Related papers: Unweighting multijet event generation using factor…
We propose a novel method to explain trained deep neural networks (DNNs), by distilling them into surrogate models using unsupervised clustering. Our method can be applied flexibly to any subset of layers of a DNN architecture and can…
We study the use of cell resampling to reduce the fraction of negatively weighted Monte Carlo events in a generated sample typical of that used in experimental analyses. To this end, we apply the Cell Resampler to a set of $pp \rightarrow…
In this paper, we first introduce batch normalization to the edRVFL network. This re-normalization method can help the network avoid divergence of the hidden features. Then we propose novel variants of Ensemble Deep Random Vector Functional…
Recently, it has been shown that neural networks not only approximate the ground-state wave functions of a single molecular system well but can also generalize to multiple geometries. While such generalization significantly speeds up…
Multipartite entanglement is a crucial resource for quantum technologies; however, its scalable generation in noisy quantum devices remains a significant challenge. Here, we propose a low-depth quantum neural network architecture with…
The preformation factor quantifies the probability of {\alpha} particles preforming on the surface of the parent nucleus in decay theory and is closely related to the study of {\alpha} clustering structure. In this work, a multilayer…
Deep Neural Networks (DNNs) have achieved extraordinary performance in various application domains. To support diverse DNN models, efficient implementations of DNN inference on edge-computing platforms, e.g., ASICs, FPGAs, and embedded…
We present a matrix factorization algorithm that scales to input matrices that are large in both dimensions (i.e., that contains morethan 1TB of data). The algorithm streams the matrix columns while subsampling them, resulting in low…
This paper illustrates a generic method for multi-dimensional reweighting of $O(1)$ GeV neutrino interaction Monte Carlo samples. The reweighting is based on a Boosted Decision Tree algorithm trained on high-dimensional space in detector…
Probabilistic forecasting of high dimensional multivariate time series is a notoriously challenging task, both in terms of computational burden and distribution modeling. Most previous work either makes simple distribution assumptions or…
This paper describes algorithms for nonnegative matrix factorization (NMF) with the beta-divergence (beta-NMF). The beta-divergence is a family of cost functions parametrized by a single shape parameter beta that takes the Euclidean…
We present a factorization framework that takes into account the production of heavy quarks through gluon splitting in the thrust distribution for e+ e- --> hadrons. The explicit factorization theorems and some numerical results are…
Matrix multiplication is the bedrock in Deep Learning inference application. When it comes to hardware acceleration on edge computing devices, matrix multiplication often takes up a great majority of the time. To achieve better performance…
In recent years, there is a growing interest in using quantum computers for solving combinatorial optimization problems. In this work, we developed a generic, machine learning-based framework for mapping continuous-space inverse design…
The scaling properties of the final state charged hadron and mean jet multiplicity distributions, calculated by deep residual neural network architectures with different complexities are presented. The parton-level input of the neural…
We tackle the problem disentangling the latent space of an autoencoder in order to separate labelled attribute information from other characteristic information. This then allows us to change selected attributes while preserving other…
The growing enforcement of the right to be forgotten regulations has propelled recent advances in certified (graph) unlearning strategies to comply with data removal requests from deployed machine learning (ML) models. Motivated by the…
The energy transition entails a rapid uptake of renewable energy sources. Besides physical changes within the grid infrastructure, energy storage devices and their smart operation are key measures to master the resulting challenges like,…
We propose a deep generative factor analysis model with beta process prior that can approximate complex non-factorial distributions over the latent codes. We outline a stochastic EM algorithm for scalable inference in a specific…
A method for incorporating information from next-to-leading order QCD matrix elements for hadronic diboson production into showering event generators is presented. In the hard central region (high jet transverse momentum) where perturbative…