arXiv subjects

Lei Ying

Publications and source records attributed to Lei Ying.

At least 55 records · Page 3Linked to original sources

arXiv2024

Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms

This paper considers a stochastic Multi-Armed Bandit (MAB) problem with dual objectives: (i) quick identification and commitment to the optimal arm, and (ii) reward maximization throughout a sequence of $T$ consecutive rounds. Though each objective has been individually well-studied, i.e., best arm identification for (i) and regret minimization for (ii), the simultaneous realization of both objectives remains an open problem, despite its practical importance. This paper introduces \emph{Regret Optimal Best Arm Identification} (ROBAI) which aims to achieve these dual objectives. To solve ROBAI with both pre-determined stopping time and adaptive stopping time requirements, we present an algorithm called EOCP and its variants respectively, which not only achieve asymptotic optimal regret in both Gaussian and general bandits, but also commit to the optimal arm in $\mathcal{O}(\log T)$ rounds with pre-determined stopping time and $\mathcal{O}(\log^2 T)$ rounds with adaptive stopping time. We further characterize lower bounds on the commitment time (equivalent to the sample complexity) of ROBAI, showing that EOCP and its variants are sample optimal with pre-determined stopping time, and almost sample optimal with adaptive stopping time. Numerical results confirm our theoretical analysis and reveal an interesting "over-exploration" phenomenon carried by classic UCB algorithms, such that EOCP has smaller regret even though it stops exploration much earlier than UCB, i.e., $\mathcal{O}(\log T)$ versus $\mathcal{O}(T)$, which suggests over-exploration is unnecessary and potentially harmful to system performance.

cs.LG↗

arXiv2024

Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs

This paper considers the best policy identification (BPI) problem in online Constrained Markov Decision Processes (CMDPs). We are interested in algorithms that are model-free, have low regret, and identify an approximately optimal policy with a high probability. Existing model-free algorithms for online CMDPs with sublinear regret and constraint violation do not provide any convergence guarantee to an optimal policy and provide only average performance guarantees when a policy is uniformly sampled at random from all previously used policies. In this paper, we develop a new algorithm, named Pruning-Refinement-Identification (PRI), based on a fundamental structural property of CMDPs proved before, which we call limited stochasticity. The property says for a CMDP with $N$ constraints, there exists an optimal policy with at most $N$ stochastic decisions. The proposed algorithm first identifies at which step and in which state a stochastic decision has to be taken and then fine-tunes the distributions of these stochastic decisions. PRI achieves trio objectives: (i) PRI is a model-free algorithm; and (ii) it outputs an approximately optimal policy with a high probability at the end of learning; and (iii) PRI guarantees $\tilde{\mathcal{O}}(H\sqrt{K})$ regret and constraint violation, which significantly improves the best existing regret bound $\tilde{\mathcal{O}}(H^4 \sqrt{SA}K^{\frac{4}{5}})$ under a model-free algorithm, where $H$ is the length of each episode, $S$ is the number of states, $A$ is the number of actions, and the total number of episodes during learning is $2K+\tilde{\cal O}(K^{0.25}).$ We further present a matching lower via an example that shows under any online learning algorithm, there exists a well-separated CMDP instance such that either the regret or violation has to be $Ω(H\sqrt{K}),$ which matches the upper bound by a polylogarithmic factor.

cs.LG↗

arXiv2024

Emergent Anomalous Hydrodynamics at Infinite Temperature in a Long-Range XXZ Model

The conventional wisdom suggests that transports of conserved quantities in non-integrable quantum many-body systems at high temperatures are diffusive. However, we discover a counterexample of this paradigm by uncovering anomalous hydrodynamics in a spin-1/2 XXZ chain with power-law couplings. This model, classified as non-integrable due to its Wigner-Dyson level-spacing statistics in the random matrix theory, exhibits a surprising superdiffusive-ballistic-superdiffusive transport transition by varying the power-law exponent of couplings for a fixed anisotropy. Our findings are verified by multiple observables, including the spin-spin autocorrelator, mean-square displacement, and spin conductivity. Interestingly, we further quantify the degree of quantum chaos using the Kullback-Leibler divergence between the entanglement entropy distributions of the model's eigenstates and a random state. Remarkably, an observed local maximum in the divergence near the transition boundary suggests a link between anomalous hydrodynamics and a suppression of quantum chaos. This work offers another deep understanding of emergent anomalous transport phenomena in a wider range of non-integrable quantum many-body systems

quant-ph↗

arXiv2024

Measuring Spectral Form Factor in Many-Body Chaotic and Localized Phases of Quantum Processors

The spectral form factor (SFF) captures universal spectral fluctuations as signatures of quantum chaos, and has been instrumental in advancing multiple frontiers of physics including the studies of black holes and quantum many-body systems. However, the measurement of SFF in many-body systems is challenging due to the difficulty in resolving level spacings that become exponentially small with increasing system size. Here we experimentally measure the SFF to probe the presence or absence of chaos in quantum many-body systems using a superconducting quantum processor with a randomized measurement protocol. For a Floquet chaotic system, we observe signatures of spectral rigidity of random matrix theory in SFF given by the ramp-plateau behavior. For a Hamiltonian system, we utilize SFF to distinguish the quantum many-body chaotic phase and the prethermal many-body localization. We observe the dip-ramp-plateau behavior of random matrix theory in the chaotic phase, and contrast the scaling of the plateau time in system size between the many-body chaotic and localized phases. Furthermore, we probe the eigenstate statistics by measuring a generalization of the SFF, known as the partial SFF, and observe distinct behaviors in the purities of the reduced density matrix in the two phases. This work unveils a new way of extracting the universal signatures of many-body quantum chaos in quantum devices by probing the correlations in eigenenergies and eigenstates.

quant-ph↗

arXiv2023

Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration

This paper studies safe Reinforcement Learning (safe RL) with linear function approximation and under hard instantaneous constraints where unsafe actions must be avoided at each step. Existing studies have considered safe RL with hard instantaneous constraints, but their approaches rely on several key assumptions: $(i)$ the RL agent knows a safe action set for {\it every} state or knows a {\it safe graph} in which all the state-action-state triples are safe, and $(ii)$ the constraint/cost functions are {\it linear}. In this paper, we consider safe RL with instantaneous hard constraints without assumption $(i)$ and generalize $(ii)$ to Reproducing Kernel Hilbert Space (RKHS). Our proposed algorithm, LSVI-AE, achieves $\tilde{\cO}(\sqrt{d^3H^4K})$ regret and $\tilde{\cO}(H \sqrt{dK})$ hard constraint violation when the cost function is linear and $\cO(Hγ_K \sqrt{K})$ hard constraint violation when the cost function belongs to RKHS. Here $K$ is the learning horizon, $H$ is the length of each episode, and $γ_K$ is the information gain w.r.t the kernel used to approximate cost functions. Our results achieve the optimal dependency on the learning horizon $K$, matching the lower bound we provide in this paper and demonstrating the efficiency of LSVI-AE. Notably, the design of our approach encourages aggressive policy exploration, providing a unique perspective on safe RL with general cost functions and no prior knowledge of safe actions, which may be of independent interest.

cs.LG↗

arXiv2023

Observation of many-body dynamical localization

The quantum kicked rotor is a paradigmatic model system in quantum physics. As a driven quantum system, it is used to study the transition from the classical to the quantum world and to elucidate the emergence of chaos and diffusion. In contrast to its classical counterpart, it features dynamical localization, specifically Anderson localization in momentum space. The interacting many-body kicked rotor is believed to break localization, as recent experiments suggest. Here, we present evidence for many-body dynamical localization for the Lieb-Liniger version of the many-body quantum kicked rotor. After some initial evolution, the momentum distribution of interacting quantum-degenerate bosonic atoms in one-dimensional geometry, kicked hundreds of times by means of a pulsed sinusoidal potential, stops spreading. We quantify the arrested evolution by analysing the energy and the information entropy of the system as the interaction strength is tuned. In the limiting cases of vanishing and strong interactions, the first-order correlation function exhibits a very different decay behavior. Our results shed light on the boundary between the classical, chaotic world and the realm of quantum physics.

quant-ph↗

arXiv2023

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

This paper considers a class of reinforcement learning problems, which involve systems with two types of states: stochastic and pseudo-stochastic. In such systems, stochastic states follow a stochastic transition kernel while the transitions of pseudo-stochastic states are deterministic given the stochastic states/transitions. We refer to such systems as mixed systems, which are widely used in various applications, including manufacturing systems, communication networks, and queueing networks. We propose a sample efficient RL method that accelerates learning by generating augmented data samples. The proposed algorithm is data-driven and learns the policy from data samples from both real and augmented samples. This method significantly improves learning by reducing the sample complexity such that the dataset only needs to have sufficient coverage of the stochastic states. We analyze the sample complexity of the proposed method under Fitted Q Iteration (FQI) and demonstrate that the optimality gap decreases as $\tilde{\mathcal{O}}(\sqrt{{1}/{n}}+\sqrt{{1}/{m}}),$ where $n$ is the number of real samples and $m$ is the number of augmented samples per real sample. It is important to note that without augmented samples, the optimality gap is $\tilde{\mathcal{O}}(1)$ due to insufficient data coverage of the pseudo-stochastic states. Our experimental results on multiple queueing network applications confirm that the proposed method indeed significantly accelerates learning in both deep Q-learning and deep policy gradient.

cs.LG↗

arXiv2023

Study on many-body phases in Jaynes-Cummings-Hubbard arrays

Disorder in one-dimensional (1D) many-body systems emerges abundant phases such as many-body localization (MBL), and thermalization. However, it remains unclear regarding their existence and behavior within hybrid quantum systems. Here, based on a simple bosonic-spin hybrid model, as known as the Jaynes-Cummings-Hubbard (JCH) array, we investigate the effect of disorder comparing to the phenomena in the clean system with the variation of atom-photon coupling strength. By using the level-spacing ratio, entanglement entropy, and the properties of observable diagonal and off-diagonal matrix elements, we find that strong disorder results in the appearance of MBL phase in the JCH model that strongly violate eigenstate thermalization hypothesis (ETH), while a conditional prethermal behavior can exist in weak disorder or weak coupling regime. The conditional prethermal dynamics is based on the choice of initial product states. This work systematically reveals abundant many-body phases in the 1D JCH model and clarifies the discrepancies in the thermalization properties of systems with and without disorder.

quant-ph↗

arXiv2023

Origin of Hilbert space quantum scars in unconstrained models

Quantum many-body scar is a recently discovered phenomenon weakly violating eigenstate thermalization hypothesis, and it has been extensively studied across various models. However, experimental realizations are mainly based on constrained models such as the $PXP$ model. Inspired by recent experimental observations on the superconducting platform in Refs.~[Nat. Phys. 19, 120 (2022)] and [arXiv:2211.05803], we study a distinct class of quantum many-body scars based on a half-filling hard-core Bose-Hubbard model, which is generic to describe in many experimental platforms. It is the so-called Hilbert space quantum scar as it originates from a subspace with a hypercube geometry weakly connecting to other thermalization regions in Hilbert space. Within the hypercube, a pair of collective Fock states do not directly connect to the thermalization region, resulting in slow thermalization dynamics with remarkable fidelity revivals with distinct differences from dynamics of other initial states. This mechanism is generic in various real-space lattice configurations, including one-dimensional Su-Schrieffer-Heeger chain, comb lattice, and even random dimer clusters consisting of dimers. In addition, we develop a toy model based on Hilbert hypercube decay approximation, to explain the spectrum overlap between the collective states and all eigenstates. Furthermore, we explore the Hilbert space quantum scar in two- and three-dimensional Su-Schrieffer-Heeger many-body systems, consisting of tetramers or octamers, respectively. This study makes quantum many-body scar state more realistic in applications such as quantum sensing and quantum metrology.

quant-ph↗

arXiv2023

Achieving Bright Organic Light Emitting Field Effect Transistors with Sustained Efficiency through Hybrid Contact Design

Organic light emitting field effect transistors (OLEFETs) with bilayer structures have been widely studied due to their potential to integrate high-mobility organic transistors and efficient organic light emitting diodes. However, these devices face a major challenge of imbalance charge transport leading to severe efficiency roll-off at high brightness. Here, we propose a solution to this challenge by introducing a transparent organic/inorganic hybrid contact with specially designed electronic structures. Our design aims to steadily accumulate the electrons injected to the emissive polymer, allowing the light emitting interface to effectively capture more holes even when hole current increases. Our numerical simulations show that the capture efficiency of these steady electrons will dominate charge recombination and lead to a sustained external quantum efficiency of 0.23% over 3 orders of magnitude of brightness (4 to 7700 cd/m2) and current density (1.2 to 2700 mA/cm2) from -4 to -100 V. The same enhancement is retained even after increasing EQE to ~0.51%. The high and tunable brightness with stable efficiency offered by hybrid-contact OLEFETs make them ideal light emitting devices for various applications. These devices have the potential to revolutionize the field of organic electronics by overcoming the fundamental challenge of imbalance charge transport.

physics.app-ph↗

arXiv2023

Learning While Scheduling in Multi-Server Systems with Unknown Statistics: MaxWeight with Discounted UCB

Multi-server queueing systems are widely used models for job scheduling in machine learning, wireless networks, crowdsourcing, and healthcare systems. This paper considers a multi-server system with multiple servers and multiple types of jobs, where different job types require different amounts of processing time at different servers. The goal is to schedule jobs on servers without knowing the statistics of the processing times. To fully utilize the processing power of the servers, it is known that one has to at least learn the service rates of different job types on different servers. Prior works on this topic decouple the learning and scheduling phases which leads to either excessive exploration or extremely large job delays. We propose a new algorithm, which combines the MaxWeight scheduling policy with discounted upper confidence bound (UCB), to simultaneously learn the statistics and schedule jobs to servers. We prove that under our algorithm the asymptotic average queue length is bounded by one divided by the traffic slackness, which is order-wise optimal. We also obtain an exponentially decaying probability tail bound for any-time queue length. These results hold for both stationary and nonstationary service rates. Simulations confirm that the delay performance of our algorithm is several orders of magnitude better than previously proposed algorithms.

cs.LG↗

arXiv2023

Scalable and Sample Efficient Distributed Policy Gradient Algorithms in Multi-Agent Networked Systems

This paper studies a class of multi-agent reinforcement learning (MARL) problems where the reward that an agent receives depends on the states of other agents, but the next state only depends on the agent's own current state and action. We name it REC-MARL standing for REward-Coupled Multi-Agent Reinforcement Learning. REC-MARL has a range of important applications such as real-time access control and distributed power control in wireless networks. This paper presents a distributed policy gradient algorithm for REC-MARL. The proposed algorithm is distributed in two aspects: (i) the learned policy is a distributed policy that maps a local state of an agent to its local action and (ii) the learning/training is distributed, during which each agent updates its policy based on its own and neighbors' information. The learned algorithm achieves a stationary policy and its iterative complexity bounds depend on the dimension of local states and actions. The experimental results of our algorithm for the real-time access control and power control in wireless networks show that our policy significantly outperforms the state-of-the-art algorithms and well-known benchmarks.

cs.MA↗

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

Online Nonstochastic Control with Adversarial and Static Constraints

This paper studies online nonstochastic control problems with adversarial and static constraints. We propose online nonstochastic control algorithms that achieve both sublinear regret and sublinear adversarial constraint violation while keeping static constraint violation minimal against the optimal constrained linear control policy in hindsight. To establish the results, we introduce an online convex optimization with memory framework under adversarial and static constraints, which serves as a subroutine for the constrained online nonstochastic control algorithms. This subroutine also achieves the state-of-the-art regret and constraint violation bounds for constrained online convex optimization problems, which is of independent interest. Our experiments demonstrate the proposed control algorithms are adaptive to adversarial constraints and achieve smaller cumulative costs and violations. Moreover, our algorithms are less conservative and achieve significantly smaller cumulative costs than the state-of-the-art algorithm.

cs.LG↗

arXiv2023

Network Utility Maximization with Unknown Utility Functions: A Distributed, Data-Driven Bilevel Optimization Approach

Fair resource allocation is one of the most important topics in communication networks. Existing solutions almost exclusively assume each user utility function is known and concave. This paper seeks to answer the following question: how to allocate resources when utility functions are unknown, even to the users? This answer has become increasingly important in the next-generation AI-aware communication networks where the user utilities are complex and their closed-forms are hard to obtain. In this paper, we provide a new solution using a distributed and data-driven bilevel optimization approach, where the lower level is a distributed network utility maximization (NUM) algorithm with concave surrogate utility functions, and the upper level is a data-driven learning algorithm to find the best surrogate utility functions that maximize the sum of true network utility. The proposed algorithm learns from data samples (utility values or gradient values) to autotune the surrogate utility functions to maximize the true network utility, so works for unknown utility functions. For the general network, we establish the nonasymptotic convergence rate of the proposed algorithm with nonconcave utility functions. The simulations validate our theoretical results and demonstrate the great effectiveness of the proposed method in a real-world network.

cs.LG↗

arXiv2022

Observation of many-body Fock space dynamics in two dimensions

Quantum many-body simulation provides a straightforward way to understand fundamental physics and connect with quantum information applications. However, suffering from exponentially growing Hilbert space size, characterization in terms of few-body probes in real space is often insufficient to tackle challenging problems such as quantum critical behavior and many-body localization (MBL) in higher dimensions. Here, we experimentally employ a new paradigm on a superconducting quantum processor, exploring such elusive questions from a Fock space view: mapping the many-body system onto an unconventional Anderson model on a complex Fock space network of many-body states. By observing the wave packet propagating in Fock space and the emergence of a statistical ergodic ensemble, we reveal a fresh picture for characterizing representative many-body dynamics: thermalization, localization, and scarring. In addition, we observe a quantum critical regime of anomalously enhanced wave packet width and deduce a critical point from the maximum wave packet fluctuations, which lend support for the two-dimensional MBL transition in finite-sized systems. Our work unveils a new perspective of exploring many-body physics in Fock space, demonstrating its practical applications on contentious MBL aspects such as criticality and dimensionality. Moreover, the entire protocol is universal and scalable, paving the way to finally solve a broader range of controversial many-body problems on future larger quantum devices.

quant-ph↗

arXiv2022

Plug-Play Plasmonic Metafibers for Ultrafast Fiber Lasers

Metafibers expand the functionalities of conventional optical fibers to unprecedented nanoscale light manipulations by integrating metasurfaces on the fiber tips, becoming an emerging light-coupling platform for both nanoscience and fiber optics communities. Mostly exploring the isolated bare fibers, current metafibers remain as proof-of-concept demonstrations due to a lack of standard interfaces with the universal fiber networks. Here, we develop new methodologies to fabricate well-defined plasmonic metasurfaces directly on the end facets of commercial single mode fiber jumpers using standard planar technologies and provide a first demonstration of their practical applications in the nonlinear optics regime. Featuring plug-play connections with fiber circuitry and arbitrary metasurfaces landscapes, the metafibers with tunable plasmonic resonances are implemented into fiber laser cavities, yielding all-fiber sub-picosecond (minimum 513 fs) soliton mode locked lasers at optical wavelengths of 1.5 micrometer and 2 micrometer, demonstrating their unusual polarimetric nonlinear transfer functions and superior saturation absorption responses. Novel insights into the physical mechanisms behind the saturable absorption of plasmonic metasurfaces are provided. The nanofabrication process flow is compatible with existing cleanroom technologies, offering metafibers an avenue to be a regular member of functionalized fiber components. The work paves the way towards next generation of ultrafast fiber lasers, optical frequency combs, optical neural networks and ultracompact "all-in-fibers" optical systems for sensing, imaging, communications, and many others.

physics.optics↗

arXiv2022

The Mean-Squared Error of Double Q-Learning

In this paper, we establish a theoretical comparison between the asymptotic mean-squared error of Double Q-learning and Q-learning. Our result builds upon an analysis for linear stochastic approximation based on Lyapunov equations and applies to both tabular setting and with linear function approximation, provided that the optimal policy is unique and the algorithms converge. We show that the asymptotic mean-squared error of Double Q-learning is exactly equal to that of Q-learning if Double Q-learning uses twice the learning rate of Q-learning and outputs the average of its two estimators. We also present some practical implications of this theoretical observation using simulations.

cs.LG↗