Searcharxiv⌕ Search

arXiv subjects

Cheng Zhang

Publications and source records attributed to Cheng Zhang.

At least 289 records · Page 16Linked to original sources
arXiv2024

Joint Port Selection Based Channel Acquisition for FDD Cell-Free Massive MIMO

In frequency division duplexing (FDD) cell-free massive MIMO, the acquisition of the channel state information (CSI) is very challenging because of the large overhead required for the training and feedback of the downlink channels of multiple cooperating base stations (BSs). In this paper, for systems with partial uplink-downlink channel reciprocity, and a general spatial domain channel model with variations in the average port power and correlation among port coefficients, we propose a joint-port-selection-based CSI acquisition and feedback scheme for the downlink transmission with zero-forcing precoding. The scheme uses an eigenvalue-decomposition-based transformation to reduce the feedback overhead by exploring the port correlation. We derive the sum-rate of the system for any port selection. Based on the sum-rate result, we propose a low-complexity greedy-search-based joint port selection (GS-JPS) algorithm. Moreover, to adapt to fast time-varying scenarios, a supervised deep learning-enhanced joint port selection (DL-JPS) algorithm is proposed. Simulations verify the effectiveness of our proposed schemes and their advantage over existing port-selection channel acquisition schemes.

cs.IT↗
arXiv2024

ProAgent: Building Proactive Cooperative Agents with Large Language Models

Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems. Current approaches to developing cooperative agents rely primarily on learning-based methods, whose policy generalization depends heavily on the diversity of teammates they interact with during the training phase. Such reliance, however, constrains the agents' capacity for strategic adaptation when cooperating with unfamiliar teammates, which becomes a significant challenge in zero-shot coordination scenarios. To address this challenge, we propose ProAgent, a novel framework that harnesses large language models (LLMs) to create proactive agents capable of dynamically adapting their behavior to enhance cooperation with teammates. ProAgent can analyze the present state, and infer the intentions of teammates from observations. It then updates its beliefs in alignment with the teammates' subsequent actual behaviors. Moreover, ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various of coordination scenarios. Experimental evaluations conducted within the Overcooked-AI environment unveil the remarkable performance superiority of ProAgent, outperforming five methods based on self-play and population-based training when cooperating with AI agents. Furthermore, in partnered with human proxy models, its performance exhibits an average improvement exceeding 10% compared to the current state-of-the-art method. For more information about our project, please visit~\url{https://pku-proagent.github.io}.

cs.AI↗
arXiv2024

Three-state coherent control using narrowband and passband sequences

In this work, we propose a comprehensive design for narrowband and passband composite pulse sequences by involving the dynamics of all states in the three-state system. The design is quite universal as all pulse parameters can be freely employed to modify the coefficients of error terms. Two modulation techniques, the strength and phase modulations, are used to achieve arbitrary population transfer with a desired excitation profile, while the system keeps minimal leakage to the third state. Furthermore, the current sequences are capable of tolerating inaccurate waveforms, detunings errors, and work well when rotating wave approximation is not strictly justified. Therefore, this work provides versatile adaptability for shaping various excitation profiles in both narrowband and passband sequences.

quant-ph↗
arXiv2024

Entropy-based Probing Beam Selection and Beam Prediction via Deep Learning

Hierarchical beam search in mmWave communications incurs substantial training overhead, necessitating deep learning-enabled beam predictions to effectively leverage channel priors and mitigate this overhead. In this study, we introduce a comprehensive probabilistic model of power distribution in beamspace, and formulate the joint optimization problem of probing beam selection and probabilistic beam prediction as an entropy minimization problem. Then, we propose a greedy scheme to iteratively and alternately solve this problem, where a transformer-based beam predictor is trained to estimate the conditional power distribution based on the probing beams and user location within each iteration, and the trained predictor selects an unmeasured beam that minimizes the entropy of remaining beams. To further reduce the number of interactions and the computational complexity of the iterative scheme, we propose a two-stage probing beam selection scheme. Firstly, probing beams are selected from a location-specific codebook designed by an entropy-based criterion, and predictions are made with corresponding feedback. Secondly, the optimal beam is identified using additional probing beams with the highest predicted power values. Simulation results demonstrate the superiority of the proposed schemes compared to hierarchical beam search and beam prediction with uniform probing beams.

cs.IT↗
arXiv2023

Properties of new even and odd nonlinear coherent states with different parameters

We construct a class of nonlinear coherent states (NLCSs) by introducing a more general nonlinear function and study their non-classical properties, specifically the second-order correlation function $g^{(2)}(0)$, Mandel parameter $Q$, squeezing, amplitude squared squeezing and Wigner function of the optical field. The results indicate that the non-classical properties of the new types of even and odd NLCSs crucially depend on nonlinear functions. More concretely, we find that the new even NLCSs could exhibit the photon-bunching effect whereas the new odd NLCSs could show photon-antibunching effect. The degree of squeezing is also significantly affected by the parameter selection of these NLCSs. By employing various forms of nonlinear functions, it becomes possible to construct NLCSs with diverse properties, thereby providing a theoretical foundation for corresponding experimental investigations.

quant-ph↗
arXiv2023

Tail-Learning: Adaptive Learning Method for Mitigating Tail Latency in Autonomous Edge Systems

In the realm of edge computing, the increasing demand for high Quality of Service (QoS), particularly in dynamic multimedia streaming applications (e.g., Augmented Reality/Virtual Reality and online gaming), has prompted the need for effective solutions. Nevertheless, adopting an edge paradigm grounded in distributed computing has exacerbated the issue of tail latency. Given a limited variety of multimedia services supported by edge servers and the dynamic nature of user requests, employing traditional queuing methods to model tail latency in distributed edge computing is challenging, substantially exacerbating head-of-line (HoL) blocking. In response to this challenge, we have developed a learning-based scheduling method to mitigate the overall tail latency, which adaptively selects appropriate edge servers for execution as incoming distributed tasks vary with unknown size. To optimize the utilization of the edge computing paradigm, we leverage Laplace transform techniques to theoretically derive an upper bound for the response time of edge servers. Subsequently, we integrate this upper bound into reinforcement learning to facilitate tail learning and enable informed decisions for autonomous distributed scheduling. The experiment results demonstrate the efficiency in reducing tail latency compared to existing methods.

cs.DC↗
arXiv2023

BayesDAG: Gradient-Based Posterior Inference for Causal Discovery

Bayesian causal discovery aims to infer the posterior distribution over causal models from observed data, quantifying epistemic uncertainty and benefiting downstream tasks. However, computational challenges arise due to joint inference over combinatorial space of Directed Acyclic Graphs (DAGs) and nonlinear functions. Despite recent progress towards efficient posterior inference over DAGs, existing methods are either limited to variational inference on node permutation matrices for linear causal models, leading to compromised inference accuracy, or continuous relaxation of adjacency matrices constrained by a DAG regularizer, which cannot ensure resulting graphs are DAGs. In this work, we introduce a scalable Bayesian causal discovery framework based on a combination of stochastic gradient Markov Chain Monte Carlo (SG-MCMC) and Variational Inference (VI) that overcomes these limitations. Our approach directly samples DAGs from the posterior without requiring any DAG regularization, simultaneously draws function parameter samples and is applicable to both linear and nonlinear causal models. To enable our approach, we derive a novel equivalence to the permutation-based DAG learning, which opens up possibilities of using any relaxed gradient estimator defined over permutations. To our knowledge, this is the first framework applying gradient-based MCMC sampling for causal discovery. Empirical evaluation on synthetic and real-world datasets demonstrate our approach's effectiveness compared to state-of-the-art baselines.

cs.LG↗
arXiv2023

Vanishing of the anomalous Hall effect and enhanced carrier mobility in the spin-gapless ferromagnetic Mn2CoGa1-xAlx alloys

Spin gapless semiconductor (SGS) has attracted long attention since its theoretical prediction, while concrete experimental hints are still lack in the relevant Heusler alloys. Here in this work, by preparing the series alloys of Mn2CoGa1-xAlx (x=0, 0.25, 0.5, 0.75 and 1), we identified the vanishing of anomalous Hall effect in the ferromagnetic Mn2CoGa (or x=0.25) alloy in a wide temperature interval, accompanying with growing contribution from the ordinary Hall effect. As a result, comparatively low carrier density (1020 cm-3) and high carrier mobility (150 cm2/Vs) are obtained in Mn2CoGa (or x=0.25) alloy in the temperature range of 10-200K. These also lead to a large dip in the related magnetoresistance at low fields. While in high Al content, despite the magnetization behavior is not altered significantly, the Hall resistivity is instead dominated by the anomalous one, just analogous to that widely reported in Mn2CoAl. The distinct electrical transport behavior of x=0 and x=0.75 (or 1) is presently understood by their possible different scattering mechanism of the anomalous Hall effect due to the differences in atomic order and conductivity. Our work can expand the existing understanding of the SGS properties and offer a better SGS candidate with higher carrier mobility that can facilitate the application in the spin-injected related devices.

cond-mat.mtrl-sci↗
arXiv2023

Digital Twin-Enhanced Deep Reinforcement Learning for Resource Management in Networks Slicing

Network slicing-based communication systems can dynamically and efficiently allocate resources for diversified services. However, due to the limitation of the network interface on channel access and the complexity of the resource allocation, it is challenging to achieve an acceptable solution in the practical system without precise prior knowledge of the dynamics probability model of the service requests. Existing work attempts to solve this problem using deep reinforcement learning (DRL), however, such methods usually require a lot of interaction with the real environment in order to achieve good results. In this paper, a framework consisting of a digital twin and reinforcement learning agents is present to handle the issue. Specifically, we propose to use the historical data and the neural networks to build a digital twin model to simulate the state variation law of the real environment. Then, we use the data generated by the network slicing environment to calibrate the digital twin so that it is in sync with the real environment. Finally, DRL for slice optimization optimizes its own performance in this virtual pre-verification environment. We conducted an exhaustive verification of the proposed digital twin framework to confirm its scalability. Specifically, we propose to use loss landscapes to visualize the generalization of DRL solutions. We explore a distillation-based optimization scheme for lightweight slicing strategies. In addition, we also extend the framework to offline reinforcement learning, where solutions can be used to obtain intelligent decisions based solely on historical data. Numerical simulation experiments show that the proposed digital twin can significantly improve the performance of the slice optimization strategy.

cs.NI↗
arXiv2023

Learn the Time to Learn: Replay Scheduling in Continual Learning

Replay methods are known to be successful at mitigating catastrophic forgetting in continual learning scenarios despite having limited access to historical data. However, storing historical data is cheap in many real-world settings, yet replaying all historical data is often prohibited due to processing time constraints. In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps. We first demonstrate the benefits of our proposal by using Monte Carlo tree search to find a proper replay schedule, and show that the found replay schedules can outperform fixed scheduling policies when combined with various replay methods in different continual learning settings. Additionally, we propose a framework for learning replay scheduling policies with reinforcement learning. We show that the learned policies can generalize better in new continual learning scenarios compared to equally replaying all seen tasks, without added computational cost. Our study reveals the importance of learning the time to learn in continual learning, which brings current research closer to real-world needs.

cs.LG↗
arXiv2023

Absence of metallicity and bias-dependent resistivity in low-carrier-density EuCd2As2

EuCd2As2 was theoretically predicted to be a minimal model of Weyl semimetals with a single pair of Weyl points in the ferromagnet state. However, the heavily p-doped EuCd2As2 crystals in previous experiments prevent direct identification of the semimetal hypothesis. Here we present a comprehensive magneto-transport study of high-quality EuCd2As2 crystals with ultralow bulk carrier density (10^13 cm-3). In contrast to the general expectation of a Weyl semimetal phase, EuCd2As2 shows insulating behavior in both antiferromagnetic and ferromagnetic states as well as surface-dominated conduction from band bending. Moreover, the application of a dc bias current can dramatically modulate the resistance by over one order of magnitude, and induce a periodic resistance oscillation due to the geometric resonance. Such nonlinear transport results from the highly nonequilibrium state induced by electrical field near the band edge. Our results suggest an insulating phase in EuCd2As2 and put a strong constraint on the underlying mechanism of anomalous transport properties in this system.

cond-mat.mes-hall↗
arXiv2023

Magnetic-field-induced nonlinear transport in HfTe5

The interplay of electron correlations and topological phases gives rise to various exotic phenomena including fractionalization, excitonic instability, and axionic excitation. Recently-discovered transition-metal pentatellurides can reach the ultra-quantum limit in low magnetic fields and serve as good candidates for achieving such a combination. Here, we report evidences of density wave and metal-insulator transition in HfTe5 induced by intense magnetic fields. Using the nonlinear transport technique, we detect a distinct nonlinear conduction behavior in the longitudinal resistivity within the a-c plane, corresponding to the formation of a density wave induced by magnetic fields. In high fields, the onset of the nonlinear conduction in the Hall resistivity indicates an impurity-pinned magnetic freeze-out as the possible origin of the insulating behavior. These frozen electrons can be gradually re-activated into mobile states above a threshold electric field. These experimental evidences call for further investigations into the underlying mechanism for the bulk quantum Hall effect and field-induced phase transtions in pentatellurides.

cond-mat.mes-hall↗
arXiv2023

Sharp local $L^p$ estimates for the Hermite eigenfunctions

We investigate the concentration of eigenfunctions for the Hermite operator $H=-Δ+|x|^2$ in $\mathbb{R}^n$ by establishing local $L^p$ bounds over the compact sets with arbitrary dilations and translations. These new results extend the local estimates by Thangavelu and improve those derived from Koch-Tataru, and explain the special phenomenon that the global $L^p$ bounds decrease in $p$ when $2\le p\le \frac{2n+6}{n+1}$. The key $L^2$-estimates show that the local probabilities decrease away from the boundary $\{|x|=λ\}$, and then they satisfy Bohr's correspondence principle in any dimension. The proof uses the Hermite spectral projection operator represented by Mehler's formula for the Hermite-Schrödinger propagator $e^{-it H}$, and the strategy developed by Thangavelu and Jeong-Lee-Ryu. We also exploit an explicit version of the stationary phase lemma and Hörmander's $L^2$ oscillatory integral theorem. Using Koch-Tataru's strategy, we construct appropriate examples to illustrate the possible concentrations and show the optimality of our local estimates.

math.AP↗
arXiv2023

Learned Causal Method Prediction

For a given causal question, it is important to efficiently decide which causal inference method to use for a given dataset. This is challenging because causal methods typically rely on complex and difficult-to-verify assumptions, and cross-validation is not applicable since ground truth causal quantities are unobserved. In this work, we propose CAusal Method Predictor (CAMP), a framework for predicting the best method for a given dataset. To this end, we generate datasets from a diverse set of synthetic causal models, score the candidate methods, and train a model to directly predict the highest-scoring method for that dataset. Next, by formulating a self-supervised pre-training objective centered on dataset assumptions relevant for causal inference, we significantly reduce the need for costly labeled data and enhance training efficiency. Our strategy learns to map implicit dataset properties to the best method in a data-driven manner. In our experiments, we focus on method prediction for causal discovery. CAMP outperforms selecting any individual candidate method and demonstrates promising generalization to unseen semi-synthetic and real-world benchmarks.

cs.LG↗
arXiv2023

The Closed and Open Unbalanced Dicke Trimer Model: Critical Properties and Nonlinear Semiclassical Dynamics

We study a generalization of a recently introduced Dicke trimer model [Phys. Rev. Lett. 128, 163601, Phys. Rev. Research 5, L042016], which allows for cavity losses and unbalanced light-matter interactions (in which rotating and counter-rotating terms can be tuned independently). We find that in the extreme unbalanced limit, the $U(1)$ symmetry of the Tavis-Cummings model is restored, qualitatively altering the critical phenomena in the superradiant phase due to the presence of a zero-energy mode. To analyze this general regime, we develop a semiclassical theory based on a re-quantization technique. This theory also provides further physical insight on a recently reported anomalous finite critical fluctuations in the time-reversal broken regime. Moving to the open-Dicke case, by introducing local dissipation to the cavities, we observe the emergence of a rich range of nonequilibrium phases characterized by trivial and non-trivial dynamical signatures. In the former case, we identify, when time-reversal symmetry is present, a new stationary phase that features superradiant states in two of the three cavities and a normal state in the other cavity. In the latter case, we observe the emergence of dynamical phases in which the system exhibits superradiant oscillations, characterized by periodic or chaotic phase space patterns. The landscape of transitions associated with these dynamical phases features a wide range of qualitatively different behaviours such as Hopf bifurcations, anomalous Hopf bifurcations, collisions between basins of attraction, and exterior crises. We highlight how the two-critical-scalings feature of the closed model is robust under dissipation while the phenomenon of anomalous finite critical fluctuations becomes a mean-field scaling in the open model.

quant-ph↗
arXiv2023

High Precision Causal Model Evaluation with Conditional Randomization

The gold standard for causal model evaluation involves comparing model predictions with true effects estimated from randomized controlled trials (RCT). However, RCTs are not always feasible or ethical to perform. In contrast, conditionally randomized experiments based on inverse probability weighting (IPW) offer a more realistic approach but may suffer from high estimation variance. To tackle this challenge and enhance causal model evaluation in real-world conditional randomization settings, we introduce a novel low-variance estimator for causal error, dubbed as the pairs estimator. By applying the same IPW estimator to both the model and true experimental effects, our estimator effectively cancels out the variance due to IPW and achieves a smaller asymptotic variance. Empirical studies demonstrate the improved of our estimator, highlighting its potential on achieving near-RCT performance. Our method offers a simple yet powerful solution to evaluate causal inference models in conditional randomization settings without complicated modification of the IPW estimator itself, paving the way for more robust and reliable model assessments.

cs.LG↗
arXiv2023

1D-CapsNet-LSTM: A Deep Learning-Based Model for Multi-Step Stock Index Forecasting

Multi-step stock index forecasting is vital in finance for informed decision-making. Current forecasting methods on this task frequently produce unsatisfactory results due to the inherent data randomness and instability, thereby underscoring the demand for advanced forecasting models. Given the superiority of capsule network (CapsNet) over CNN in various forecasting and classification tasks, this study investigates the potential of integrating a 1D CapsNet with an LSTM network for multi-step stock index forecasting. To this end, a hybrid 1D-CapsNet-LSTM model is introduced, which utilizes a 1D CapsNet to generate high-level capsules from sequential data and a LSTM network to capture temporal dependencies. To maintain stochastic dependencies over different forecasting horizons, a multi-input multi-output (MIMO) strategy is employed. The model's performance is evaluated on real-world stock market indices, including S&P 500, DJIA, IXIC, and NYSE, and compared to baseline models, including LSTM, RNN, and CNN-LSTM, using metrics such as RMSE, MAE, MAPE, and TIC. The proposed 1D-CapsNet-LSTM model consistently outperforms baseline models in two key aspects. It exhibits significant reductions in forecasting errors compared to baseline models. Furthermore, it displays a slower rate of error increase with lengthening forecast horizons, indicating increased robustness for multi-step forecasting tasks.

cs.LG↗
arXiv2023

Transmission infrared micro-spectroscopic study of individual human hair

Understanding the optical transmission property of human hair, especially in the infrared regime, is vital in physical, clinical, and biomedical research. However, the majority of infrared spectroscopy on human hair is performed in the reflection mode, which only probes the absorptance of the surface layer. The direct transmission spectrum of individual hair without horizontal cut offers a rapid and non-destructive test of the hair cortex but is less investigated experimentally due to the small size and strong absorption of the hair. In this work, we conduct transmission infrared micro-spectroscopic study on individual human hair. By utilizing direct measurements of the transmission spectrum using a Fourier-transform infrared microscope, the human hair is found to display prominent band filtering behavior. The high spatial resolution of infrared micro-spectroscopy further allows the comparison among different regions of hair. In a case study of adult-onset Still's disease, the corresponding infrared transmission exhibits systematic variations of spectral weight as the disease evolves. The geometry effect of the internal hair structure is further quantified using the finite-element simulation. The results imply that the variation of spectral weight may relate to the disordered microscopic structure variation of the hair cortex during the inflammatory attack. Our work reveals the potential of hair infrared transmission spectrum in tracing the variation of hair cortex retrospectively.

physics.bio-ph↗