arXiv subjects

Marwa H. Farag

Publications and source records attributed to Marwa H. Farag.

7 recordsLinked to original sources

arXiv2026

Learning to Prepare Molecular Ground States with Transformer Models

Quantum state preparation is a key component of many quantum algorithms. Performing this step efficiently is essential for realizing practical quantum advantage in quantum chemistry applications. Iterative algorithms like ADAPT-VQE can produce shallow ground-state preparation circuits, but become computationally prohibitive for the larger molecules relevant to materials science and pharmaceutical development. Here, we introduce ADAPT-GQE, a generative AI framework that learns to synthesize ground-state preparation circuits for electronic structure calculations. We first use ADAPT-VQE to generate high-quality reference circuits, which are then used as targets for training models for circuit generation. Once trained, the model can efficiently propose and score circuits, enabling reinforcement learning (RL) to drive circuit generation accuracy beyond the accuracy of the ADAPT-VQE training data. This pipeline achieves order-of-magnitude reductions in circuit generation time relative to ADAPT-VQE while maintaining comparable or improved state-preparation accuracy. We demonstrate ADAPT-GQE on imipramine, a well-established tricyclic antidepressant that serves as a representative, challenging target for computational modelling in drug stability protocols. We execute generated circuits on Quantinuum Helios-1, representing a milestone for AI-generated quantum chemistry circuits on state-of-the-art quantum hardware. These results establish a pathway toward automated quantum circuit synthesis for utility-scale quantum computational chemistry.

quant-ph↗

arXiv2025

Artificial Intelligence for Quantum Computing

Artificial intelligence (AI) advancements over the past few years have had an unprecedented and revolutionary impact across everyday application areas. Its significance also extends to technical challenges within science and engineering, including the nascent field of quantum computing (QC). The counterintuitive nature and high-dimensional mathematics of QC make it a prime candidate for AI's data-driven learning capabilities, and in fact, many of QC's biggest scaling challenges may ultimately rest on developments in AI. However, bringing leading techniques from AI to QC requires drawing on disparate expertise from arguably two of the most advanced and esoteric areas of computer science. Here we aim to encourage this cross-pollination by reviewing how state-of-the-art AI techniques are already advancing challenges across the hardware and software stack needed to develop useful QC - from device design to applications. We then close by examining its future opportunities and obstacles in this space.

quant-ph↗

arXiv2025

Quantum simulation of CO$_2$ chemisorption in an amine-functionalized metal-organic framework

We perform a series of calculations using simulated QPUs, accelerated by the NVIDIA CUDA-Q platform, focusing on a molecular analog of an amine-functionalized metal-organic framework (MOF), a promising class of materials for CO$_2$ capture. The variational quantum eigensolver (VQE) technique is employed, utilizing both the unitary coupled-cluster method with singles and doubles (UCCSD) and adaptive ansätze within active spaces extracted from the larger material system. We explore active spaces of (6e,6o), (8e,8o), and (10e,10o), corresponding to 12, 16, and 20 qubits, respectively, and simulate them using CUDA-Q's GPU-accelerated state-vector simulator. Gate fusion is shown to decrease circuit evaluation time by 2-3$\times$, while parameter shift decreases the number of epochs required for variational convergence. The ADAPT-VQE method decreases both the number of epochs required for convergence and reduces the number of circuit parameters across all active spaces, at the cost of an increased number of circuit evaluations. Combining ADAPT-VQE with the 1- and 2-electron integrals from a CASSCF calculation recovers more correlation energy, at the cost of increased computational time. The CO$_2$ binding energy is computed, and we observe and discuss how increasing the active space size can lead to uneven recovery of correlation energy, making the predicted binding energies variable, even positive (\textit{i.e.}, energetically unfavorable) in some instances. This can be partially remedied by using an alternative approach to computing the binding energy that more evenly spreads the active space. This work explores the application of VQE to a novel material system using simulated QPUs and provides some insight into various consideration when performing these types of calculations, ultimately highlighting the challenges of studying chemisorption on near-term quantum machines.

physics.chem-ph↗

arXiv2025

A Hybrid Transformer Architecture with a Quantized Self-Attention Mechanism Applied to Molecular Generation

The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing computational overhead. Self-attention integrates learnable query and key matrices to calculate attention scores between all pairs of tokens in a sequence. These scores are then multiplied by a learnable value matrix to obtain the output self-attention matrix, enabling the model to effectively capture long-range dependencies within the input sequence. Here, we propose a hybrid quantum-classical self-attention mechanism as part of a transformer decoder, the architecture underlying large language models (LLMs). To demonstrate its utility in chemistry, we train this model on the QM9 dataset for conditional generation, using SMILES strings as input, each labeled with a set of physicochemical properties that serve as conditions during inference. Our theoretical analysis shows that the time complexity of the query-key dot product is reduced from $\mathcal{O}(n^2 d)$ in a classical model to $\mathcal{O}(n^2\log d)$ in our quantum model, where $n$ and $d$ represent the sequence length and embedding dimension, respectively. We perform simulations using NVIDIA's CUDA-Q platform, which is designed for efficient GPU scalability. This work provides a promising avenue for quantum-enhanced natural language processing (NLP).

quant-ph↗

arXiv2025

QAOA-GPT: Efficient Generation of Adaptive and Regular Quantum Approximate Optimization Algorithm Circuits

Quantum computing has the potential to improve our ability to solve certain optimization problems that are computationally difficult for classical computers, by offering new algorithmic approaches that may provide speedups under specific conditions. In this work, we introduce QAOA-GPT, a generative framework that leverages Generative Pretrained Transformers (GPT) to directly synthesize quantum circuits for solving quadratic unconstrained binary optimization problems, and demonstrate it on the MaxCut problem on graphs. To diversify the training circuits and ensure their quality, we have generated a synthetic dataset using the adaptive QAOA approach, a method that incrementally builds and optimizes problem-specific circuits. The experiments conducted on a curated set of graph instances demonstrate that QAOA-GPT, generates high quality quantum circuits for new problem instances unseen in the training as well as successfully parametrizes QAOA. Our results show that using QAOA-GPT to generate quantum circuits will significantly decrease both the computational overhead of classical QAOA and adaptive approaches that often use gradient evaluation to generate the circuit and the classical optimization of the circuit parameters. Our work shows that generative AI could be a promising avenue to generate compact quantum circuits in a scalable way.

quant-ph↗

arXiv2024

Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries

The nexus of quantum computing and machine learning - quantum machine learning - offers the potential for significant advancements in chemistry. This review specifically explores the potential of quantum neural networks on gate-based quantum computers within the context of drug discovery. We discuss the theoretical foundations of quantum machine learning, including data encoding, variational quantum circuits, and hybrid quantum-classical approaches. Applications to drug discovery are highlighted, including molecular property prediction and molecular generation. We provide a balanced perspective, emphasizing both the potential benefits and the challenges that must be addressed.

quant-ph↗

arXiv2022

Towards the simulation of transition-metal oxides of the cathode battery materials using VQE methods

Variational quantum eigensolver (VQE) is a hybrid quantum-classical technique that leverages noisy intermediate scale quantum (NISQ) hardware to obtain the minimum eigenvalue of a model Hamiltonian. VQE has so far been used to simulate condensed matter systems as well as quantum chemistry of small molecules. In this work, we employ VQE methods to obtain the ground-state energy of LiCoO$_2$, a candidate transition metal oxide used for battery cathodes. We simulate Li$_2$Co$_2$O$_4$ and Co$_2$O$_4$ gas-phase models, which represent the lithiated and delithiated states during the discharge and the charge of the Li-ion battery, respectively. Computations are performed using a statevector simulator with a single reference state for three different trial wavefunctions: unitary coupled-cluster singles and doubles (UCCSD), unitary coupled-cluster generalized singles and doubles (UCCGSD) and k-unitary pair coupled-cluster generalized singles and doubles (k-UpCCGSD). The resources in terms of circuit depth, two-qubit entangling gates and wavefunction parameters are analyzed. We find that the k-UpCCGSD with k=5 produces results similar to UCCSD but at a lower cost. Finally, the performance of VQE methods is benchmarked against the classical wavefunction-based methods, such as coupled-cluster singles and doubles (CCSD) and complete active space configuration interaction (CASCI). Our results show that VQE methods quantitatively agree with the results obtained from CCSD. However, the comparison against the CASCI results clearly suggests that advanced trial wavefunctions are likely necessary to capture the multi-reference characteristics as well as the correlations emerging from high-level electronic excitations.

quant-ph↗