arXiv subjects

Lei Ying

Publications and source records attributed to Lei Ying.

At least 19 recordsLinked to original sources

arXiv2026

Near-Quadratic Error-Free Graph Matching above Otter's Threshold via Approximate Local Tree Correlation Testing

This paper presents a near-quadratic-time algorithm that correctly matches almost all nodes of two correlated Erdős-Rényi graphs without any incorrect matches. Each graph has average degree $λ$ and its edges are subsampled from a common parent Erdős-Rényi graph with $n$ nodes, with subsampling probability $s$. The nodes of one graph are then relabeled by an unknown permutation. The algorithm is built on a test for correlated versus independent Galton-Watson trees with approximated likelihood ratios. For every constant $s>\sqrt{C_{\mathrm{Otter}}}$, where $C_{\mathrm{Otter}}\approx0.338$ is Otter's tree-counting constant, and every $λ=ω(1)$ with $λ=(\log n)^{O(1)}$, the algorithm outputs a partial matching of size $n-o(n)$ that contains no incorrect matches with high probability. If, in addition, $λs\ge(1+ε)\log n$ for a constant $ε>0$, a seeded completion step recovers the permutation exactly. In both cases, the time complexity of the algorithm is $n^{2+o(1)}$ with high probability, whereas previous polynomial-time algorithms with the same guarantees either have a time-complexity bound whose exponent goes to $\infty$ as $s$ approaches $\sqrt{C_{\mathrm{Otter}}}$ from above, or apply only when $s$ is close to $1$.

cs.DS↗

arXiv2026

Zeroth-Order Policy Optimization for Scheduling in Queueing Networks

Reinforcement learning in queueing network scheduling presents significant challenges because of the countably infinite state space and the high stochasticity in transitions. In this paper, we propose zeroth-order policy optimization algorithms that are easy to implement and rely solely on estimates of the average cost, a single scalar quantity, without requiring the estimation of value or advantage functions. Our analysis focuses on back-pressure guarded policies and establishes uniform smoothness of the average cost objective with respect to the policy parameters. Building on this property, we establish finite-time convergence guarantees to an $ε$-stationary policy for the proposed algorithms. Numerical experiments on multiple queueing networks, including systems beyond classical exponential service distribution, demonstrate competitive performance, outperforming gradient-based RL methods like PPO and traditional queueing baselines.

cs.LG↗

arXiv2026

On the Approximation and Convergence of Distributional Policy Gradient Algorithms for Risk-Sensitive Reinforcement Learning

Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate of the random cumulative cost, distributional RL seeks to estimate the entire distribution of it, leading to a unified framework for handling different risk measures. However, developing policy gradient methods for risk-sensitive distributional RL is inherently more complex as it often involves finding the gradient of a probability measure. This paper introduces a new distributional policy gradient framework for risk-sensitive RL, where we derive an analytical gradient of the probability measure of the cumulative cost. For practical implementation, we further design a categorical distributional policy gradient algorithm (CDPG) that approximates arbitrary distributions using a categorical family supported on fixed points. Using Conditional Value-at-Risk (CVaR) as the objective, we prove that the proposed CDPG converges to stationary points and establish its iteration complexities under inexact policy evaluation. Through experiments in a stochastic Cliffwalk environment, we demonstrate the effectiveness of the proposed algorithm and highlight the benefits of incorporating risk sensitivity into distributional RL.

cs.LG↗

arXiv2026

Spatiotemporal programming via asymmetric dielectric engineering for nonvolatile 2D optoelectronics

Ambipolar two dimensional (2D) semiconductors integrated with floating-gate architectures offer a promising platform for nonvolatile, reconfigurable electronics. However, the switching between p-n and n-p junction polarities has conventionally required complex multi-gate designs, hindering the scalability and integration density. Here, we demonstrate a spatiotemporal programming strategy using a dual-floating-gate architecture with a symmetry broken tunneling dielectric. An asymmetric dielectric stack creates distinct tunneling thresholds for two floating gates, enabling a single input gate to encode spatial doping profiles in the 2D channel via defined voltage pulse sequences. We achieve on demand, nonvolatile, and reversible switching between p-n and n-p configurations with excellent retention and endurance. The reconfigurable homojunction serves as a multifunctional platform for logic encoding, rectification, photodetection, and in sensor computing. This work establishes a design paradigm that replaces spatial input complexity with spatiotemporal programming, paving the way for high-density, multifunctional intelligent hardware.

cond-mat.mes-hall↗

arXiv2026

Beyond Scaling: Calculable Error Bounds of the Power-of-Two-Choices Mean-Field Model in Heavy-Traffic

This paper provides a recipe for deriving calculable approximation errors of mean-field models in heavy-traffic with the focus on the well-known load balancing algorithm---power-of-two-choices (Po2). The recipe combines Stein's method for linearized mean-field models and State Space Concentration (SSC) based on geometric tail bounds. In particular, we divide the state space into two regions, a neighborhood near the mean-field equilibrium and the complement of that. We first use a tail bound to show that the steady-state probability being outside the neighborhood is small. Then, we use a linearized mean-field model and Stein's method to characterize the generator difference, which provides the dominant term of the approximation error. From the dominant term, we are able to obtain an asymptotically-tight bound, a calculable bound, not order-wise scaling results like most results in the literature. Finally, we compare the theoretical bound with numerical evaluations to show the effectiveness of our results. We note that the simulation results show that the bound is valid even for small size systems such as a system with only hundred servers.

cs.PF↗

arXiv2026

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling

Preference-based reinforcement learning (PbRL) for general stochastic MDPs often requires training a reward model. Existing reward-model-free methods are either restricted to bandits or deterministic MDPs, such as DPO or P3O, or use zeroth-order, gradient-free optimization, which in general exhibits a slower convergence rate than gradient-based algorithms. Furthermore, existing reward-model-free preference-based RL algorithms almost exclusively use trajectory-level feedback, which can require significant effort from a human evaluator when trajectories are long. On the other hand, segments are much shorter, so they are easier to compare and evaluate. In this paper, we introduce a novel reward-model-free, critic-free, and gradient-based PbRL algorithm compatible with segment preferences named Segment Pairwise Proximal Policy Optimization (SP3O). SP3O utilizes segment-level preference feedback to construct an accurate policy value difference estimator via off-policy importance sampling, and then uses the estimator to compute the policy gradient via a PPO-type loss function. We provide a theoretical basis for the algorithm and analyze the tradeoff in choosing the segment length. We also evaluate it experimentally against other PbRL/RLHF algorithms in robotic control and LLM finetuning settings to show its improved performance, especially in long-horizon tasks.

cs.LG↗

arXiv2026

Achieving Almost Exact Recovery in Almost Quadratic Time: Rank-Based Graph Matching via Local Tree Correlation Tests

This paper studies graph matching under the correlated $\text{Erdős-Rényi}$ (ER) graph pair model. This model first samples an $\mathrm{ER}(n,\fracλ{ns})$ base graph, whose edges are then independently subsampled twice with probability $s$ to produce two correlated $\mathrm{ER}(n,\fracλ{n})$ graphs. We propose a graph matching algorithm that has $n^{2+o(1)}$ time complexity and achieves almost exact recovery with high probability under the assumptions $λ=(\log n)^{α+o(1)}$ for some $α\in(0,1)$ and $s\in(\sqrt{C_{\mathrm{Otter}}},1]$, where $C_{\mathrm{Otter}}\approx 0.338$ is Otter's tree-counting constant. This is the first algorithm with almost quadratic time complexity in this regime of $λ$, while the best known result in this regime is the chandelier-counting algorithm with time complexity $O(n^{c(s)})$, where $c(s)\rightarrow \infty$ as $s$ approaches $\sqrt{C_\mathrm{Otter}}$ from above. The proposed algorithm is based on local tree correlation tests. It uses a rank-based algorithm to match the vertex pairs instead of threshold-based rules in the literature. This avoids the need of computing an explicit threshold, which is computationally difficult to obtain. To prove the almost exact recovery result, we establish a new analysis of tree correlation tests in the diverging-degree regime, where both the mean degree and the tree depth grow with $n$. Based on this new result, we establish the existence of a threshold for a threshold-based graph matching algorithm via local tree correlation tests. Finally, we couple the performance of the rank-based algorithm with the threshold-based algorithm to show almost exact recovery.

cs.DS↗

arXiv2026

Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function

The link function, which characterizes the relationship between the preference for two trajectories and their returns, is a crucial component in designing RL algorithms that learn from preference feedback. Most existing methods, both theoretical and empirical, assume that the link function is known (often a logistic function based on the Bradley-Terry model), which is arguably restrictive given the complex nature of preferences, especially those of humans. To avoid mis-specification, this paper studies preference-based RL with an unknown link function and proposes a novel zeroth-order policy optimization algorithm called Sign-SZPO. Unlike typical zeroth-order methods, which rely on the known link function to estimate the value function differences and form a gradient estimator, Sign-SZPO only estimates the sign of the value function difference. It then constructs a parameter update direction that is positively correlated with the true policy gradient, eliminating the need to know the link function exactly. Under mild conditions, Sign-SZPO provably converges to a stationary policy with a polynomial rate in the number of policy iterations and trajectories per iteration. Empirical evaluations further demonstrate the robustness of Sign-SZPO under link function mis-specifications.

cs.LG↗

arXiv2026

Quantum many-body mixed phase space revealed by hybrid feedback control

Understanding how complex systems transition between order and chaos is a central challenge of nonequilibrium physics. While weak perturbations of classical integrable systems give rise to a mixed phase space of coexisting regular and chaotic trajectories, analogous behavior in interacting quantum many-body systems has remained elusive. Here we develop and experimentally implement a hybrid quantum-classical feedback protocol that autonomously discovers and stabilizes long-lived regular trajectories in a superconducting quantum processor. Each iteration combines short-time quantum evolution with classical optimization that projects the dynamics back onto a low-entanglement variational manifold, effectively distilling coherence from chaotic evolution. The stabilized trajectories reveal a quantum many-body mixed phase space emerging from nonlinear variational dynamics, without a direct analogue in classical or few-body quantum systems. Our results establish a versatile framework for algorithmic discovery and control of coherent dynamics previously inaccessible to experiment.

quant-ph↗

arXiv2026

Steady-State Approximation Error of Heterogeneous Mean-Field Models

This paper studies heterogeneous mean-field models in which agent parameters are sampled from a population distribution. We establish an $O(1/M)$ bound on the steady-state mean-square error between the occupancy measure of the $M$-agent system and the corresponding annealed mean-field equilibrium. The analysis extends Stein's method for homogeneous mean-field models and reveals a fundamental difference between homogeneous and heterogeneous systems. While stability of the mean-field dynamics is sufficient in the homogeneous setting, heterogeneous systems further require uniform robustness of the occupancy dynamics with respect to perturbations of the initial condition. The results are illustrated through a heterogeneous SIS epidemic model.

math.PR↗

arXiv2026

Diffusion-Network Alignment: An Efficient Algorithm and Explicit Probability Bounds

This paper studies a variation of the classic network alignment problem, named diffusion-network alignment. The goal is to align the vertices of a rooted diffusion tree to the vertices of a network, where the diffusion tree could be from a communication trace or contact tracing, and the network could be an online or offline social network. Different from the classic network alignment where both networks are fully observed, this model captures the information asymmetry of two networks. To solve this problem, this paper presents an efficient algorithm based on tree correlation tests to extract alignment information from local neighborhoods. We analyze the performance of the algorithm in the sparse graph regime and show that with high probability, all matched pairs are correct. Furthermore, for each vertex on the diffusion tree, this paper establishes an explicit lower bound on the probability that the vertex is correctly matched. These lower bounds are depth-dependent and increase as vertices get closer to the root.

cs.DS↗

arXiv2026

Interaction-enabled metal-insulator phase transition in a driven quantum gas

Particle transport and energy flow are central to a wide range of phenomena in the natural sciences. While interactions generically promote ergodicity and diffusion, quantum interference can arrest transport, defying classical expectations. Here, we experimentally investigate their interplay in a periodically driven 3D quantum gas with tunable interactions. Strikingly, we find a sharp dynamical boundary separating localization from diffusive energy absorption. By tuning the driving amplitude and interaction strength, we map the localization-delocalization phase diagram and characterize this boundary via finite-time scaling. On the insulating side, we observe many-body dynamical localization (MBDL) featuring arrested momentum-space transport. Transport becomes subdiffusive near the boundary and diffusive in the delocalized regime, yielding a metal-insulator transition that we interpret as localization in many-body Hilbert space. Our results exemplify an interaction-enabled dynamical phase transition in a closed Floquet many-body system, and clarify how coherence and interactions jointly govern the quantum-to-classical transition.

cond-mat.quant-gas↗

arXiv2026

Nonlinear Photonic Tripartite Phase

Anderson localization is usually understood as a transition between extended and localized phases, with criticality confined to a single mobility edge. Recent advances predict that quasiperiodic systems can instead host a finite critical window bounded by mobility edges, in which localized, critical and extended states coexist. Yet both the experimental realization of this regime and whether interactions can provide controlled access to it remain unknown. Here, we realize such a tripartite phase in a nonlinear quasiperiodic photonic lattice and show that Kerr nonlinearity, acting as an effective interaction, enables state-selective access to the critical window. By tracking wavepacket dynamics, we distinguish localized, critical and extended transport regimes and uncover a state-selective response: rather than simply reinforcing localization through self-trapping, weak nonlinearity drives low-energy localized states into the critical window, whereas stronger nonlinearity restores localization. By contrast, critical, extended and high-energy localized states evolve monotonically towards self-trapped behaviour. Our results reveal a state-selective mechanism by which interactions provide controlled access to a pre-existing critical window in quasiperiodic systems.

cond-mat.mes-hall↗

arXiv2026

Efficient Federated RLHF via Zeroth-Order Policy Optimization

This paper considers reinforcement learning from human feedback in a federated learning setting with resource-constrained agents, such as edge devices. We propose an efficient federated RLHF algorithm, named Partitioned, Sign-based Stochastic Zeroth-order Policy Optimization (Par-S$^2$ZPO). The algorithm is built on zeroth-order optimization with binary perturbation, resulting in low communication, computation, and memory complexity by design. Our theoretical analysis establishes an upper bound on the convergence rate of Par-S$^2$ZPO, revealing that it is as efficient as its centralized counterpart in terms of sample complexity but converges faster in terms of policy update iterations. Our experimental results show that it outperforms a FedAvg-based RLHF on four MuJoCo RL tasks.

cs.LG↗

arXiv2026

Origin and emergent features of many-body dynamical localization

The question of whether interactions can break dynamical localization in quantum kicked rotor systems has been the subject of a long--standing debate. Here, we introduce an extended mapping from the kicked Lieb--Liniger model to a high--dimensional lattice model and reveal universal features: on--site pseudorandomness and hybrid exponential--algebraic decay couplings with increasing momenta. We find that the exponent and the amplitude of the algebraic decay undergo a crossover as the interaction strength increases. This mapping uncovers the origin of dynamical localization and the interaction effect on the integrability of the system. An analysis of the generalized fractal dimension and level--spacing ratio supports these findings, highlighting the presence of near integrability and multifractality in different regions of parameter space. Our results offer an explanation for the occurrence of many--body dynamical localization, particularly in strongly correlated quantum gases, and are anticipated to generalize to systems of many particles.

cond-mat.quant-gas↗

arXiv2026

Temperature effect on a kicked Tonks-Girardeau gas

It is widely recognized that finite temperatures degrade quantum coherence and can induce thermalization. Here, we study the effect of finite temperature on a kicked Tonks--Girardeau gas, which is known to exhibit many--body dynamical localization and delocalization under periodic and quasiperiodic kicks, respectively. We find that many--body dynamical localization persists at finite--and even high--temperatures, although the coherence of the localized state is further degraded. In particular, we demonstrate a modified effective thermalization of the localized state by considering the initial temperature. Moreover, we show many--body dynamical localization transition at intermediate temperature. Our work extends the study of many--body dynamical localization and delocalization to the finite--temperature regime, providing guidance for cold-atom experiments, particularly in the strongly-interacting regime.

quant-ph↗

arXiv2026

Zero-Waiting Load Balancing with Heterogeneous Servers in Heavy Traffic

We study the steady-state delay performance of load balancing in large-scale systems with heterogeneous servers in the heavy-traffic regimes. The system consists of $N$ servers, each with a local buffer of size $b-1$, serving jobs in the first-in-first-out (FIFO) order. Jobs arrive according to a Poisson process with rate $λN$, where $λ= 1 - N^{-α}$ for any $α\in (0,1)$. Service times are assumed to be exponentially distributed with fully heterogeneous rates, where the service rate of each server can differ and may scale with the system size $N$. We study a queue length aware and service rate aware load balancing policy, Join-the-Fastest-Shortest-Queue (JFSQ), and demonstrate that it achieves asymptotic zero waiting time and probability under the heavy traffic regimes, including both the Sub-Halfin-Whitt ($α\in (0,0.5)$) and Super-Halfin-Whitt ($α\in [0.5,1)$) regimes. The performance bounds of waiting time and probability explicitly capture the convergence rate w.r.t. the system size $N$ and show the negative effect of server heterogeneity. Our analysis builds on the general framework of Stein's method with iterative state-space peeling, where we design a sequence of Lyapunov functions to analyze the high-dimensional heterogeneous system without assuming exchangeability and monotonicity. Our analysis shows that JFSQ efficiently utilizes servers with higher capacities, and the steady-state system can be coupled with a single-server queue via Stein's method. To the best of our knowledge, this is the first work to establish delay performance bounds of a load-balancing system with size $N$ and fully heterogeneous servers in heavy traffic.

math.PR↗

arXiv2026

Interaction-induced moiré lattices: from mosaic mobility edges to many-body localization

We study localization driven solely by interparticle interactions in moiré lattice systems without intrinsic disorder or externally imposed quasiperiodic potentials. We consider a one-dimensional bilayer with incommensurate lattice constants, described by a spin-dependent Fermi-Hubbard-type model with short-range interlayer interactions, where quasiperiodicity emerges only through interactions. Exact diagonalization shows that quenching hopping in one layer generates an interaction-induced mosaic potential with multiple mobility edges. When both layers are dynamical, increasing interlayer interactions drives transitions among ergodic, critical, and many-body localized regimes, with energy-dependent coexistence in certain parameter ranges. An exact mapping to a noninteracting single-particle model on a higher-dimensional structured graph provides a unified interpretation of these results and suggests an experimentally accessible route to interaction-induced moiré physics and localization.

cond-mat.dis-nn↗