arXiv subjects

Yang Peng

Publications and source records attributed to Yang Peng.

At least 37 records · Page 2Linked to original sources

arXiv2025

Engineering micromotion in Floquet prethermalization via space-time symmetries

We present a systematic framework for Floquet prethermalization under strong resonant driving, emphasizing the pivotal role of dynamical space-time symmetries. Our approach demonstrates how dynamical space-time symmetries map onto the projective static symmetry group of the prethermal Hamiltonian governing the prethermal regime. We introduce techniques for detecting dynamical symmetries through the time evolution of local observables, facilitating a detailed analysis of micromotion within each period and surpassing the limitations of conventional stroboscopic Floquet prethermal dynamics. To implement this framework, we present a prethermal protocol that preserves order-two dynamical symmetry in a spin-ladder model, confirming the predicted relationships between the expectation values of local observables at distinct temporal points in the Floquet cycle, linked by this symmetry.

quant-ph↗

arXiv2025

Accelerated Distributional Temporal Difference Learning with Linear Function Approximation

In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The purpose of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy. Previous works on statistical analysis of distributional TD learning focus mainly on the tabular case. We first consider the linear function approximation setting and conduct a fine-grained analysis of the linear-categorical Bellman equation. Building on this analysis, we further incorporate variance reduction techniques in our new algorithms to establish tight sample complexity bounds independent of the support size $K$ when $K$ is large. Our theoretical results imply that, when employing distributional TD learning with linear function approximation, learning the full distribution of the return function from streaming data is no more difficult than learning its expectation. This work provide new insights into the statistical efficiency of distributional reinforcement learning algorithms.

stat.ML↗

arXiv2025

Quantum anomalous Hall effects and emergent $\rm{SU}(2)$ Hall ferromagnets at fractional filling of helical trilayer graphene

Helical trilayer graphene realizes a versatile moiré system for exploring correlated topological states emerging from high Chern bands. Motivated by recent experimental observations of anomalous Hall effects at fractional fillings of magic-angle helical trilayers, we focus on the higher Chern number $|C_{band}|=2$ band and explore gapped many-body Hall states beyond the conventional Landau level paradigm. Through extensive exact diagonalization, we predict novel phases unattainable in a single $|C_{band}|=1$ band. At filling $ν=2/3$ and $ν=1/3$, a $\sqrt{3}\times \sqrt{3}$ charge-ordered quantum Hall crystal and a Halperin fractional Chern insulator with Hall conductance $|σ_{H}|=2e^2/3h$ are predicted respectively, indicating strong particle-hole asymmetry of the system. At half-filling $ν=1/2$, an extensively degenerate pseudospin Hall ferromagnet featuring emergent $\rm{SU}(2)$ symmetry is found without the band being flat. Inspired by striking robustness of the ferromagnetic degeneracy, we develop a method to unveil and quantify the emergent symmetry via pseudospin operator construction in the presence of band dispersion and Coulomb interaction, and demonstrate persistence of the $\rm{SU}(2)$ quantum numbers even far away from the chiral limit. Incorporating spin-valley degrees of freedom, we identify an optimal filling regime $ν_{\rm{total}}=3+ν$ for realizing the above states. Notably, inter-flavor interactions renormalize the bandwidth and stabilize all the gapped phases even in realistic sublattice corrugation parameter regimes.

cond-mat.str-el↗

arXiv2025

The Observations of Magnetic Reconnection During the Interaction Process of Two Active Region Filaments

We investigate the interaction between two filaments (F1 and F2) and their subsequent magnetic reconnection in active region (AR) NOAA 13296 and AR NOAA 13293 on May 9, 2023, utilizing high spatial and temporal resolution and multi-wavelength observational data from the Solar Dynamics Observatory, the New Vacuum Solar Telescope, and the Chinese Hα Solar Explorer. The movement of F1 from the southeast toward the northwest, driven by the motion of the positive magnetic polarity (P1), leads to a collision and reconnection with F2. This reconnection exchanges their footpoints, resulting in the formation of two new filaments (F3 and F4) consistent with "slingshot" type filament interaction. During the interaction, the current sheet moving due to the motion of F1 and the reconnection outflows moving along F3 and F4 were both observed. The current sheet is rarely observed in the slingshot type filament interaction, measuring approximately 2.17 Mm in length and 0.84 Mm in width. After the interaction, the F1 disappears whereas a portion of F2 remains, indicating that the interaction involves partial slingshot reconnection, due to the unequal magnetic flux between the filaments. The residual part of F2 will undergo another magnetic reconnection in the same interaction region with the magnetic loops connecting polarities N1 and P1. The material generated by the reconnection is continuously injected into F4, leading to its final morphology. The findings enhance our understanding of slingshot-type filament interactions, indicating that partial slingshot reconnections between filaments may be more common than full slingshot events.

astro-ph.SR↗

arXiv2025

A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation

In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy π. Previous works on statistical analysis of distributional TD learning mainly focus on the tabular case. In contrast, we first consider the linear function approximation setting and derive sharp finite-sample rates. Our theoretical results demonstrate that the sample complexity of linear distributional TD learning matches that of classic linear TD learning. This implies that, with linear function approximation, learning the full distribution of the return from streaming data is no more difficult than learning its expectation (value function). To derive tight sample complexity bounds, we conduct a fine-grained analysis of the linear-categorical Bellman equation and employ the exponential stability arguments for products of random matrices. Our results provide new insights into the statistical efficiency of distributional reinforcement learning algorithms.

stat.ML↗

arXiv2025

AI Delivers Creative Output but Struggles with Thinking Processes

A key objective in artificial intelligence (AI) development is to create systems that match or surpass human creativity. Although current AI models perform well across diverse creative tasks, it remains unclear whether these achievements reflect genuine creative thinking. This study examined whether AI models (GPT-3.5-turbo, GPT-4, and GPT-4o) engage in creative thinking by comparing their performance with humans across various creative tasks and core cognitive processes. Results showed that AI models outperformed humans in divergent thinking, convergent thinking, and insight problem-solving, but underperformed in creative writing. Compared to humans, AI generated lower forward flow values in both free and chain association tasks and showed lower accuracy in the representational change task. In creative evaluation, AI exhibited no significant correlation between the weights of novelty and appropriateness when predicting creative ratings, suggesting the absence of a human-like trade-off strategy. AI also had higher decision error scores in creative selection, suggesting difficulty identifying the most creative ideas. These findings suggest that while AI can mimic human creativity, its strong performance in creative tasks is likely driven by non-creative mechanisms rather than genuine creative thinking.

cs.HC↗

arXiv2025

Statistical Efficiency of Distributional Temporal Difference Learning and Freedman's Inequality in Hilbert Spaces

Distributional reinforcement learning (DRL) has achieved empirical success in various domains. One core task in DRL is distributional policy evaluation, which involves estimating the return distribution $η^π$ for a given policy $π$. Distributional temporal difference learning has been accordingly proposed, which extends the classic temporal difference learning (TD) in RL. In this paper, we focus on the non-asymptotic statistical rates of distributional TD. To facilitate theoretical analysis, we propose non-parametric distributional TD (NTD). For a $γ$-discounted infinite-horizon tabular Markov decision process, we show that for NTD with a generative model, we need $\tilde{O}(\varepsilon^{-2}μ_{\min}^{-1}(1-γ)^{-3})$ interactions with the environment to achieve an $\varepsilon$-optimal estimator with high probability, when the estimation error is measured by the $1$-Wasserstein. This sample complexity bound is minimax optimal up to logarithmic factors. In addition, we revisit categorical distributional TD (CTD), showing that the same non-asymptotic convergence bounds hold for CTD in the case of the $1$-Wasserstein distance. We also extend our analysis to the more general setting where the data generating process is Markovian. In the Markovian setting, we propose variance-reduced variants of NTD and CTD, and show that both can achieve a $\tilde{O}(\varepsilon^{-2} μ_{π,\min}^{-1}(1-γ)^{-3}+t_{mix}μ_{π,\min}^{-1}(1-γ)^{-1})$ sample complexity bounds in the case of the $1$-Wasserstein distance, which matches the state-of-the-art statistical results for classic policy evaluation. To achieve the sharp statistical rates, we establish a novel Freedman's inequality in Hilbert spaces. This new Freedman's inequality would be of independent interest for statistical analysis of various infinite-dimensional online learning problems.

stat.ML↗

arXiv2024

SUSTechGAN: Image Generation for Object Detection in Adverse Conditions of Autonomous Driving

Autonomous driving significantly benefits from data-driven deep neural networks. However, the data in autonomous driving typically fits the long-tailed distribution, in which the critical driving data in adverse conditions is hard to collect. Although generative adversarial networks (GANs) have been applied to augment data for autonomous driving, generating driving images in adverse conditions is still challenging. In this work, we propose a novel framework, SUSTechGAN, with customized dual attention modules, multi-scale generators, and a novel loss function to generate driving images for improving object detection of autonomous driving in adverse conditions. We test the SUSTechGAN and the well-known GANs to generate driving images in adverse conditions of rain and night and apply the generated images to retrain object detection networks. Specifically, we add generated images into the training datasets to retrain the well-known YOLOv5 and evaluate the improvement of the retrained YOLOv5 for object detection in adverse conditions. The experimental results show that the generated driving images by our SUSTechGAN significantly improved the performance of retrained YOLOv5 in rain and night conditions, which outperforms the well-known GANs. The open-source code, video description and datasets are available on the page 1 to facilitate image generation development in autonomous driving under adverse conditions.

cs.CV↗

arXiv2024

Quantum phase diagram and non-abelian Moore-Read state in double twisted bilayer graphene

Experimental realizations of Abelian fractional Chern insulators (FCIs) have demonstrated the potentials of moiré systems in synthesizing exotic quantum phases. Remarkably, twisted multilayer graphene system may also host non-Abelian states competing with charge density wave under Coulomb interaction. Here, through larger scale exact diagonalization simulations, we map out the quantum phase diagram for $ν=1/2$ system with electrons occupying the lowest moirè band of the double twisted bilayer graphene. By increasing the system size, we find the ground state has six-fold near degeneracy and with a finite spectral gap separating the ground states from excited states across a broad range of parameters. Further computation of many-body Chern number establish the topological order of the state, and we rule out possibility of charge density wave orders based on featureless density structure factor. Furthermore, we inspect the particle-cut entanglement spectrum to identify the topological state as a non-Abelian Moore-Read state. Combining all the above evidences we conclude that Moore-Read ground state dominates the quantum phase diagram for the double twisted bilayer graphene system for a broad range of coupling strength with realistic Coulomb interaction.

cond-mat.str-el↗

arXiv2024

Exploring Thouless Pumping in the Generalized Creutz Model: A Graphical Method and Modulation Schemes

Thouless pumping with nontrivial topological phases provides a powerful means for the manipulation of matter waves in one-dimensional lattice systems. The band topology is revealed by the quantization of pumped charge. In the context of Thouless pumping, we present a graphical representation for the topological phases characterized by the Chern number of an effective two-dimensional band. We illustrate how the two topological phases with distinct Zak phase is connected in the pumping process. Such a visual depiction exhibits typical patterns that is directly related to a linking number and to the Chern number, allowing for the construction of Thouless pumping schemes in a practical way. As a demonstration, we present a generalized Creutz model with tunable Peierls phase, inter-leg imbalance and diagonal hopping. Various modulation schemes for Thouless pumping are studied, focusing on their graphical representations in Bloch space, as well as the quantized pumping phenomenon in real space.

cond-mat.quant-gas↗

arXiv2024

Self-similar phase diagram of the Fibonacci-driven quantum Ising model

We study a stroboscopic quantum Ising model with Fibonacci dynamics. Focusing on boundary spin correlation functions in long but finite chains, our simulations as well as analytical arguments reveal a self-similar phase diagram exhibiting regions with Majorana zero modes (MZM) as well as Majorana golden-ratio modes (MGM). We identify the self-similarity transform which governs the evolution of the phase diagram with increasing simulation time. Integrability-breaking perturbations lead to a temporal decay of the boundary spin correlations, ultimaltely limiting the self-similarity of the phase diagram. Our predictions are testable with current quantum information processors.

cond-mat.dis-nn↗

arXiv2024

Topological quantum phase transitions driven by a displacement field in the twisted MoTe2 bilayers

We study twisted bilayer MoTe$_2$ systems at fractional fillings of the lowest hole band under an applied out-of-plane displacement field. By employing exact diagonalization in finite-size systems, we systematically map out the ground state quantum phase diagram for two filling fractions, $ν=1/3$ and $2/3$, and provide a detailed characterization of each phase. We identify the phase transition between a fractional Chern insulator (FCI) and a layer-polarized charge density wave (CDW) at a filling fraction of $ν=1/3$, denoted as CDW-$1$. Additionally, we demonstrate that the competition between the displacement field and twist angle leads to another phase transition from a layer-polarized CDW-$1$ to a layer-hybridized CDW-$2$, identified as a first-order phase transition. Furthermore, at $ν=2/3$ filling of the lowest hole band, we observe that the FCI remains stable against the displacement field until it approaches proximity to a transition in single-particle band topology at a smaller twist angle.

cond-mat.mes-hall↗

arXiv2024

Estimation and Inference in Distributional Reinforcement Learning

In this paper, we study distributional reinforcement learning from the perspective of statistical efficiency. We investigate distributional policy evaluation, aiming to estimate the complete return distribution (denoted $η^π$) attained by a given policy $π$. We use the certainty-equivalence method to construct our estimator $\hatη^π$, given a generative model is available. In this circumstance we need a dataset of size $\widetilde O\left(\frac{|\mathcal{S}||\mathcal{A}|}{\varepsilon^{2p}(1-γ)^{2p+2}}\right)$ to guarantee the $p$-Wasserstein metric between $\hatη^π$ and $η^π$ less than $\varepsilon$ with high probability. This implies the distributional policy evaluation problem can be solved with sample efficiency. Also, we show that under different mild assumptions a dataset of size $\widetilde O\left(\frac{|\mathcal{S}||\mathcal{A}|}{\varepsilon^{2}(1-γ)^{4}}\right)$ suffices to ensure the Kolmogorov metric and total variation metric between $\hatη^π$ and $η^π$ is below $\varepsilon$ with high probability. Furthermore, we investigate the asymptotic behavior of $\hatη^π$. We demonstrate that the ``empirical process'' $\sqrt{n}(\hatη^π-η^π)$ converges weakly to a Gaussian process in the space of bounded functionals on Lipschitz function class $\ell^\infty(\mathcal{F}_{\text{W}})$, also in the space of bounded functionals on indicator function class $\ell^\infty(\mathcal{F}_{\text{KS}})$ and bounded measurable function class $\ell^\infty(\mathcal{F}_{\text{TV}})$ when some mild conditions hold. Our findings give rise to a unified approach to statistical inference of a wide class of statistical functionals of $η^π$.

stat.ML↗

arXiv2024

Origin of the Chromospheric Umbral Waves in Sunspots

Oscillations are ubiquitous in sunspots and the associated higher atmospheres. However, it is still unclear whether these oscillations are driven by the external acoustic waves (p-modes) or generated by the internal magnetoconvection. To obtain clues about the driving source of umbral waves in sunspots, we analyzed the spiral wave patterns (SWPs) in two sunspots registered by IRIS MgII 2796 Å slit-jaw images. By tracking the motion of the SWPs, we find for the first time that two one-armed SWPs coexist in the umbra, and they can rotate either in the same or opposite directions. Furthermore, by analyzing the spatial distribution of the oscillation centers of the one-armed SWPs within the umbra (the oscillation center is defined as the location where the SWP first appears), we find that the chromospheric umbral waves repeatedly originate from the regions with high oscillation power and most of the umbral waves occur in the dark nuclei and strong magnetic field regions of the umbra. Our study results indicate that the chromospheric umbral waves are likely excited by the p-mode oscillations.

astro-ph.SR↗

arXiv2024

Real-space topological invariant for time-quasiperiodic Majoranas

When subjected to quasiperiodic driving protocols, superconducting systems have been found to harbor robust time-quasiperiodic Majorana modes, extending the concept beyond static and Floquet systems. However, the presence of incommensurate driving frequencies results in dense energy spectra, rendering conventional methods of defining topological invariants based on band structure inadequate. In this work, we introduce a real-space topological invariant capable of identifying time-quasiperiodic Majoranas by leveraging the system's spectral localizer, which integrates information from both Hamiltonian and position operators. Drawing insights from non-Hermitian physics, we establish criteria for constructing the localizer and elucidate the robustness of this invariant in the presence of dense spectra. Our numerical simulations, focusing on a Kitaev chain driven by two incommensurate frequencies, validate the efficacy of our approach.

cond-mat.mes-hall↗

arXiv2024

Federated Control in Markov Decision Processes

We study problems of federated control in Markov Decision Processes. To solve an MDP with large state space, multiple learning agents are introduced to collaboratively learn its optimal policy without communication of locally collected experience. In our settings, these agents have limited capabilities, which means they are restricted within different regions of the overall state space during the training process. In face of the difference among restricted regions, we firstly introduce concepts of leakage probabilities to understand how such heterogeneity affects the learning process, and then propose a novel communication protocol that we call Federated-Q protocol (FedQ), which periodically aggregates agents' knowledge of their restricted regions and accordingly modifies their learning problems for further training. In terms of theoretical analysis, we justify the correctness of FedQ as a communication protocol, then give a general result on sample complexity of derived algorithms FedQ-X with the RL oracle , and finally conduct a thorough study on the sample complexity of FedQ-SynQ. Specifically, FedQ-X has been shown to enjoy linear speedup in terms of sample complexity when workload is uniformly distributed among agents. Moreover, we carry out experiments in various environments to justify the efficiency of our methods.

stat.ML↗

arXiv2024

The Decay Process of an α-configuration Sunspot

The decay of sunspot plays a key role in magnetic flux transportation in solar active regions (ARs). To better understand the physical mechanism of the entire decay process of a sunspot, an α-configuration sunspot in AR NOAA 12411 was studied. Based on the continuum intensity images and vector magnetic field data with stray light correction from Solar Dynamics Observatory/Helioseismic and Magnetic Imager, the area, vector magnetic field and magnetic flux in the umbra and penumbra are calculated with time, respectively. Our main results are as follows: (1) The decay curves of the sunspot area in its umbra, penumbra, and whole sunspot take the appearance of Gaussian profiles. The area decay rates of the umbra, penumbra and whole sunspot are -1.56 MSH/day, -12.61 MSH/day and -14.04 MSH/day, respectively; (2) With the decay of the sunspot, the total magnetic field strength and the vertical component of the penumbra increase, and the magnetic field of the penumbra becomes more vertical. Meanwhile, the total magnetic field strength and vertical magnetic field strength for the umbra decrease, and the inclination angle changes slightly with an average value of about 20°; (3) The magnetic flux decay curves of the sunspot in its umbra, penumbra, and whole sunspot exhibit quadratic patterns, their magnetic flux decay rates of the umbra, penumbra and whole sunspot are -9.84 * 10^19 Mx/day, -1.59 * 10^20 Mx/day and -2.60 * 10^20 Mx/day , respectively. The observation suggests that the penumbra may be transformed into the umbra, resulting in the increase of the average vertical magnetic field strength and the reduction of the inclination angle in the penumbra during the decay of the sunspot.

astro-ph.SR↗

arXiv2024

The Decay of Two Adjacent Sunspots Associated with Moving Magnetic Features

The relationship between the decay of sunspots and moving magnetic features (MMFs) plays an important role in understanding the evolution of active regions. We present observations of two adjacent sunspots, the gap between them, and a lot of MMFs propagating from the gap and the sunspots' outer edges in NOAA Active Region 13023. The MMFs are divided into two types based on their magnetic field inclination angle: vertical (0°<γ<45°) and horizontal (45°<γ<90°) MMFs (V-MMFs and H-MMFs, respectively). The main results are as follows: (1) the mean magnetic flux decay rates of the two sunspots are -1.7*10^20 and -1.4*10^20 Mx/day; (2) the magnetic flux generation rate of all MMFs is calculated to be -1.9 *10^21 Mx/day, which is on average 5.6 times higher than the total magnetic flux loss rate of the sunspots; (3) the magnetic flux of V-MMFs (including a pore separated from the sunspots) is 1.4 times larger than the total lost magnetic flux of the two sunspots, and in a later stage when the pore has passed through the reference ellipse, the magnetic flux generation rate of the V-MMFs is almost the same as the magnetic flux loss rate of the sunspots; and (4) within the gap, the magnetic flux of V-MMFs is one third of the total magnetic flux. Few V-MMFs stream out from the sunspots at the nongap region. All observations suggest that MMFs with vertical magnetic fields are closely related to the disintegration of the sunspot, and most of the MMFs from the gap may originate directly from the sunspot umbra.

astro-ph.SR↗