Automated machine learning (AutoML) usually involves several crucial components, such as Data Augmentation (DA) policy, Hyper-Parameter Optimization (HPO), and Neural Architecture Search (NAS). Although many strategies have been developed for automat
ing these components in separation, joint optimization of these components remains challenging due to the largely increased search dimension and the variant input types of each component. Meanwhile, conducting these components in a sequence often requires careful coordination by human experts and may lead to sub-optimal results. In parallel to this, the common practice of searching for the optimal architecture first and then retraining it before deployment in NAS often suffers from low performance correlation between the search and retraining stages. An end-to-end solution that integrates the AutoML components and returns a ready-to-use model at the end of the search is desirable. In view of these, we propose DHA, which achieves joint optimization of Data augmentation policy, Hyper-parameter and Architecture. Specifically, end-to-end NAS is achieved in a differentiable manner by optimizing a compressed lower-dimensional feature space, while DA policy and HPO are updated dynamically at the same time. Experiments show that DHA achieves state-of-the-art (SOTA) results on various datasets, especially 77.4% accuracy on ImageNet with cell based search space, which is higher than current SOTA by 0.5%. To the best of our knowledge, we are the first to efficiently and jointly optimize DA policy, NAS, and HPO in an end-to-end manner without retraining.
In this paper, we investigate a new multi-armed bandit (MAB) online learning model that considers real-world phenomena in many recommender systems: (i) the learning agent cannot pull the arms by itself and thus has to offer rewards to users to incent
ivize arm-pulling indirectly; and (ii) if users with specific arm preferences are well rewarded, they induce a self-reinforcing effect in the sense that they will attract more users of similar arm preferences. Besides addressing the tradeoff of exploration and exploitation, another key feature of this new MAB model is to balance reward and incentivizing payment. The goal of the agent is to maximize the total reward over a fixed time horizon $T$ with a low total payment. Our contributions in this paper are two-fold: (i) We propose a new MAB model with random arm selection that considers the relationship of users self-reinforcing preferences and incentives; and (ii) We leverage the properties of a multi-color Polya urn with nonlinear feedback model to propose two MAB policies termed At-Least-$n$ Explore-Then-Commit and UCB-List. We prove that both policies achieve $O(log T)$ expected regret with $O(log T)$ expected payment over a time horizon $T$. We conduct numerical simulations to demonstrate and verify the performances of these two policies and study their robustness under various settings.
Quantum machine learning could possibly become a valuable alternative to classical machine learning for applications in High Energy Physics by offering computational speed-ups. In this study, we employ a support vector machine with a quantum kernel e
stimator (QSVM-Kernel method) to a recent LHC flagship physics analysis: $tbar{t}H$ (Higgs boson production in association with a top quark pair). In our quantum simulation study using up to 20 qubits and up to 50000 events, the QSVM-Kernel method performs as well as its classical counterparts in three different platforms from Google Tensorflow Quantum, IBM Quantum and Amazon Braket. Additionally, using 15 qubits and 100 events, the application of the QSVM-Kernel method on the IBM superconducting quantum hardware approaches the performance of a noiseless quantum simulator. Our study confirms that the QSVM-Kernel method can use the large dimensionality of the quantum Hilbert space to replace the classical feature space in realistic physics datasets.
Forced oscillation (FO) is a significant concern threating the power system stability. Its mechanisms are mostly studied via linear models. However, FO amplitude is increasing, e.g., Nordic and Western American FOs, which can stimulate power system n
onlinearity. Hence, this paper incorporates nonlinearity in FO mechanism analysis. The multi-scale technique is employed in solving the forced oscillation equation to handle the quadratic nonlinearity. The amplitude-frequency characteristic curves and first-order approximate expressions are derived. The frequency deviation and jumping phenomenon caused by nonlinearity are discovered and further analyzed by comparing with linear models. This paper provides a preliminary research for nonlinear FOs of power system, and more characteristics should be further analysis in the near future.
One of the major objectives of the experimental programs at the LHC is the discovery of new physics. This requires the identification of rare signals in immense backgrounds. Using machine learning algorithms greatly enhances our ability to achieve th
is objective. With the progress of quantum technologies, quantum machine learning could become a powerful tool for data analysis in high energy physics. In this study, using IBM gate-model quantum computing systems, we employ the quantum variational classifier method in two recent LHC flagship physics analyses: $tbar{t}H$ (Higgs boson production in association with a top quark pair) and $Hrightarrowmu^{+}mu^{-}$ (Higgs boson decays to two muons, probing the Higgs boson couplings to second-generation fermions). We have obtained early results with 10 qubits on the IBM quantum simulator and the IBM quantum hardware. With small training samples of 100 events on the quantum simulator, the quantum variational classifier method performs similarly to classical algorithms such as SVM (support vector machine) and BDT (boosted decision tree), which are often employed in LHC physics analyses. On the quantum hardware, the quantum variational classifier method has shown promising discrimination power, comparable to that on the quantum simulator. This study demonstrates that quantum machine learning has the ability to differentiate between signal and background in realistic physics datasets. We foresee the usage of quantum machine learning in future high-luminosity LHC physics analyses, including measurements of the Higgs boson self-couplings and searches for dark matter.
A deep learning based non-line-of-sight (NLOS) imaging system is developed to image an occluded object off a scattering surface. The neural net is trained using only handwritten digits, and yet exhibits capability to reconstruct patterns distinct fro
m the training set, including physical objects. It can also reconstruct a cartoon video from its scattering patterns in real time, demonstrating the robustness and generalization capability of the deep learning based approach. Several scattering surfaces with varying degree of Lambertian and specular contributions were examined experimentally; it is found that for a Lambertian surface the structural similarity index (SSIM) of reconstructed images is about 0.63, while the SSIM obtained from a scattering surface possessing a specular component can be as high as 0.93. A forward model of light transport was developed based on the Phong scattering model. Scattering patterns from Phong surfaces with different degrees of specular contribution were numerically simulated. It is found that a specular contribution of as small as 5% can enhance the SSIM from 0.83 to 0.93, consistent with the results from experimental data. Singular value spectra of the underlying transfer matrix were calculated for various Phong surfaces. As the weight and the shininess factor increase, i.e., the specular contribution increases, the singular value spectrum broadens and the 50-dB bandwidth is increased by more than 4X with a 10% specular contribution, which indicates that at the presence of even a small amount of specular contribution the NLOS measurement can retain significantly more singular value components, leading to higher reconstruction fidelity. With an ordinary camera and incoherent light source, this work enables a low-cost, real-time NLOS imaging system without the need of an explicit physical model of the underlying light transport process.
Recent learning-based approaches have achieved impressive results in the field of single-shot camera localization. However, how best to fuse multiple modalities (e.g., image and depth) and to deal with degraded or missing input are less well studied.
In particular, we note that previous approaches towards deep fusion do not perform significantly better than models employing a single modality. We conjecture that this is because of the naive approaches to feature space fusion through summation or concatenation which do not take into account the different strengths of each modality. To address this, we propose an end-to-end framework, termed VMLoc, to fuse different sensor inputs into a common latent space through a variational Product-of-Experts (PoE) followed by attention-based fusion. Unlike previous multimodal variational works directly adapting the objective function of vanilla variational auto-encoder, we show how camera localization can be accurately estimated through an unbiased objective function based on importance weighting. Our model is extensively evaluated on RGB-D datasets and the results prove the efficacy of our model. The source code is available at https://github.com/Zalex97/VMLoc.
In large-scale classification problems, the data set always be faced with frequent updates when a part of the data is added to or removed from the original data set. In this case, conventional incremental learning, which updates an existing classifie
r by explicitly modeling the data modification, is more efficient than retraining a new classifier from scratch. However, sometimes, we are more interested in determining whether we should update the classifier or performing some sensitivity analysis tasks. To deal with these such tasks, we propose an algorithm to make rational inferences about the updated linear classifier without exactly updating the classifier. Specifically, the proposed algorithm can be used to estimate the upper and lower bounds of the updated classifiers coefficient matrix with a low computational complexity related to the size of the updated dataset. Both theoretical analysis and experiment results show that the proposed approach is superior to existing methods in terms of tightness of coefficients bounds and computational complexity.
During recent decades, the automatic train operation (ATO) system has been gradually adopted in many subway systems for its low-cost and intelligence. This paper proposes two smart train operation algorithms by integrating the expert knowledge with r
einforcement learning algorithms. Compared with previous works, the proposed algorithms can realize the control of continuous action for the subway system and optimize multiple critical objectives without using an offline speed profile. Firstly, through learning historical data of experienced subway drivers, we extract the expert knowledge rules and build inference methods to guarantee the riding comfort, the punctuality, and the safety of the subway system. Then we develop two algorithms for optimizing the energy efficiency of train operation. One is the smart train operation (STO) algorithm based on deep deterministic policy gradient named (STOD) and the other is the smart train operation algorithm based on normalized advantage function (STON). Finally, we verify the performance of proposed algorithms via some numerical simulations with the real field data from the Yizhuang Line of the Beijing Subway and illustrate that the developed smart train operation algorithm are better than expert manual driving and existing ATO algorithms in terms of energy efficiency. Moreover, STOD and STON can adapt to different trip times and different resistance conditions.
This paper investigates the integration of gradient boosted decision trees and varying coefficient models. We introduce the tree boosted varying coefficient framework which justifies the implementation of decision tree boosting as the nonparametric e
ffect modifiers in varying coefficient models. This framework requires no structural assumptions in the space containing the varying coefficient covariates, is easy to implement, and keeps a balance between model complexity and interpretability. To provide statistical guarantees, we prove the asymptotic consistency of the proposed method under the regression settings with $L^2$ loss. We further conduct a thorough empirical study to show that the proposed method is capable of providing accurate predictions as well as intelligible visual explanations.
