arXiv subjects

Yitian Chen

Publications and source records attributed to Yitian Chen.

26 records · Page 2Linked to original sources

arXiv2023

Extending black-hole remnant surrogate models to extreme mass ratios

Numerical-relativity surrogate models for both black-hole merger waveforms and remnants have emerged as important tools in gravitational-wave astronomy. While producing very accurate predictions, their applicability is limited to the region of the parameter space where numerical-relativity simulations are available and computationally feasible. Notably, this excludes extreme mass ratios. We present a machine-learning approach to extend the validity of existing and future numerical-relativity surrogate models toward the test-particle limit, targeting in particular the mass and spin of post-merger black-hole remnants. Our model is trained on both numerical-relativity simulations at comparable masses and analytical predictions at extreme mass ratios. We extend the gaussian-process-regression model NRSur7dq4Remnant, validate its performance via cross validation, and test its accuracy against additional numerical-relativity runs. Our fit, which we dub NRSur7dq4EmriRemnant, reaches an accuracy that is comparable to or higher than that of existing remnant models while providing robust predictions for arbitrary mass ratios.

gr-qc↗

arXiv2023

Regret Analysis of Online LQR Control via Trajectory Prediction and Tracking: Extended Version

In this paper, we propose and analyze a new method for online linear quadratic regulator (LQR) control with a priori unknown time-varying cost matrices. The cost matrices are revealed sequentially with the potential for future values to be previewed over a short window. Our novel method involves using the available cost matrices to predict the optimal trajectory, and a tracking controller to drive the system towards it. We adopted the notion of dynamic regret to measure the performance of this proposed online LQR control method, with our main result being that the (dynamic) regret of our method is upper bounded by a constant. Moreover, the regret upper bound decays exponentially with the preview window length, and is extendable to systems with disturbances. We show in simulations that our proposed method offers improved performance compared to other previously proposed online LQR methods.

math.OC↗

arXiv2023

GP-NAS-ensemble: a model for NAS Performance Prediction

It is of great significance to estimate the performance of a given model architecture without training in the application of Neural Architecture Search (NAS) as it may take a lot of time to evaluate the performance of an architecture. In this paper, a novel NAS framework called GP-NAS-ensemble is proposed to predict the performance of a neural network architecture with a small training dataset. We make several improvements on the GP-NAS model to make it share the advantage of ensemble learning methods. Our method ranks second in the CVPR2022 second lightweight NAS challenge performance prediction track.

cs.LG↗

arXiv2022

Multipole moments on the common horizon in a binary-black-hole simulation

We construct the covariantly defined multipole moments on the common horizon of an equal-mass, non-spinning, quasicircular binary-black-hole system. We see a strong correlation between these multipole moments and the gravitational waveform. We find that the multipole moments are well described by the fundamental quasinormal modes at sufficiently late times. For each multipole moment, at least two fundamental modes of different $\ell$ are detectable in the best model. These models provide faithful estimates of the true mass and spin of the remnant black hole. We also show that by including overtones, the $\ell=m=2$ mass multipole moment admits an excellent quasinormal-mode description at all times after the merger. This demonstrates the perhaps surprising power of perturbation theory near the merger.

gr-qc↗

arXiv2021

Efficient simulations of high-spin black holes with a new gauge

We present a new choice of initial data for binary black hole simulations that significantly improves the efficiency of high-spin simulations. We use spherical Kerr-Schild coordinates, where the horizon of a rotating black hole is spherical, for each black hole. The superposed spherical Kerr-Schild initial data reduce the runtime by a factor of 2 compared to standard superposed Kerr-Schild for an intermediate resolution spin-0.99 binary-black-hole simulation. We also explore the possibility of delaying the transition from the initial data gauge to the evolution gauge, which produces an additional speed-up of 1.3.

gr-qc↗

arXiv2021

DQN Control Solution for KDD Cup 2021 City Brain Challenge

We took part in the city brain challenge competition and achieved the 8th place. In this competition, the players are provided with a real-world city-scale road network and its traffic demand derived from real traffic data. The players are asked to coordinate the traffic signals with a self-designed agent to maximize the number of vehicles served while maintaining an acceptable delay. In this abstract paper, we present an overall analysis and our detailed solution to this competition. Our approach is mainly based on the adaptation of the deep Q-network (DQN) for real-time traffic signal control. From our perspective, the major challenge of this competition is how to extend the classical DQN framework to traffic signals control in real-world complex road network and traffic flow situation. After trying and implementing several classical reward functions, we finally chose to apply our newly-designed reward in our agent. By applying our newly-proposed reward function and carefully tuning the control scheme, an agent based on a single DQN model can rank among the top 15 teams. We hope this paper could serve, to some extent, as a baseline solution to traffic signal control of real-world road network and inspire further attempts and researches.

cs.LG↗

arXiv2020

Probabilistic Forecasting with Temporal Convolutional Neural Network

We present a probabilistic forecasting framework based on convolutional neural network for multiple related time series forecasting. The framework can be applied to estimate probability density under both parametric and non-parametric settings. More specifically, stacked residual blocks based on dilated causal convolutional nets are constructed to capture the temporal dependencies of the series. Combined with representation learning, our approach is able to learn complex patterns such as seasonality, holiday effects within and across series, and to leverage those patterns for more accurate forecasts, especially when historical data is sparse or unavailable. Extensive empirical studies are performed on several real-world datasets, including datasets from JD.com, China's largest online retailer. The results show that our framework outperforms other state-of-the-art methods in both accuracy and efficiency.

stat.ML↗

arXiv2017

Optimal use of Charge Information for the HL-LHC Pixel Detector Readout

The pixel detectors for the High Luminosity upgrades of the ATLAS and CMS detectors will preserve digitized charge information in spite of extremely high hit rates. Both circuit physical size and output bandwidth will limit the number of bits to which charge can be digitized and stored. We therefore study the effect of the number of bits used for digitization and storage on single and multi-particle cluster resolution, efficiency, classification, and particle identification. We show how performance degrades as fewer bits are used to digitize and to store charge. We find that with limited charge information (4 bits), one can achieve near optimal performance on a variety of tasks.

physics.ins-det↗