arXiv subjects

Xingyu Zhou

Publications and source records attributed to Xingyu Zhou.

At least 91 records · Page 5Linked to original sources

arXiv2023

Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards

In this paper, we study the problem of (finite horizon tabular) Markov decision processes (MDPs) with heavy-tailed rewards under the constraint of differential privacy (DP). Compared with the previous studies for private reinforcement learning that typically assume rewards are sampled from some bounded or sub-Gaussian distributions to ensure DP, we consider the setting where reward distributions have only finite $(1+v)$-th moments with some $v \in (0,1]$. By resorting to robust mean estimators for rewards, we first propose two frameworks for heavy-tailed MDPs, i.e., one is for value iteration and another is for policy optimization. Under each framework, we consider both joint differential privacy (JDP) and local differential privacy (LDP) models. Based on our frameworks, we provide regret upper bounds for both JDP and LDP cases and show that the moment of distribution and privacy budget both have significant impacts on regrets. Finally, we establish a lower bound of regret minimization for heavy-tailed MDPs in JDP model by reducing it to the instance-independent lower bound of heavy-tailed multi-armed bandits in DP model. We also show the lower bound for the problem in LDP by adopting some private minimax methods. Our results reveal that there are fundamental differences between the problem of private RL with sub-Gaussian and that with heavy-tailed rewards.

cs.LG↗

arXiv2023

On Differentially Private Federated Linear Contextual Bandits

We consider cross-silo federated linear contextual bandit (LCB) problem under differential privacy, where multiple silos (agents) interact with the local users and communicate via a central server to realize collaboration while without sacrificing each user's privacy. We identify three issues in the state-of-the-art: (i) failure of claimed privacy protection and (ii) incorrect regret bound due to noise miscalculation and (iii) ungrounded communication cost. To resolve these issues, we take a two-step principled approach. First, we design an algorithmic framework consisting of a generic federated LCB algorithm and flexible privacy protocols. Then, leveraging the proposed framework, we study federated LCBs under two different privacy constraints. We first establish privacy and regret guarantees under silo-level local differential privacy, which fix the issues present in state-of-the-art algorithm. To further improve the regret performance, we next consider shuffle model of differential privacy, under which we show that our algorithm can achieve nearly ``optimal'' regret without a trusted server. We accomplish this via two different schemes -- one relies on a new result on privacy amplification via shuffling for DP mechanisms and another one leverages the integration of a shuffle protocol for vector sum into the tree-based mechanism, both of which might be of independent interest. Finally, we support our theoretical results with numerical evaluations over contextual bandit instances generated from both synthetic and real-life data.

cs.LG↗

arXiv2023

Provably Efficient Model-Free Algorithms for Non-stationary CMDPs

We study model-free reinforcement learning (RL) algorithms in episodic non-stationary constrained Markov Decision Processes (CMDPs), in which an agent aims to maximize the expected cumulative reward subject to a cumulative constraint on the expected utility (cost). In the non-stationary environment, reward, utility functions, and transition kernels can vary arbitrarily over time as long as the cumulative variations do not exceed certain variation budgets. We propose the first model-free, simulator-free RL algorithms with sublinear regret and zero constraint violation for non-stationary CMDPs in both tabular and linear function approximation settings with provable performance guarantees. Our results on regret bound and constraint violation for the tabular case match the corresponding best results for stationary CMDPs when the total budget is known. Additionally, we present a general framework for addressing the well-known challenges associated with analyzing non-stationary CMDPs, without requiring prior knowledge of the variation budget. We apply the approach for both tabular and linear approximation settings.

cs.LG↗

arXiv2023

On Private and Robust Bandits

We study private and robust multi-armed bandits (MABs), where the agent receives Huber's contaminated heavy-tailed rewards and meanwhile needs to ensure differential privacy. We first present its minimax lower bound, characterizing the information-theoretic limit of regret with respect to privacy budget, contamination level and heavy-tailedness. Then, we propose a meta-algorithm that builds on a private and robust mean estimation sub-routine \texttt{PRM} that essentially relies on reward truncation and the Laplace mechanism only. For two different heavy-tailed settings, we give specific schemes of \texttt{PRM}, which enable us to achieve nearly-optimal regret. As by-products of our main results, we also give the first minimax lower bound for private heavy-tailed MABs (i.e., without contamination). Moreover, our two proposed truncation-based \texttt{PRM} achieve the optimal trade-off between estimation accuracy, privacy and robustness. Finally, we support our theoretical results with experimental studies.

cs.LG↗

arXiv2023

A Cloud-Based Energy Management Strategy for Hybrid Electric City Bus Considering Real-Time Passenger Load Prediction

Electric city bus gains popularity in recent years for its low greenhouse gas emission, low noise level, etc. Different from a passenger car, the weight of a city bus varies significantly with different amounts of onboard passengers. After analyzing the importance of battery aging and passenger load effects on an optimal energy management strategy, this study introduces the passenger load prediction into the hybrid-electric city buses energy management problem, which is not well studied in the existing literature. The average model, Decision Tree, Gradient Boost Decision Tree, and Neural Networks models are compared in the passenger load prediction. The Gradient Boost Decision Tree model is selected due to its best accuracy and high stability. Given the predicted passenger load, a dynamic programming algorithm determines the optimal power demand for supercapacitor and battery by optimizing the battery aging and energy usage leveraging cloud techniques. Then, rule extraction is conducted on dynamic programming results, and the rule is real-time loaded to the vehicle onboard controller to handle prediction errors and uncertainties. The proposed cloud-based Dynamic Programming and rule extraction framework with the passenger load prediction show 4% and 11% lower bus operating costs in off-peak and peak hours, respectively. The operating cost by the proposed framework is less than 1% of the dynamic programming with the true passenger load information.

eess.SY↗

arXiv2023

(Private) Kernelized Bandits with Distributed Biased Feedback

In this paper, we study kernelized bandits with distributed biased feedback. This problem is motivated by several real-world applications (such as dynamic pricing, cellular network configuration, and policy making), where users from a large population contribute to the reward of the action chosen by a central entity, but it is difficult to collect feedback from all users. Instead, only biased feedback (due to user heterogeneity) from a subset of users may be available. In addition to such partial biased feedback, we are also faced with two practical challenges due to communication cost and computation complexity. To tackle these challenges, we carefully design a new \emph{distributed phase-then-batch-based elimination (\texttt{DPBE})} algorithm, which samples users in phases for collecting feedback to reduce the bias and employs \emph{maximum variance reduction} to select actions in batches within each phase. By properly choosing the phase length, the batch size, and the confidence width used for eliminating suboptimal actions, we show that \texttt{DPBE} achieves a sublinear regret of $\tilde{O}(T^{1-α/2}+\sqrt{γ_T T})$, where $α\in (0,1)$ is the user-sampling parameter one can tune. Moreover, \texttt{DPBE} can significantly reduce both communication cost and computation complexity in distributed kernelized bandits, compared to some variants of the state-of-the-art algorithms (originally developed for standard kernelized bandits). Furthermore, by incorporating various \emph{differential privacy} models (including the central, local, and shuffle models), we generalize \texttt{DPBE} to provide privacy guarantees for users participating in the distributed learning process. Finally, we conduct extensive simulations to validate our theoretical results and evaluate the empirical performance.

cs.LG↗

arXiv2023

Provably Efficient Model-Free Constrained RL with Linear Function Approximation

We study the constrained reinforcement learning problem, in which an agent aims to maximize the expected cumulative reward subject to a constraint on the expected total value of a utility function. In contrast to existing model-based approaches or model-free methods accompanied with a `simulator', we aim to develop the first model-free, simulator-free algorithm that achieves a sublinear regret and a sublinear constraint violation even in large-scale systems. To this end, we consider the episodic constrained Markov decision processes with linear function approximation, where the transition dynamics and the reward function can be represented as a linear function of some known feature mapping. We show that $\tilde{\mathcal{O}}(\sqrt{d^3H^3T})$ regret and $\tilde{\mathcal{O}}(\sqrt{d^3H^3T})$ constraint violation bounds can be achieved, where $d$ is the dimension of the feature mapping, $H$ is the length of the episode, and $T$ is the total number of steps. Our bounds are attained without explicitly estimating the unknown transition model or requiring a simulator, and they depend on the state space only through the dimension of the feature mapping. Hence our bounds hold even when the number of states goes to infinity. Our main results are achieved via novel adaptations of the standard LSVI-UCB algorithms. In particular, we first introduce primal-dual optimization into the LSVI-UCB algorithm to balance between regret and constraint violation. More importantly, we replace the standard greedy selection with respect to the state-action function in LSVI-UCB with a soft-max policy. This turns out to be key in establishing uniform concentration for the constrained case via its approximation-smoothness trade-off. We also show that one can achieve an even zero constraint violation while still maintaining the same order with respect to $T$.

cs.LG↗

arXiv2022

Grant-Free NOMA-OTFS Paradigm: Enabling Efficient Ubiquitous Access for LEO Satellite Internet-of-Things

With the blooming of Internet-of-Things (IoT), we are witnessing an explosion in the number of IoT terminals, triggering an unprecedented demand for ubiquitous wireless access globally. In this context, the emerging low-Earth-orbit satellites (LEO-SATs) have been regarded as a promising enabler to complement terrestrial wireless networks in providing ubiquitous connectivity and bridging the ever-growing digital divide in the expected next-generation wireless communications. Nevertheless, the harsh conditions posed by LEO-SATs have imposed significant challenges to the current multiple access (MA) schemes and led to an emerging paradigm shift in system design. In this article, we first provide a comprehensive overview of the state-of-the-art MA schemes and investigate their limitations in the context of LEO-SATs. To this end, we propose a novel next generation MA (NGMA), which amalgamates the grant-free non-orthogonal multiple access (GF-NOMA) mechanism and the orthogonal time frequency space (OTFS) waveform, for simplifying the connection procedure with reduced access latency and enhanced Doppler-robustness. Critical open challenging issues and future directions are finally presented for further technical development.

eess.SP↗

arXiv2022

Active Terminal Identification, Channel Estimation, and Signal Detection for Grant-Free NOMA-OTFS in LEO Satellite Internet-of-Things

This paper investigates the massive connectivity of low Earth orbit (LEO) satellite-based Internet-of-Things (IoT) for seamless global coverage. We propose to integrate the grant-free non-orthogonal multiple access (GF-NOMA) paradigm with the emerging orthogonal time frequency space (OTFS) modulation to accommodate the massive IoT access, and mitigate the long round-trip latency and severe Doppler effect of terrestrial-satellite links (TSLs). On this basis, we put forward a two-stage successive active terminal identification (ATI) and channel estimation (CE) scheme as well as a low-complexity multi-user signal detection (SD) method. Specifically, at the first stage, the proposed training sequence aided OTFS (TS-OTFS) data frame structure facilitates the joint ATI and coarse CE, whereby both the traffic sparsity of terrestrial IoT terminals and the sparse channel impulse response are leveraged for enhanced performance. Moreover, based on the single Doppler shift property for each TSL and sparsity of delay-Doppler domain channel, we develop a parametric approach to further refine the CE performance. Finally, a least square based parallel time domain SD method is developed to detect the OTFS signals with relatively low complexity. Simulation results demonstrate the superiority of the proposed methods over the state-of-the-art solutions in terms of ATI, CE, and SD performance confronted with the long round-trip latency and severe Doppler effect.

cs.IT↗

arXiv2022

Stellar Flyby Analysis for Spiral Arm Hosts with Gaia DR3

Scattered light imaging studies have detected nearly two dozen spiral arm systems in circumstellar disks, yet the formation mechanisms for most of them are still under debate. Although existing studies can use motion measurements to distinguish leading mechanisms such as planet-disk interaction and disk self-gravity, close-in stellar flybys can induce short-lived spirals and even excite arm-driving planets into highly eccentric orbits. With unprecedented stellar location and proper motion measurements from Gaia DR3, here we study for known spiral arm systems their flyby history with their stellar neighbours by formulating an analytical on-sky flyby framework. For stellar neighbors currently located within 10 pc from the spiral hosts, we restrict the flyby time to be within the past $10^4$ yr and the flyby distance to be within $10$ times the disk extent in scattered light. Among a total of $12570$ neighbors that are identified in Gaia DR3 for $20$ spiral systems, we do not identify credible flyby candidates for isolated systems. Our analysis suggests that close-in recent flyby is not the dominant formation mechanism for isolated spiral systems in scattered light.

astro-ph.EP↗

arXiv2022

Spectroscopic Confirmation of a Population of Isolated, Intermediate-Mass YSOs

Wide-field searches for young stellar objects (YSOs) can place useful constraints on the prevalence of clustered versus distributed star formation. The Spitzer/IRAC Candidate YSO (SPICY) catalog is one of the largest compilations of such objects (~120,000 candidates in the Galactic midplane). Many SPICY candidates are spatially clustered, but, perhaps surprisingly, approximately half the candidates appear spatially distributed. To better characterize this unexpected population and confirm its nature, we obtained Palomar/DBSP spectroscopy for 26 of the optically-bright (G<15 mag) "isolated" YSO candidates. We confirm the YSO classifications of all 26 sources based on their positions on the Hertzsprung-Russell diagram, H and Ca II line-emission from over half the sample, and robust detection of infrared excesses. This implies a contamination rate of <10% for SPICY stars that meet our optical selection criteria. Spectral types range from B4 to K3, with A-type stars most common. Spectral energy distributions, diffuse interstellar bands, and Galactic extinction maps indicate moderate to high extinction. Stellar masses range from ~1 to 7 $M_\odot$, and the estimated accretion rates, ranging from $3\times10^{-8}$ to $3\times10^{-7}$ $M_\odot$ yr$^{-1}$, are typical for YSOs in this mass range. The 3D spatial distribution of these stars, based on Gaia astrometry, reveals that the "isolated" YSOs are not evenly distributed in the Solar neighborhood but are concentrated in kpc-scale dusty Galactic structures that also contain the majority of the SPICY YSO clusters. Thus, the processes that produce large Galactic star-forming structures may yield nearly as many distributed as clustered YSOs.

astro-ph.GA↗

arXiv2022

Temporal and Spatial Chaos of RN-AdS Black Holes Immersed in Perfect Fluid Dark Matter

We investigate the thermodynamic chaos of RN-AdS black holes immersed in Perfect Fluid Dark Matter by considering the dynamical equations of the fluid system evolved in the spinodal region. Based on the Melnikov method, it is shown that there exists a critical amplitude that affects the temporal chaos. And the influence of black holes charge and state parameter on the critical amplitude is investigated with specific initial temperature. Then, for inevitable spatial chaos, three different types of portraits are discssued according to the difference between the phase transition pressure and the ambient pressure. Additionally, we check the local equilibrium near saddle points which shows that spatial chaos always exists regardless of the perturbation intensity.

gr-qc↗

arXiv2022

Diagnosing FUor-like Sources: The Parameter Space of Viscously Heated Disks in the Optical and Near-IR

FU Ori type objects (FUors) are decades-long outbursts of accretion onto young stars that are strong enough to viscously heat disks so that the disk outshines the central star. We construct models for FUor objects by calculating emission components from a steady-state viscous accretion disk, a passively-heated dusty disk, magnetospheric accretion columns, and the stellar photosphere. We explore the parameter space of the accretion rate and stellar mass to investigate implications on the optical and near-infrared spectral energy distribution and spectral lines. The models are validated by fitting to multi-wavelength photometry of three confirmed FUor objects, FU Ori, V883 Ori and HBC 722 and then comparing the predicted spectrum to observed optical and infrared spectra. The brightness ratio between the viscous disk and the stellar photosphere, $η$, provides an important guide for identifying viscous accretion disks, with $η=1$ ("transition line") and $η=5$ ("sufficient dominance line") marking turning points in diagnostics, evaluated here in the near-infrared. These turning points indicate the emergence and complete development of FUor-characteristic strong CO absorption, weak metallic absorption, the triangular spectral continuum shape in the $H$-band, and location in color-magnitude diagrams. Lower stellar mass $M_*$ and higher accretion rate $\dot{M}$ lead to larger $η$; for $M_*=0.3~{\rm M_\odot}$, $η=1$ corresponds to $\dot{M}=2\times10^{-7}~{\rm M_\odot}/$yr and $η=5$ to $\dot{M}=6\times10^{-7}~{\rm M_\odot}/$yr. The sufficient dominance line also coincides with the expected accretion rate where accreting material directly reaches the star. We discuss implications of the models on extinction diagnostics, FUor brightening timescales, viscous disks during initial protostellar growth, and eruptive young stellar objects (YSO) associated with FUors.

astro-ph.SR↗

arXiv2022

Interference Constrained Beam Alignment for Time-Varying Channels via Kernelized Bandits

To fully utilize the abundant spectrum resources in millimeter wave (mmWave), Beam Alignment (BA) is necessary for large antenna arrays to achieve large array gains. In practical dynamic wireless environments, channel modeling is challenging due to time-varying and multipath effects. In this paper, we formulate the beam alignment problem as a non-stationary online learning problem with the objective to maximize the received signal strength under interference constraint. In particular, we employ the non-stationary kernelized bandit to leverage the correlation among beams and model the complex beamforming and multipath channel functions. Furthermore, to mitigate interference to other user equipment, we leverage the primal-dual method to design a constrained UCB-type kernelized bandit algorithm. Our theoretical analysis indicates that the proposed algorithm can adaptively adjust the beam in time-varying environments, such that both the cumulative regret of the received signal and constraint violations have sublinear bounds with respect to time. This result is of independent interest for applications such as adaptive pricing and news ranking. In addition, the algorithm assumes the channel is a black-box function and does not require any prior knowledge for dynamic channel modeling, and thus is applicable in a variety of scenarios. We further show that if the information about the channel variation is known, the algorithm will have better theoretical guarantees and performance. Finally, we conduct simulations to highlight the effectiveness of the proposed algorithm.

cs.NI↗

arXiv2022

Model-Driven Deep Learning-Based MIMO-OFDM Detector: Design, Simulation, and Experimental Results

Multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM), a fundamental transmission scheme, promises high throughput and robustness against multipath fading. However, these benefits rely on the efficient detection strategy at the receiver and come at the expense of the extra bandwidth consumed by the cyclic prefix (CP). We use the iterative orthogonal approximate message passing (OAMP) algorithm in this paper as the prototype of the detector because of its remarkable potential for interference suppression. However, OAMP is computationally expensive for the matrix inversion per iteration. We replace the matrix inversion with the conjugate gradient (CG) method to reduce the complexity of OAMP. We further unfold the CG-based OAMP algorithm into a network and tune the critical parameters through deep learning (DL) to enhance detection performance. Simulation results and complexity analysis show that the proposed scheme has significant gain over other iterative detection methods and exhibits comparable performance to the state-of-the-art DL-based detector at a reduced computational cost. Furthermore, we design a highly efficient CP-free MIMO-OFDM receiver architecture to remove the CP overhead. This architecture first eliminates the intersymbol interference by buffering the previously recovered data and then detects the signal using the proposed detector. Numerical experiments demonstrate that the designed receiver offers a higher spectral efficiency than traditional receivers. Finally, over-the-air tests verify the effectiveness and robustness of the proposed scheme in realistic environments.

cs.IT↗

arXiv2022

Distributed Differential Privacy in Multi-Armed Bandits

We consider the standard $K$-armed bandit problem under a distributed trust model of differential privacy (DP), which enables to guarantee privacy without a trustworthy server. Under this trust model, previous work largely focus on achieving privacy using a shuffle protocol, where a batch of users data are randomly permuted before sending to a central server. This protocol achieves ($ε,δ$) or approximate-DP guarantee by sacrificing an additional additive $O\!\left(\!\frac{K\log T\sqrt{\log(1/δ)}}ε\!\right)\!$ cost in $T$-step cumulative regret. In contrast, the optimal privacy cost for achieving a stronger ($ε,0$) or pure-DP guarantee under the widely used central trust model is only $Θ\!\left(\!\frac{K\log T}ε\!\right)\!$, where, however, a trusted server is required. In this work, we aim to obtain a pure-DP guarantee under distributed trust model while sacrificing no more regret than that under central trust model. We achieve this by designing a generic bandit algorithm based on successive arm elimination, where privacy is guaranteed by corrupting rewards with an equivalent discrete Laplace noise ensured by a secure computation protocol. We also show that our algorithm, when instantiated with Skellam noise and the secure protocol, ensures \emph{Rényi differential privacy} -- a stronger notion than approximate DP -- under distributed trust model with a privacy cost of $O\!\left(\!\frac{K\sqrt{\log T}}ε\!\right)\!$.

cs.LG↗

arXiv2022

Learning to Control under Time-Varying Environment

This paper investigates the problem of regret minimization in linear time-varying (LTV) dynamical systems. Due to the simultaneous presence of uncertainty and non-stationarity, designing online control algorithms for unknown LTV systems remains a challenging task. At a cost of NP-hard offline planning, prior works have introduced online convex optimization algorithms, although they suffer from nonparametric rate of regret. In this paper, we propose the first computationally tractable online algorithm with regret guarantees that avoids offline planning over the state linear feedback policies. Our algorithm is based on the optimism in the face of uncertainty (OFU) principle in which we optimistically select the best model in a high confidence region. Our algorithm is then more explorative when compared to previous approaches. To overcome non-stationarity, we propose either a restarting strategy (R-OFU) or a sliding window (SW-OFU) strategy. With proper configuration, our algorithm is attains sublinear regret $O(T^{2/3})$. These algorithms utilize data from the current phase for tracking variations on the system dynamics. We corroborate our theoretical findings with numerical experiments, which highlight the effectiveness of our methods. To the best of our knowledge, our study establishes the first model-based online algorithm with regret guarantees under LTV dynamical systems.

cs.LG↗

arXiv2022

The Ages of Optically Bright Sub-Clusters in the Serpens Star-Forming Region

The Serpens Molecular Cloud is one of the most active star-forming regions within 500 pc, with over one thousand of YSOs at different evolutionary stages. The ages of the member stars inform us about the star formation history of the cloud. In this paper, we develop a spectral energy distribution (SED) fitting method for nearby evolved (diskless) young stars from members of the Pleiades to estimate their ages, with a temperature scale adopted from APOGEE spectra. When compared with literature temperatures of selected YSOs in Orion, the SED fits to cool (<5000 K) stars have temperatures that differ by an average of <~ 50 K and have a scatter of ~ 210 K for both disk-hosting and diskless stars. We then apply this method to YSOs in the Serpens Molecular Cloud to estimate ages of optical members previously identified from Gaia DR2 astrometry data. The optical members in Serpens are concentrated in different subgroups with ages from ~4 Myr to ~22 Myr; the youngest clusters, W40 and Serpens South, are dusty regions that lack enough optical members to be included in this analysis. These ages establish that the Serpens Molecular Cloud has been forming stars for much longer than has been inferred from infrared surveys.

astro-ph.SR↗