On fundamental aspects of quantum extreme learning machines

Quantum Extreme Learning Machines (QELMs) have emerged as a promising framework for quantum machine learning. Their appeal lies in the rich feature map induced by the dynamics of a quantum substrate - the quantum reservoir - and the efficient post-measurement training via linear regression. Here we study the expressivity of QELMs by decomposing the prediction of QELMs into a Fourier series. We show that the achievable Fourier frequencies are determined by the data encoding scheme, while Fourier coefficients depend on both the reservoir and the measurement. Notably, the expressivity of QELMs is fundamentally limited by the number of Fourier frequencies and the number of observables, while the complexity of the prediction hinges on the reservoir. As a cautionary note on scalability, we identify four sources that can lead to the exponential concentration of the observables as the system size grows (randomness, hardware noise, entanglement, and global measurements) and show how this can turn QELMs into useless input-agnostic oracles. Our analysis elucidates the potential and fundamental limitations of QELMs, and lays the groundwork for systematically exploring quantum reservoir systems for other machine learning tasks.

Quantum Next Generation Reservoir Computing: An Efficient Quantum Algorithm for Forecasting Quantum Dynamics

Next Generation Reservoir Computing (NG-RC) is a modern class of model-free machine learning that enables an accurate forecasting of time series data generated by dynamical systems. We demonstrate that NG-RC can accurately predict full many-body quantum dynamics, instead of merely concentrating on the dynamics of observables, which is the conventional application of reservoir computing. In addition, we apply a technique which we refer to as skipping ahead to predict far future states accurately without the need to extract information about the intermediate states. However, adopting a classical NG-RC for many-body quantum dynamics prediction is computationally prohibitive due to the large Hilbert space of sample input data. In this work, we propose an end-to-end quantum algorithm for many-body quantum dynamics forecasting with a quantum computational speedup via the block-encoding technique. This proposal presents an efficient model-free quantum scheme to forecast quantum dynamics coherently, bypassing inductive biases incurred in a model-based approach.

Diffusion probabilistic models enhance variational autoencoder for crystal structure generative modeling

The crystal diffusion variational autoencoder (CDVAE) is a machine learning model that leverages score matching to generate realistic crystal structures that preserve crystal symmetry. In this study, we leverage novel diffusion probabilistic (DP) models to denoise atomic coordinates rather than adopting the standard score matching approach in CDVAE. Our proposed DP-CDVAE model can reconstruct and generate crystal structures whose qualities are statistically comparable to those of the original CDVAE. Furthermore, notably, when comparing the carbon structures generated by the DP-CDVAE model with relaxed structures obtained from density functional theory calculations, we find that the DP-CDVAE generated structures are remarkably closer to their respective ground states. The energy differences between these structures and the true ground states are, on average, 68.1 meV/atom lower than those generated by the original CDVAE. This significant improvement in the energy accuracy highlights the effectiveness of the DP-CDVAE model in generating crystal structures that better represent their ground-state configurations.

StrainNet: Predicting crystal structure elastic properties using SE(3)-equivariant graph neural networks

Accurately predicting the elastic properties of crystalline solids is vital for computational materials science. However, traditional atomistic scale ab initio approaches are computationally intensive, especially for studying complex materials with a large number of atoms in a unit cell. We introduce a novel data-driven approach to efficiently predict the elastic properties of crystal structures using SE(3)-equivariant graph neural networks (GNNs). This approach yields important scalar elastic moduli with the accuracy comparable to recent data-driven studies. Importantly, our symmetry-aware GNNs model also enables the prediction of the strain energy density (SED) and the associated elastic constants, the fundamental tensorial quantities that are significantly influenced by a material's crystallographic group. The model consistently distinguishes independent elements of SED tensors, in accordance with the symmetry of the crystal structures. Finally, our deep learning model possesses meaningful latent features, offering an interpretable prediction of the elastic properties.

Explainable Natural Language Processing with Matrix Product States

Despite empirical successes of recurrent neural networks (RNNs) in natural language processing (NLP), theoretical understanding of RNNs is still limited due to intrinsically complex computations in RNNs. We perform a systematic analysis of RNNs' behaviors in a ubiquitous NLP task, the sentiment analysis of movie reviews, via the mapping between a class of RNNs called recurrent arithmetic circuits (RACs) and a matrix product state (MPS). Using the von-Neumann entanglement entropy (EE) as a proxy for information propagation, we show that single-layer RACs possess a maximum information propagation capacity, reflected by the saturation of the EE. Enlarging the bond dimension of an MPS beyond the EE saturation threshold does not increase the prediction accuracies, so a minimal model that best estimates the data statistics can be constructed. Although the saturated EE is smaller than the maximum EE achievable by the area law of an MPS, our model achieves ~99% training accuracies in realistic sentiment analysis data sets. Thus, low EE alone is not a warrant against the adoption of single-layer RACs for NLP. Contrary to a common belief that long-range information propagation is the main source of RNNs' expressiveness, we show that single-layer RACs also harness high expressiveness from meaningful word vector embeddings. Our work sheds light on the phenomenology of learning in RACs and more generally on the explainability aspects of RNNs for NLP, using tools from many-body quantum physics.

Quantum diffusion map for nonlinear dimensionality reduction

Inspired by random walk on graphs, diffusion map (DM) is a class of unsupervised machine learning that offers automatic identification of low-dimensional data structure hidden in a high-dimensional dataset. In recent years, among its many applications, DM has been successfully applied to discover relevant order parameters in many-body systems, enabling automatic classification of quantum phases of matter. However, classical DM algorithm is computationally prohibitive for a large dataset, and any reduction of the time complexity would be desirable. With a quantum computational speedup in mind, we propose a quantum algorithm for DM, termed quantum diffusion map (qDM). Our qDM takes as an input N classical data vectors, performs an eigen-decomposition of the Markov transition matrix in time $O(\log^3 N)$, and classically constructs the diffusion map via the readout (tomography) of the eigenvectors, giving a total runtime of $O(N^2 \text{polylog}\, N)$. Lastly, quantum subroutines in qDM for constructing a Markov transition operator, and for analyzing its spectral properties can also be useful for other random walk-based algorithms.

Follow-the-Regularized-Leader Routes to Chaos in Routing Games

We study the emergence of chaotic behavior of Follow-the-Regularized Leader (FoReL) dynamics in games. We focus on the effects of increasing the population size or the scale of costs in congestion games, and generalize recent results on unstable, chaotic behaviors in the Multiplicative Weights Update dynamics to a much larger class of FoReL dynamics. We establish that, even in simple linear non-atomic congestion games with two parallel links and any fixed learning rate, unless the game is fully symmetric, increasing the population size or the scale of costs causes learning dynamics to become unstable and eventually chaotic, in the sense of Li-Yorke and positive topological entropy. Furthermore, we show the existence of novel non-standard phenomena such as the coexistence of stable Nash equilibria and chaos in the same game. We also observe the simultaneous creation of a chaotic attractor as another chaotic attractor gets destroyed. Lastly, although FoReL dynamics can be strange and non-equilibrating, we prove that the time average still converges to an exact equilibrium for any choice of learning rate and any scale of costs.

Biologically Plausible Sequence Learning with Spiking Neural Networks

Motivated by the celebrated discrete-time model of nervous activity outlined by McCulloch and Pitts in 1943, we propose a novel continuous-time model, the McCulloch-Pitts network (MPN), for sequence learning in spiking neural networks. Our model has a local learning rule, such that the synaptic weight updates depend only on the information directly accessible by the synapse. By exploiting asymmetry in the connections between binary neurons, we show that MPN can be trained to robustly memorize multiple spatiotemporal patterns of binary vectors, generalizing the ability of the symmetric Hopfield network to memorize static spatial patterns. In addition, we demonstrate that the model can efficiently learn sequences of binary pictures as well as generative models for experimental neural spike-train data. Our learning rule is consistent with spike-timing-dependent plasticity (STDP), thus providing a theoretical ground for the systematic design of biologically inspired networks with large and robust long-range sequence storage capacity.

Expectation propagation: a probabilistic view of Deep Feed Forward Networks

We present a statistical mechanics model of deep feed forward neural networks (FFN). Our energy-based approach naturally explains several known results and heuristics, providing a solid theoretical framework and new instruments for a systematic development of FFN. We infer that FFN can be understood as performing three basic steps: encoding, representation validation and propagation. We obtain a set of natural activations -- such as sigmoid, $\tanh$ and ReLu -- together with a state-of-the-art one, recently obtained by Ramachandran et al.(arXiv:1710.05941) using an extensive search algorithm. We term this activation ESP (Expected Signal Propagation), explain its probabilistic meaning, and study the eigenvalue spectrum of the associated Hessian on classification tasks. We find that ESP allows for faster training and more consistent performances over a wide range of network architectures.