arXiv subjects

Bin Hu

Publications and source records attributed to Bin Hu.

At least 199 records · Page 11Linked to original sources

arXiv2023

Learning the Kalman Filter with Fine-Grained Sample Complexity

We develop the first end-to-end sample complexity of model-free policy gradient (PG) methods in discrete-time infinite-horizon Kalman filtering. Specifically, we introduce the receding-horizon policy gradient (RHPG-KF) framework and demonstrate $\tilde{\mathcal{O}}(ε^{-2})$ sample complexity for RHPG-KF in learning a stabilizing filter that is $ε$-close to the optimal Kalman filter. Notably, the proposed RHPG-KF framework does not require the system to be open-loop stable nor assume any prior knowledge of a stabilizing filter. Our results shed light on applying model-free PG methods to control a linear dynamical system where the state measurements could be corrupted by statistical noises and other (possibly adversarial) disturbances.

math.OC↗

arXiv2023

Pretraining De-Biased Language Model with Large-scale Click Logs for Document Ranking

Pre-trained language models have achieved great success in various large-scale information retrieval tasks. However, most of pretraining tasks are based on counterfeit retrieval data where the query produced by the tailored rule is assumed as the user's issued query on the given document or passage. Therefore, we explore to use large-scale click logs to pretrain a language model instead of replying on the simulated queries. Specifically, we propose to use user behavior features to pretrain a debiased language model for document ranking. Extensive experiments on Baidu desensitization click logs validate the effectiveness of our method. Our team on WSDM Cup 2023 Pre-training for Web Search won the 1st place with a Discounted Cumulative Gain @ 10 (DCG@10) score of 12.16525 on the final leaderboard.

cs.IR↗

arXiv2023

Multi-Feature Integration for Perception-Dependent Examination-Bias Estimation

Eliminating examination bias accurately is pivotal to apply click-through data to train an unbiased ranking model. However, most examination-bias estimators are limited to the hypothesis of Position-Based Model (PBM), which supposes that the calculation of examination bias only depends on the rank of the document. Recently, although some works introduce information such as clicks in the same query list and contextual information when calculating the examination bias, they still do not model the impact of document representation on search engine result pages (SERPs) that seriously affects one's perception of document relevance to a query when examining. Therefore, we propose a Multi-Feature Integration Model (MFIM) where the examination bias depends on the representation of document except the rank of it. Furthermore, we mine a key factor slipoff counts that can indirectly reflects the influence of all perception-bias factors. Real world experiments on Baidu-ULTR dataset demonstrate the superior effectiveness and robustness of the new approach. The source code is available at \href{https://github.com/lixsh6/Tencent_wsdm_cup2023/tree/main/pytorch_unbias}{https://github.com/lixsh6/Tencent\_wsdm\_cup2023}

cs.IR↗

arXiv2023

Uniform tensor clustering by jointly exploring sample affinities of various orders

Conventional clustering methods based on pairwise affinity usually suffer from the concentration effect while processing huge dimensional features yet low sample sizes data, resulting in inaccuracy to encode the sample proximity and suboptimal performance in clustering. To address this issue, we propose a unified tensor clustering method (UTC) that characterizes sample proximity using multiple samples' affinity, thereby supplementing rich spatial sample distributions to boost clustering. Specifically, we find that the triadic tensor affinity can be constructed via the Khari-Rao product of two affinity matrices. Furthermore, our early work shows that the fourth-order tensor affinity is defined by the Kronecker product. Therefore, we utilize arithmetical products, Khatri-Rao and Kronecker products, to mathematically integrate different orders of affinity into a unified tensor clustering framework. Thus, the UTC jointly learns a joint low-dimensional embedding to combine various orders. Finally, a numerical scheme is designed to solve the problem. Experiments on synthetic datasets and real-world datasets demonstrate that 1) the usage of high-order tensor affinity could provide a supplementary characterization of sample proximity to the popular affinity matrix; 2) the proposed method of UTC is affirmed to enhance clustering by exploiting different order affinities when processing high-dimensional data.

cs.LG↗

arXiv2023

Thermo-optic phase shifter based on hydrogen-doped indium oxide microheater

Thermo-optic (TO) phase shifters are very fundamental units in large-scale active silicon photonic integrated circuits (PICs). However, due to the limitation of microheater materials with a trade-off between heating efficiency and absorption loss, designs reported so far typically suffer from slow response time, high power consumption, low yields, and so on. Here, we demonstrate an energy-efficient, fast-response, and low-loss TO phase shifter by introducing hydrogen-doped indium oxide (IHO) films as microheater, and the optimized electron concentration with enhanced mobility endows the IHO high conductivity as well as high near-infrared (NIR) transparency, which allow it to directly contact the silicon waveguide without any insulating layer for efficient tuning and fast response. The TO phase shifter achieves a sub-microsecond response time (970 ns/980 ns) with a π phase shift power consumption of 9.6 mW. And the insertion loss introduced by the IHO microheater is ~ 0.5 dB. The proposed IHO-based microheaters with compatible processing technology illustrate the great potential of such material in the application of large-scale silicon PICs.

physics.optics↗

arXiv2022

Weight-based Channel-model Matrix Framework provides a reasonable solution for EEG-based cross-dataset emotion recognition

Cross-dataset emotion recognition as an extremely challenging task in the field of EEG-based affective computing is influenced by many factors, which makes the universal models yield unsatisfactory results. Facing the situation that lacks EEG information decoding research, we first analyzed the impact of different EEG information(individual, session, emotion and trial) for emotion recognition by sample space visualization, sample aggregation phenomena quantification, and energy pattern analysis on five public datasets. Based on these phenomena and patterns, we provided the processing methods and interpretable work of various EEG differences. Through the analysis of emotional feature distribution patterns, the Individual Emotional Feature Distribution Difference(IEFDD) was found, which was also considered as the main factor of the stability for emotion recognition. After analyzing the limitations of traditional modeling approach suffering from IEFDD, the Weight-based Channel-model Matrix Framework(WCMF) was proposed. To reasonably characterize emotional feature distribution patterns, four weight extraction methods were designed, and the optimal was the correction T-test(CT) weight extraction method. Finally, the performance of WCMF was validated on cross-dataset tasks in two kinds of experiments that simulated different practical scenarios, and the results showed that WCMF had more stable and better emotion recognition ability.

eess.SP↗

arXiv2022

Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential

Direct policy search has been widely applied in modern reinforcement learning and continuous control. However, the theoretical properties of direct policy search on nonsmooth robust control synthesis have not been fully understood. The optimal $\mathcal{H}_\infty$ control framework aims at designing a policy to minimize the closed-loop $\mathcal{H}_\infty$ norm, and is arguably the most fundamental robust control paradigm. In this work, we show that direct policy search is guaranteed to find the global solution of the robust $\mathcal{H}_\infty$ state-feedback control design problem. Notice that policy search for optimal $\mathcal{H}_\infty$ control leads to a constrained nonconvex nonsmooth optimization problem, where the nonconvex feasible set consists of all the policies stabilizing the closed-loop dynamics. We show that for this nonsmooth optimization problem, all Clarke stationary points are global minimum. Next, we identify the coerciveness of the closed-loop $\mathcal{H}_\infty$ objective function, and prove that all the sublevel sets of the resultant policy search problem are compact. Based on these properties, we show that Goldstein's subgradient method and its implementable variants can be guaranteed to stay in the nonconvex feasible set and eventually find the global optimal solution of the $\mathcal{H}_\infty$ state-feedback synthesis problem. Our work builds a new connection between nonconvex nonsmooth optimization theory and robust control, leading to an interesting global convergence result for direct policy search on optimal $\mathcal{H}_\infty$ synthesis.

math.OC↗

arXiv2022

Titanium doped kagome superconductor CsV3-xTixSb5 and two distinct phases

The vanadium-based kagome superconductor CsV3Sb5 has attracted tremendous attention due to its unexcepted anomalous Hall effect (AHE), charge density waves (CDWs), nematicity, and a pseudogap pair density wave (PDW) coexisting with unconventional strong-coupling superconductivity (SC). The origins of CDWs, unconventional SC, and their correlation with different electronic states in this kagome system are of great significance, but so far, are still under debate. Chemical doping in the kagome layer provides one of the most direct ways to reveal the intrinsic physics, but remains unexplored. Here, we report, for the first time, the synthesis of Ti-substituted CsV3Sb5 single crystals and its rich phase diagram mapping the evolution of intertwining electronic states. The Ti atoms directly substitute for V in the kagome layers. CsV3-xTixSb5 shows two distinct SC phases upon substitution. The Ti slightly-substituted phase displays an unconventional V-shaped SC gap, coexisting with weakening CDW, PDW, AHE, and nematicity. The Ti highly-substituted phase has a U-shaped SC gap concomitant with a short-range rotation symmetry breaking CDW, while long-range CDW, twofold symmetry of in-plane resistivity, AHE, and PDW are absent. Furthermore, we also demonstrate the chemical substitution of V atoms with other elements such as Cr and Nb, showing a different modulation on the SC phase and CDWs. These findings open up a way to synthesise a new family of doped CsV3Sb5 materials, and further representing a new platform for tuning the different correlated electronic states and superconducting pairing in kagome superconductors.

cond-mat.supr-con↗

arXiv2022

Performance forecasts for the primordial gravitational wave detection pipelines for AliCPT-1

AliCPT is the first Chinese cosmic microwave background (CMB) experiment which will make the most precise measurements of the CMB polarization in the northern hemisphere. The key science goal for AliCPT is the detection of primordial gravitational waves (PGWs). It is well known that an epoch of cosmic inflation, in the very early universe, can produce PGWs, which leave an imprint on the CMB in form of odd parity $B$-mode polarization. In this work, we study the performance of the component separation and parameter estimation pipelines in context of constraining the value of the tensor-to-scalar ratio. Based on the simulated data for one observation season, we compare five different pipelines with different working principles. Three pipelines perform component separation at map or spectra level before estimating $r$ from the cleaned spectra, while the other two pipelines performs a global fit for both foreground parameters and $r$. We also test different methods to account for the effects of time stream filtering systematics. This work shows that our pipelines provide consistent and robust constraints on the tensor-to-scalar ratio and a consistent sensitivity $σ(r) \sim 0.02$. This showcases the potential of precise $B$-mode polarization measurement with AliCPT-1. AliCPT will provide a powerful opportunity to detect PGWs, which is complementary with various ground-based CMB experiments in the southern hemisphere.

astro-ph.CO↗

arXiv2022

Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and reinforcement learning. This article surveys some of the recent developments on policy optimization, a gradient-based iterative approach for feedback control synthesis, popularized by successes of reinforcement learning. We take an interdisciplinary perspective in our exposition that connects control theory, reinforcement learning, and large-scale optimization. We review a number of recently-developed theoretical results on the optimization landscape, global convergence, and sample complexity of gradient-based methods for various continuous control problems such as the linear quadratic regulator (LQR), $\mathcal{H}_\infty$ control, risk-sensitive control, linear quadratic Gaussian (LQG) control, and output feedback synthesis. In conjunction with these optimization results, we also discuss how direct policy optimization handles stability and robustness concerns in learning-based control, two main desiderata in control engineering. We conclude the survey by pointing out several challenges and opportunities at the intersection of learning and control.

math.OC↗

arXiv2022

Gravitational wave source clustering in the luminosity distance space with the presence of peculiar velocity and lensing errors

GW number count can be used as a novel tracer of the large scale structure (LSS) in the luminosity distance space (LDS), just like galaxies in the redshift space. It is possible to obtain the $D_L-D_A$ duality relation with clustering effect. However, several LSS induced errors will contaminate the GW luminosity distance measurement, such as the peculiar velocity dispersion error of the host galaxy as well as the foreground lensing magnification. The distance uncertainties induced from these effects will degrade the GW clustering from a spectroscopic-like data down to a photometric-like data. In this paper, we investigate how these LSS induced distance errors modify our cosmological parameter precision inferred from the LDS clustering. We consider two of the next generation GW observatories, namely the Big Bang Observatory (BBO) and the Einstein Telescope (ET). We forecast the parameter estimation errors on the angular diameter distance $D_A$, luminosity distance space Hubble parameter $H_L$ and structure growth rate $f_Lσ_8$ with a Fisher matrix method. Generally speaking, the GW source clustering data can be used for cosmological studies below $D_L<5$ Gpc, while above this scale the lensing errors will increase significantly. We find that for BBO, it is possible to constrain the cosmological parameters with a relative error of $10^{-3}$ to $10^{-2}$ below $D_L<5$ Gpc. The velocity dispersion error is dominant in the low luminosity distance range, while the lensing magnification error is the bottleneck in the large luminosity distance range. To reduce the lensing error, we assumed a $50\%$ delensing efficiency. Even with this optimal assumption, the fractional error increased to $O(1)$ at luminosity distance $D_L=25$ Gpc. The results for ET are similar as those from BBO. Due to the GW source number in ET is less than that from BBO, the corresponding results also get a bit worse.

astro-ph.CO↗

arXiv2022

Numerical implementation of the Cubic Galileon model in PINOCCHIO

We present a perturbative treatment of nonlinear galaxy clustering in the context of the cubic Galileon modified gravity model, in terms of 2nd order Lagrangian Perturbation theory and an extension of ellipsoidal collapse that includes Vainshtein screening. We numerically implement such prescriptions in the approximate PINOCCHIO code, and use it to generate realisations of the matter density field and halo catalogues with different prescriptions for ellipsoidal collapse. We investigate the impact of three different approximations in the computation of collapse times on the halo mass function, halo bias and matter power spectrum. In the halo mass function, both the modified gravity effect and the screening effect are significant in the high mass end, similar to what is found for other MG models. We perform a comparison with N-body simulations to assess the validity of our approach, and show that we can reproduce the same trend observed in simulations for all quantities considered. With a simple modification to the grouping algorithm of PINOCCHIO to take into account the gravity modification, and without the need to re-calibrate the algorithm, we show that we can reproduce the linear halo bias and the mildly-nonlinear matter power spectrum of simulations with good accuracy, especially for the implementation with Vainshtein screening. We stress that, while approximate, our method is orders of magnitude faster than a full N-body simulation, making it an optimal tool for the quick generation of large sets of halo catalogues for cosmological observables.

astro-ph.CO↗

arXiv2022

LitePIG: A Lite Parameter Inference system for the Gravitational wave in the millihertz band

We present a python based parameter inference system for the gravitational wave (GW) measured in the millihertz band. This system includes the following features: the GW waveform originated from the massive black hole binaries (MBHB), the stationary instrumental gaussian noise, the higher-order harmonic modes, the full response function from the time delay interferometry (TDI) and the gaussian likelihood function with the dynamic nested parameter sampler. In particular, we highlight the role of higher-order modes. By including these modes, the luminosity distance estimation precision can be improved roughly by a factor of 50, compared with the case with only the leading order ($\ell=2,|m|=2$) mode. This is due to the response function of different harmonic modes on the inclination angle are different. Hence, it can help to break the distance-inclination degeneracy. Furthermore, we show the robustness of testing general relativity (GR) by using the higher-order harmonics. Our results show that the GW from MBHB can simultaneously constrain four of the higher harmonic amplitudes (deviation from GR) with a precision of $c_{21}=0.54^{+0.61}_{-0.82}$, $c_{32}=-0.65^{+0.22}_{-0.08}$, $c_{33}=0.56^{+0.60}_{-0.76}$ and $c_{44}=1.57^{+2.34}_{-1.90}$, respectively.

astro-ph.IM↗

arXiv2022

Model-Free $μ$ Synthesis via Adversarial Reinforcement Learning

Motivated by the recent empirical success of policy-based reinforcement learning (RL), there has been a research trend studying the performance of policy-based RL methods on standard control benchmark problems. In this paper, we examine the effectiveness of policy-based RL methods on an important robust control problem, namely $μ$ synthesis. We build a connection between robust adversarial RL and $μ$ synthesis, and develop a model-free version of the well-known $DK$-iteration for solving state-feedback $μ$ synthesis with static $D$-scaling. In the proposed algorithm, the $K$ step mimics the classical central path algorithm via incorporating a recently-developed double-loop adversarial RL method as a subroutine, and the $D$ step is based on model-free finite difference approximation. Extensive numerical study is also presented to demonstrate the utility of our proposed model-free algorithm. Our study sheds new light on the connections between adversarial RL and robust control.

cs.LG↗

arXiv2022

Energy Minimization for Federated Asynchronous Learning on Battery-Powered Mobile Devices via Application Co-running

Energy is an essential, but often forgotten aspect in large-scale federated systems. As most of the research focuses on tackling computational and statistical heterogeneity from the machine learning algorithms, the impact on the mobile system still remains unclear. In this paper, we design and implement an online optimization framework by connecting asynchronous execution of federated training with application co-running to minimize energy consumption on battery-powered mobile devices. From a series of experiments, we find that co-running the training process in the background with foreground applications gives the system a deep energy discount with negligible performance slowdown. Based on these results, we first study an offline problem assuming all the future occurrences of applications are available, and propose a dynamic programming-based algorithm. Then we propose an online algorithm using the Lyapunov framework to explore the solution space via the energy-staleness trade-off. The extensive experiments demonstrate that the online optimization framework can save over 60% energy with 3 times faster convergence speed compared to the previous schemes.

cs.DC↗

arXiv2022

Exact Formulas for Finite-Time Estimation Errors of Decentralized Temporal Difference Learning with Linear Function Approximation

In this paper, we consider the policy evaluation problem in multi-agent reinforcement learning (MARL) and derive exact closed-form formulas for the finite-time mean-squared estimation errors of decentralized temporal difference (TD) learning with linear function approximation. Our analysis hinges upon the fact that the decentralized TD learning method can be viewed as a Markov jump linear system (MJLS). Then standard MJLS theory can be applied to quantify the mean and covariance matrix of the estimation error of the decentralized TD method at every time step. Various implications of our exact formulas on the algorithm performance are also discussed. An interesting finding is that under a necessary and sufficient stability condition, the mean-squared TD estimation error will converge to an exact limit at a specific exponential rate.

cs.LG↗

arXiv2022

Forecasts on CMB lensing observations with AliCPT-1

AliCPT-1 is the first Chinese CMB experiment aiming for high precision measurement of Cosmic Microwave Background B-mode polarization. The telescope, currently under deployment in Tibet, will observe in two frequency bands centered at 90 and 150 GHz. We forecast the CMB lensing reconstruction, lensing-galaxy as well as lensing-CIB (Cosmic Infrared Background) cross correlation signal-to-noise ratio (SNR) for AliCPT-1. We consider two stages with different integrated observation time, namely "4 module*yr" (first stage) and "48 module*yr" (final stage). For lensing reconstruction, we use three different quadratic estimators, namely temperature-only, polarization-only and minimum-variance estimators, using curved sky geometry. We take into account the impact of inhomogeneous hit counts as well as of the mean-field bias due to incomplete sky coverage. In the first stage, our results show that the 150 GHz channel is able to measure the lensing signal at $15σ$ significance with the minimum-variance estimator. In the final stage, the measurement significance will increase to $31σ$. We also combine the two frequency data in the harmonic domain to optimize the SNR. Our result show that the coadding procedure can significantly reduce the reconstruction bias in the multiple range l>800. Thanks to the high quality of the polarization data in the final stage of AliCPT-1, the EB estimator will dominate the lensing reconstruction in this stage. We also estimate the SNR of cross-correlations between AliCPT-1 CMB lensing and other tracers of the large scale structure of the universe. For its cross-correlation with DESI galaxies/quasars, we report the cross-correlation SNR = 10-20 for the 4 redshift bins at 0.05<z<2.1. In the first stage, the total SNR is about $32$. In the final stage, the lensing-galaxy cross-correlation can reach SNR=52.

astro-ph.CO↗

arXiv2022

Forecast of observing time delay of the strongly lensed quasars with Muztagh-Ata 1.93m telescope

As a completely independent method, the measurement of time delay of strongly lensed quasars (TDSL) are crucial to resolve the Hubble tension. Extensive monitoring is required but so far limited to a small sample of strongly lensed quasars. Together with several partner institutes, Beijing Normal University is constructing a 1.93m reflector telescope at the Muztagh-Ata site in west China, which has the world class observing conditions. The telescope will be equipped with both a three-channel imager/photometer which covers $3500-11000$ Angstrom wavelength band, and a low-medium resolution ($λ/δλ=500/2000/7500$) spectrograph. In this paper, we investigate the capability of Muztagh-Ata 1.93m telescope in measuring time delays of strongly lensed quasars. We generate mock strongly lensed quasar systems and light curves with microlensing effects based on five known strongly lensed quasars, i.e., RX J1131-1231, HE 0435-1223, PG 1115+080, WFI 2033-4723 and SDSS 1206+4332. In particular, RX J1131-1231 is generated with lens modeling in this work. Due to lack of enough information, we simulate the other 4 systems with the public data without lens modeling. According to simulations, for RX J1131-like systems (wide variation in time delay between images) the TDSL measurement can be achieved with the precision about $Δt=0.5$ day with 4 seasons campaign length and 1 day cadence. This accuracy is comparable to the up-coming TDCOSMO project. And it would be better when the campaign length keeps longer and with high cadence. As a result, the capability of Muztagh-Ata 1.93m telescope allows it to join the network of TDSL observatories. It will enrich the database for strongly lensed quasar observations and make more precise measurements of time delays, especially considering the unique coordinate of the site.

astro-ph.CO↗