arXiv subjects

Aleksandar Vučković

Publications and source records attributed to Aleksandar Vučković.

4 recordsLinked to original sources

arXiv2026

TabularQGAN: A quantum generative model for tabular data synthesis

In this paper, we introduce a novel quantum generative model for synthesizing tabular data. Synthetic data is valuable in scenarios where real-world data is scarce or private, as it can be used to augment or replace existing datasets. As enterprise data is predominantly tabular and heterogeneous, often consisting of both categorical and numerical features, this task is relevant across various industries such as healthcare, finance, and software. Existing quantum generative models are designed for homogeneous data; we seek to fill this gap by proposing a quantum generative adversarial network architecture with flexible data encoding and a novel quantum circuit ansatz for effectively modeling tabular data. The proposed approach is tested on the MIMIC-III healthcare and Adult Census datasets, with extensive benchmarking against leading classical models, CTGAN, CopulaGAN, VAE-GMM, and an LLM-based approach using the be-GReaT framework for tabular data synthesis. We evaluated our model as a proof-of-concept on reduced feature subsets using a noiseless statevector simulator on classical hardware. Our simulations show that, for the MIMIC-III dataset, our quantum model achieves competitive, and in some cases, leading performance with respect to an overall similarity score used in the open-source Python library SDMetrics. Additionally, we evaluate the generalization capabilities of the models using two custom-designed metrics that demonstrate the ability of the proposed quantum model to generate useful and novel tabular samples.

cs.LG↗

arXiv2024

A performance characterization of quantum generative models

Quantum generative modeling is a growing area of interest for industry-relevant applications. With the field still in its infancy, there are many competing techniques. This work is an attempt to systematically compare a broad range of these techniques to guide quantum computing practitioners when deciding which models and techniques to use in their applications. We compare fundamentally different architectural ansatzes of parametric quantum circuits used for quantum generative modeling: 1. A continuous architecture, which produces continuous-valued data samples, and 2. a discrete architecture, which samples on a discrete grid. We compare the performance of different data transformations: normalization by the min-max transform or by the probability integral transform. We learn the underlying probability distribution of the data sets via two popular training methods: 1. quantum circuit Born machines (QCBM), and 2. quantum generative adversarial networks (QGAN). We study their performance and trade-offs as the number of model parameters increases, with the baseline of similarly trained classical neural networks. The study is performed on six low-dimensional synthetic and two real financial data sets. Our two key findings are that: 1. For all data sets, our quantum models require similar or fewer parameters than their classical counterparts. In the extreme case, the quantum models require two of orders of magnitude less parameters. 2. We empirically find that a variant of the discrete architecture, which learns the copula of the probability distribution, outperforms all other methods.

quant-ph↗

arXiv2023

Unsupervised Learning of Invariance Transformations

The need for large amounts of training data in modern machine learning is one of the biggest challenges of the field. Compared to the brain, current artificial algorithms are much less capable of learning invariance transformations and employing them to extrapolate knowledge from small sample sets. It has recently been proposed that the brain might encode perceptual invariances as approximate graph symmetries in the network of synaptic connections. Such symmetries may arise naturally through a biologically plausible process of unsupervised Hebbian learning. In the present paper, we illustrate this proposal on numerical examples, showing that invariance transformations can indeed be recovered from the structure of recurrent synaptic connections which form within a layer of feature detector neurons via a simple Hebbian learning rule. In order to numerically recover the invariance transformations from the resulting recurrent network, we develop a general algorithmic framework for finding approximate graph automorphisms. We discuss how this framework can be used to find approximate automorphisms in weighted graphs in general.

cs.NE↗

arXiv2023

A locally signed-distance preserving level set method (SDPLS) for moving interfaces

It is well-known that the standard level set advection equation does not preserve the signed distance property, which is a desirable property for the level set function representing a moving interface. Therefore, reinitialization or redistancing methods are frequently applied to restore the signed distance property while keeping the zero-contour fixed. As an alternative approach to these methods, we introduce a modified level set advection equation that intrinsically preserves the norm of the gradient at the interface, i.e. the local signed distance property. Mathematically, this is achieved by introducing a carefully chosen source term being proportional to the local rate of interfacial area generation. The introduction of the source term turns the problem into a non-linear one. However, we show that by discretizing the source term explicitly in time, it is sufficient to solve a linear equation in each time step. Notably, without further adjustment, the method works in the case of a moving contact line. This is a major advantage since redistancing is known to be an issue when contact lines are involved. We provide a first implementation of the method in a simple first-order upwind scheme in both two and three spatial dimensions.

math.NA↗