The work presented in this thesis shows that efficient ML for quantum chemistry does not rely on a single universally optimal model class, and hybrid strategies that combine explicit physical models with learned components can be as effective as fully data-driven approaches while retaining the robustness and interpretability of the underlying physical description.
Abstract
The development of quantum chemistry has long been shaped by a central tension: while the laws governing electronic structure are known, their exact application quickly becomes computationally prohibitive for realistic molecular systems. Over decades, this challenge has driven the design of increasingly sophisticated approximations that balance predictive accuracy with computational affordability. More recently, machine learning (ML) has emerged as a new addition to this methodological landscape, offering the possibility of reproducing high-level quantum chemical results at a fraction of the cost.
This thesis explores how ML can contribute to this long-standing objective in a particularly resource-conscious way. Rather than treating ML purely as a black-box substitute for quantum chemistry, the work asks a broader methodological question: under finite budgets for data generation, training and inference, what is the most efficient way to use data-driven models to accelerate quantum chemical simulations? Across the different applications studied here, the guiding principle has been to identify the simplest effective strategy for the problem at hand while retaining as much physical structure and reusing as much existing data as possible.
A first key result of this thesis is that substantial acceleration can, in some settings, be achieved with remarkably simple models. In the context of basis set extrapolation for GW quasiparticle energies, a linear regression model based on molecular orbital descriptors was shown to recover near-complete basis set accuracy from finite-basis calculations. This demonstrates that when the underlying quantum chemical representations already contain the essential physical information, even lightweight statistical models can provide acceleration while maintaining high-level quantum chemical accuracy.
As many ML applications, especially neural networks, critically depend on sufficiently broad and reliable training data, part of this work focused on constructing a large-scale dataset of quasiparticle self-consistent GW (qsGW) quasiparticle energies, GW Bethe--Salpter equation (GW-BSE) neutral excitation energies, transition dipole moments and oscillator strengths across a chemically diverse space of organic molecules. Building on this foundation, a graph neural network was trained for the prediction of charged and neutral excitation energies. A central finding is that transfer learning from lower-fidelity but already widely available data sources, such as molecular orbital energies from density functional theory (DFT) and excitation energies from time-dependent DFT (TDDFT), can substantially improve the prediction of the high-fidelity qsGW and GW-BSE targets. In this way, previously generated computational data become a powerful resource for reducing the cost of expensive reference calculations.
The question of how simple ML models can remain while still being effective was further investigated for solvation energies and geometry optimization in solution. Here, the results show that relatively simple graph neural network architectures can already yield accurate predictions of Gibbs solvation energies for highly charged molecules. At the same time, ML was also used to parametrize and correct established physically grounded solvation models. These results suggest that, in such settings, hybrid strategies that combine explicit physical models with learned components can be as effective as fully data-driven approaches while retaining the robustness and interpretability of the underlying physical description.
Taken together, the work presented in this thesis shows that efficient ML for quantum chemistry does not rely on a single universally optimal model class. Instead, the most effective strategies arise from matching the complexity of the statistical model to the physical structure of the problem, reusing data across different levels of quantum chemical theory and retaining established physical models wherever they already provide reliable inductive bias. In this sense, ML serves not simply as a faster predictor but as a flexible methodological tool for extending the practical reach of quantum chemical simulations through resource-efficient acceleration.
The predictive simulation of molecules and materials has had a broad and significant impact. It nevertheless remains constrained by the cost of accurately treating electronic correlation, excited states, and complex energy landscapes. Quantum computing offers a fundamentally different computational paradigm in which quantum states are encoded and manipulated directly rather than approximated on classical hardware. Here we discuss where this approach may provide a genuine scientific advantage in chemistry, materials science, and biochemistry. Promising directions include the high-accuracy treatment of correlated active spaces, improved excited-state simulations, and accelerated exploration of combinatorial structure spaces. The central challenge is therefore not qubit scaling alone, but demonstrably chemically meaningful gains in predictive reliability. We argue that near-term value is most likely to come from disciplined workflow integration rather than wholesale replacement of classical methods. Noisy physical devices, error-mitigated utility experiments, early fault-tolerant devices, and fully fault-tolerant quantum computers offer different scientific prospects, and claims of usefulness must be tied to the specific regime being discussed. Quantum computing will become scientifically valuable when it demonstrably reduces uncertainty in computed energies, rates, spectra, or materials stability after the full costs of state preparation, measurement, error handling, and coupling to classical simulation are included.
Bruno Camino, C. R. A. Catlow, J. Buckeridge et al.· 0 citations
The field of quantum chemistry has long been defined by the central computational challenge of the quantum many‐body fermionic system problem—namely, the electronic Schrödinger equation. The exponential scaling of this equation makes it computationally intractable to solve exactly. As a result, various approximation methods have been developed, ranging from the widely used Density Functional Theory (DFT) to Coupled Cluster (CC) theory. While powerful, these conventional approaches often involve controlled truncations which cause a trade‐off between accuracy and computational cost, leaving many systems—particularly those with strong electron correlation—beyond the reach of ab initio simulation. Furthermore, the famous fermionic sign problem is particularly severe in stochastic methods like Quantum Monte Carlo (QMC). Traditional ansatz are also frequently engineered specifically for particular systems, which results in a fragmentation of methodologies and fundamentally limits their transferability. Recent research demonstrates that with carefully designed architectures, ANNs can not only represent ground states of model systems with high precision but also tackle the sign problem, offering a promising path forward for strongly correlated electronic structure calculations. This review charts the paradigm shift driven by Neural Network Quantum States (NNQS), which leverage the representational power of deep learning to overcome these barriers. We detail the architectural evolution from Restricted Boltzmann Machines to autoregressive models like RNNs and Transformers, which enable exact, uncorrelated sampling and bypass critical bottlenecks. The high‐efficiency optimization via neural networks was also explored, which decouples optimization cost from model complexity. Furthermore, the frontier of the field is marked by the integration of operator learning and hybrid quantum‐classical frameworks, such as Reinforcement Learning for contractive quantum eigen‐solvers to generate quantum circuits for simulating many‐body molecular systems, and Quantum‐Enhanced Neural Networks, which leverage quantum processors to enhance expressivity for hardware‐efficient ansatz. By framing the problem through the lens of computational resource allocation and quantum hardware integration—specifically, trading exponential memory demands for polynomial‐complexity optimization and sampling—this review elucidates how recent advances at the intersection of artificial neural networks and quantum computing have evolved. The emergence of these methods represents not merely progress toward powerful simulation tools, but also the creation of a hybrid computational interface. This convergence offers a versatile and systematically improvable framework for potentially addressing some of the most challenging problems in quantum physics and chemistry.
Chengze Yang· International Journal of Qua...· 0 citations
Results indicate that the topology-aligned inductive bias is the active ingredient driving parameter efficiency at QM9 scale, with implications for matched-baseline benchmarking in quantum machine learning.
Quantum computing is a deep technology whose progress cannot be driven effectively from one direction alone. While the field has developed a growing catalogue of mathematically grounded algorithmic speedups, industrial impact will depend just as much on starting from real industrial decision contexts and working downward to what must be computed, validated and integrated. In this Perspective, I argue that sustained progress requires treating these two directions: bottom-up development from physics, hardware and algorithms, and top-down development from industrial needs and constraints. Equally primary and continuously coupled. This dual-viewpoint is not a matter of balance for its own sake. Quantum computers cannot solve arbitrary problems, so engagement with industry must remain anchored in algorithmic tractability. Yet tractable computations are rarely valuable unless they connect to decision points in established workflows such as candidate selection in drug discovery or the design of a new aircraft shape with improved aerodynamics. I analyse how historical narratives and structural separations of expertise slowed the formation of this coupling and outline what it takes to build it: explicit interfaces between technical teams and domain context and intermediate layers that translate quantum outputs into decision-relevant observables without suffocating foundational innovation. Framed this way, quantum computing's opportunity is clearest where deep physical modelling meets high-value decisions. Provided the field co-designs both sides from the outset.
No interatomic potential has offered universality across chemistry, near-first-principles accuracy and the speed of empirical potentials at once. Here we introduce DPA4C, an equivariant potential whose architecture and compressed CUDA operators are co-designed under deployment constraints to pursue accuracy and efficiency together. Five variants spanning a 49-fold parameter range form the high-throughput end of the measured accuracy--throughput frontier. The largest variant approaches the accuracy of the MACE-Omat models at about two orders of magnitude higher measured throughput. The most compact reduces the energy, force and stress errors of the fastest existing universal MLIP by 61.4%, 48.1% and 34.3% at 1.92 times its saturated throughput. All five variants complete multimillion-atom simulations on a single GPU and run molecular dynamics for 2.048 billion atoms on 1,024 16-GB NVIDIA V100 GPUs at 83.3--91.2% weak-scaling efficiency. Compared with the MEAM empirical potential, DPA4C-Nano reaches 1.8 and 2.5 times the saturated throughput in single-GPU scans on the same V100 hardware for diamond carbon and FCC copper, respectively. DPA4C therefore brings quantum-trained universal accuracy into a regime of speed and system size previously associated with empirical potentials.
Tian Li, Jianming Xue, Linfeng Zhang et al.· 0 citations
Designing molecules with optimized properties remains a fundamental challenge due to the intricate relationship between molecular structure and properties. Traditional computational approaches that address the combinatorial number of possible molecular designs become unfeasible as the molecular size increases, suffering from the so-called "curse of dimensionality" problem. Recent advances in quantum computing hardware present new opportunities to address this problem. Here, we introduce the quantum ensemble variational optimization (QEVO) method for near-term and early fault-tolerant quantum computing platforms. QEVO efficiently maps molecular structures onto an orthonormal basis of binary strings and samples from a superposition state generated by a variational ansatz. The ansatz is iteratively optimized to identify molecular candidates with the desired property. Our numerical simulations demonstrate the potential of QEVO to design drug-like molecules with anticancer properties, operating in combinatorial spaces composed of up to [Formula: see text] solutions, while employing a shallow quantum circuit that requires only a modest number of qubits. We envision that QEVO could be applied to a wide range of complex problems, offering practical solutions to problems with combinatorial complexity.
F. Calcagno, Delmar G A Cabral, Ivan Rivalta et al.· Proceedings of the National...· 0 citations