore and exploit the design space, finds only a single sample point per iteration. The efforthere builds upon this previously developed optimization framework to include multiple infillsampling capability that combines the concept of generalized expected improvement function,unsupervised learning, and multi-objective evolutionary technique. To demonstrate, AMIEGOwith the multiple infill capability (called AMIEGO-MIMOS) solves a series of increasingly difficultengineering design optimization problems. The results reveal the performance of the newapproach is problem dependent. When applied to a ten-bar truss problem, the newly proposedmultiple infill strategy consistently leads to a better design solutions when compared to theexisting CPTV method (implemented with the context of the AMIEGO framework). On theother hand, when applied to a mixed-integer high fidelity wing topology optimization problem- MIMOS, despite showing a steeper convergence at the start, eventually leads to an inferiorsolution as compared to CPTV approach. These results also reveal that a small number ofstarting points, in general, are sufficient to lead to a good overall solution.

Mixed-integer optimization↗

Toward Evolvable Hardware Chips: Experiments with a Programmable Transistor Array

Evolvable Hardware is reconfigurable hardware that self-configures under the control of an evolutionary algorithm. We search for a hardware configuration can be performed using software models or, faster and more accurate, directly in reconfigurable hardware. Several experiments have demonstrated the possibility to automatically synthesize both digital and analog circuits. The paper introduces an approach to automated synthesis of CMOS circuits, based on evolution on a Programmable Transistor Array (PTA). The approach is illustrated with a software experiment showing evolutionary synthesis of a circuit with a desired DC characteristic. A hardware implementation of a test PTA chip is then described, and the same evolutionary experiment is performed on the chip demonstrating circuit synthesis/self-configuration directly in hardware.

Stoica, Adrian↗

Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators

This work evaluates different optimization algorithms for computational fluid dynamics (CFD) simulations of engine combustion. Due to the computational expense of CFD simulations, emulators built with machine learning algorithms were used as surrogates for the optimizers. Two types of emulators were used: a Gaussian process (GP) and a weighted variety of machine learning methods called SuperLearner (SL). The emulators were trained using a dataset of 2048 CFD simulations that were run concurrently on a supercomputer. The design of experiments (DOE) for the CFD runs was obtained by perturbing nine input parameters using a Monte-Carlo method. The CFD simulations were of a heavy duty engine running with a low octane gasoline-like fuel at a partially premixed compression ignition mode. Ten optimization algorithms were tested, including types typically used in research applications. Each optimizer was allowed 800 function evaluations and was randomly tested 100 times. The optimizers were evaluated for the median, minimum, and maximum merits obtained in the 100 attempts. Some optimizers required more sequential evaluations, thereby resulting in longer wall clock times to reach an optimum. The best performing optimization methods were particle swarm optimization (PSO), differential evolution (DE), GENOUD (an evolutionary algorithm), and micro-genetic algorithm (GA). These methods found a high median optimum as well as a reasonable minimum optimum of the 100 trials. Moreover, all of these methods were able to operate with less than 100 successive iterations, which reduced the wall clock time required in practice. Two methods were found to be effective but required a much larger number of successive iterations: the DIRECT and MALSCHAINS algorithms. A random search method that completed in a single iteration performed poorly in finding optimum designs but was included to illustrate the limitation of highly concurrent search methods. The last three methods, Nelder–Mead, bound optimization by quadratic approximation (BOBYQA), and constrained optimization by linear approximation (COBYLA), did not perform as well.

Probst, Daniel M.↗

Using Generative Representations to Evolve Robots

Recent research has demonstrated the ability of evolutionary algorithms to automatically design both the physical structure and software controller of real physical robots. One of the challenges for these automated design systems is to improve their ability to scale to the high complexities found in real-world problems. Here we claim that for automated design systems to scale in complexity they must use a representation which allows for the hierarchical creation and reuse of modules, which we call a generative representation. Not only is the ability to reuse modules necessary for functional scalability, but it is also valuable for improving efficiency in testing and construction. We then describe an evolutionary design system with a generative representation capable of hierarchical modularity and demonstrate it for the design of locomoting robots in simulation. Finally, results from our experiments show that evolution with our generative representation produces better robots than those evolved with a non-generative representation.

Hornby, Gregory S.↗

Benchmarking the Performance of Neuromorphic and Spiking Neural Network Simulators

Software simulators play a critical role in the development of new algorithms and system architectures in any field of engineering. Neuromorphic computing, which has shown potential in building brain-inspired energy-efficient hardware, suffers a slow-down in the development cycle due to a lack of flexible and easy-to-use simulators of either neuromorphic hardware itself or of spiking neural networks (SNNs), the type of neural network computation executed on most neuromorphic systems. While there are several openly available neuromorphic or SNN simulation packages developed by a variety of research groups, they have mostly targeted computational neuroscience simulations, and only a few have targeted small-scale machine learning tasks with SNNs. Evaluations or comparisons of these simulators have often targeted computational neuroscience-style workloads. In this work, we seek to evaluate the performance of several publicly available SNN simulators with respect to non-computational neuroscience workloads, in terms of speed, flexibility, and scalability. We evaluate the performance of the NEST, Brian2, Brian2GeNN, BindsNET and Nengo packages under a common front-end neuromorphic framework. Our evaluation tasks include a variety of different network architectures and workload types to mimic the computation common in different algorithms, including feed-forward network inference, genetic algorithms, and reservoir computing. We also study the scalability of each of these simulators when running on different computing hardware, from single core CPU workstations to multi-node supercomputers. Our results show that the BindsNET simulator has the best speed and scalability for most of the SNN workloads (sparse, dense, and layered SNN architectures) on a single core CPU. However, when comparing the simulators leveraging the GPU capabilities, Brian2GeNN outperforms the others for these workloads in terms of scalability. NEST performs the best for small sparse networks and is also the most flexible simulator in terms of reconfiguration capability NEST shows a speedup of at least 2x compared to the other packages when running evolutionary algorithms for SNNs. The multi-node and multi-thread capabilities of NEST show at least 2x speedup compared to the rest of the simulators (single core CPU or GPU based simulators) for large and sparse networks. We conclude our work by providing a set of recommendations on the suitability of employing these simulators for different tasks and scales of operations. We also present the characteristics for a future generic ideal SNN simulator for different neuromorphic computing workloads.

97 MATHEMATICS AND COMPUTING↗

Sequence-defined Pareto frontier of a copolymer structure

The correlations between the sequence of monomers in a macromolecule and its three-dimensional (3D) structure is a grand challenge in polymer science. The properties and functions of macromolecules depend on their 3D shape that has appeared to be dictated by their monomer sequence. However, the progress towards understanding the sequence–structure-property correlations and their utilization in materials engineering are slow because it is almost impossible to characterize an astronomically large number of possible sequences of a copolymer using traditional experimental and simulation methods. To address this problem, here, we combine evolutionary computing and coarse-grained molecular dynamics (CGMD) simulation and study the sequence-structure correlations of a model AB-type copolymer in a solution and assess the impact of sequence on the packing density in its bulk phase. The CGMD-based evolutionary algorithm (EA) screens the sequence space of a single chain copolymer efficiently and identifies a wide range of single-molecule structures including extremal radii of gyration. The data are utilized to estimate the Pareto front of the structure-space of a binary copolymer as a function of its composition. The monomer packings in single-molecule solution phase and multimolecular bulk phase are found to be identical. Finally, this work highlights the opportunities of sequence-specific control of macromolecular structure for designing target materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Toward Consistent High-Fidelity Quantum Learning on Unstable Devices via Efficient In-Situ Calibration

In the near-term noisy intermediate-scale quantum (NISQ) era, high noise will significantly reduce the fidelity of quantum computing. What's worse, recent works reveal that the noise on quantum devices is not stable, that is, the noise is dynamically changing over time. This leads to an imminent challenging problem: At run-time, is there a way to efficiently achieve a consistent high-fidelity quantum system on unstable devices? To study this problem, we take quantum learning (a.k.a., variational quantum algorithm) as a vehicle, which has a wide range of applications, such as combinatorial optimization and machine learning. A straightforward approach is to optimize a variational quantum circuit (VQC) with a parameter-shift approach on the target quantum device before using it; however, the optimization has an extremely high time cost, which is not practical at run-time. To address the pressing issue, in this paper, we proposed a novel quantum pulse-based noise adaptation framework, namely QuPAD. In the proposed framework, first, we identify that the CNOT gate is the fidelity bottleneck of the conventional VQC, and we employ a more robust parameterized multi-qubit gate (i.e., Rzx gate) to replace CNOT gate. Second, by benchmarking Rzx gate with different parameters, we build a fitting function for each coupling qubit pair, such that the deviation between the theoretic output of Rzx gate and its on-device output under a given pulse amplitude and duration can be efficiently predicted. On top of this, an evolutionary algorithm is devised to identify the pulse amplitude and duration of each Rzx gate (i.e., calibration) and find the quantum circuits with high fidelity. Experiments show that the runtime on quantum devices of QuPAD with 8–10 qubits is less than 15 minutes, which is up to 270 x faster than the parameter-shift approach. In addition, compared to the vanilla VQC as a baseline, QuPAD can achieve 59.33% accuracy gain on a classification task, and average 66.34% closer to ground state energy for molecular simulation.

Hu, Zhirui↗