arXiv subjects

Lei Ying

Publications and source records attributed to Lei Ying.

At least 37 records · Page 2Linked to original sources

arXiv2025

Early Lung Cancer Diagnosis from Virtual Follow-up LDCT Generation via Correlational Autoencoder and Latent Flow Matching

Lung cancer is one of the most commonly diagnosed cancers, and early diagnosis is critical because the survival rate declines sharply once the disease progresses to advanced stages. However, achieving an early diagnosis remains challenging, particularly in distinguishing subtle early signals of malignancy from those of benign conditions. In clinical practice, a patient with a high risk may need to undergo an initial baseline and several annual follow-up examinations (e.g., CT scans) before receiving a definitive diagnosis, which can result in missing the optimal treatment. Recently, Artificial Intelligence (AI) methods have been increasingly used for early diagnosis of lung cancer, but most existing algorithms focus on radiomic features extraction from single early-stage CT scans. Inspired by recent advances in diffusion models for image generation, this paper proposes a generative method, named CorrFlowNet, which creates a virtual, one-year follow-up CT scan after the initial baseline scan. This virtual follow-up would allow for an early detection of malignant/benign nodules, reducing the need to wait for clinical follow-ups. During training, our approach employs a correlational autoencoder to encode both early baseline and follow-up CT images into a latent space that captures the dynamics of nodule progression as well as the correlations between them, followed by a flow matching algorithm on the latent space with a neural ordinary differential equation. An auxiliary classifier is used to further enhance the diagnostic accuracy. Evaluations on a real clinical dataset show our method can significantly improve downstream lung nodule risk assessment compared with existing baseline models. Moreover, its diagnostic accuracy is comparable with real clinical CT follow-ups, highlighting its potential to improve cancer diagnosis.

cs.CV↗

arXiv2025

ScarFinder: a detector of optimal scar trajectories in quantum many-body dynamics

Mechanisms that give rise to coherent quantum dynamics, such as quantum many-body scars, have recently attracted much interest as a way of controlling quantum chaos. However, identifying the presence of quantum scars in general many-body Hamiltonians remains an outstanding challenge. Here we introduce ScarFinder, a variational framework that reveals possible scar-like dynamics without prior knowledge of scar states or their algebraic structure. By iteratively evolving and projecting states within a low-entanglement variational manifold, ScarFinder isolates scarred trajectories by suppressing thermal contributions. We validate the method on the analytically tractable spin-1 XY model, recovering the known scar dynamics, as well as the mixed field Ising model, where we capture and generalize the initial conditions previously associated with ``weak thermalization''. We then apply the method to the PXP model of Rydberg atom arrays, efficiently characterizing its mixed phase space and finding a previously unknown trajectory with nearly-perfect revival dynamics in the thermodynamic limit. Our results establish ScarFinder as a powerful, model-agnostic tool for identifying and optimizing coherent dynamics in quantum many-body systems.

quant-ph↗

arXiv2025

Low-Energy Free-Electron Nonclassical Lasing

Harnessing a beam of slow free electrons in artificial photonic structures offers a powerful, tunable platform for generating nonclassical light without the need for heavy physical equipment. Here we present a theory of nonclassical lasing, demonstrating how incoherent electrons in photonic crystal cavities can coherently emit photons through collective dynamics. When photon emission rate exceeds cavity losses, nonclassical lasing with sub-Poissonian photon statistics emerges, driven by multi-photon Rabi oscillations. At specific coupling strengths, quantum state trapping effect emerges, producing high-fidelity Fock states at room temperature (e.g. nearly 90%-fidelity of four photon Fock state). Notably, the frequency of the emitted photons can be readily tuned via the velocity of the injected electrons to match cavity modes. This approach supports photonic integration and offers a scalable, energy-efficient platform for room-temperature quantum light sources and advanced studies in quantum electrodynamics.

physics.optics↗

arXiv2025

Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets

We study a two-sided market, wherein, price-sensitive heterogeneous customers and servers arrive and join their respective queues. A compatible customer-server pair can then be matched by the platform, at which point, they leave the system. Our objective is to design pricing and matching algorithms that maximize the platform's profit, while maintaining reasonable queue lengths. As the demand and supply curves governing the price-dependent arrival rates may not be known in practice, we design a novel online-learning-based pricing policy and establish its near-optimality. In particular, we prove a tradeoff among three performance metrics: $\tilde{O}(T^{1-γ})$ regret, $\tilde{O}(T^{γ/2})$ average queue length, and $\tilde{O}(T^γ)$ maximum queue length for $γ\in (0, 1/6]$, significantly improving over existing results [1]. Moreover, barring the permissible range of $γ$, we show that this trade-off between regret and average queue length is optimal up to logarithmic factors under a class of policies, matching the optimal one as in [2] which assumes the demand and supply curves to be known. Our proposed policy has two noteworthy features: a dynamic component that optimizes the tradeoff between low regret and small queue lengths; and a probabilistic component that resolves the tension between obtaining useful samples for fast learning and maintaining small queue lengths.

cs.LG↗

arXiv2025

Liouvillian Spectral Transition in Noisy Quantum Many-Body Scars

Understanding the behavior of quantum many-body systems under decoherence is essential for developing robust quantum technologies. Here, we examine the fate of weak ergodicity breaking in systems hosting quantum many-body scars when subject to local pure dephasing -- an experimentally relevant form of environmental noise. Focusing on a large class of models with an approximate su(2)-structured scar subspace, we show that scarred eigenmodes of the Liouvillean exhibit a transition reminiscent of spontaneous $\mathbb{PT}$-symmetry breaking as the dephasing strength increases. Unlike previously studied non-Hermitian mechanisms, this transition arises from a distinct quantum jump effect. Remarkably, in platforms such as the XY spin ladder and PXP model of Rydberg atom arrays, the critical dephasing rate shows only weak dependence on the system size, revealing an unexpected robustness of scarred dynamics in noisy environments.

quant-ph↗

arXiv2025

Dynamical phase evolution of Coulomb-focused electrons in strong-field ionization probed by a standing light wave

We investigate the dynamical phase evolution of Coulomb-focused electrons in strong-field ionization. We diffract the electrons with an ultrashort standing light wave to track their time-dependent phase. Our findings show that low-energy electrons exhibit a unique chromosome-shaped diffraction pattern, distinct from higher-energy electrons. Our numerical model quantitatively reproduces the experimental results, confirming this pattern maps the electron's time-dependent phase evolution as it escapes from a Coulomb potential. Our pulsed diffraction grating technique offers a new way to sense an electron's quantum phase without interfering its release mechanism.

physics.atom-ph↗

arXiv2025

Cavity-Quantum Electrodynamics with Moiré Flatband Photonic Crystals

Quantum emitters are a key component in photonic quantum technologies. Enhancing their single-photon emission by engineering the photonic environment using cavities can significantly improve the overall efficiency in quantum information processing. However, this enhancement is often constrained by the need for precise nanoscale control over the emitter's position within micro- or nano-cavities. Inspired by the fascinating physics of moiré patterns, we present an approach to strongly modify the spontaneous emission rate of a quantum emitter using a finely designed multilayer moiré photonic crystal with a robust isolated-flatband dispersion. Theoretical analysis reveals that, due to its nearly infinite photonic density of states, the moiré cavity can simultaneously achieve a high Purcell factor and exhibit large tolerance over the emitter's position. We experimentally demonstrate the coupling between this moiré cavity and a quantum dot through the cavity-determined polarization of the dot's emission. The radiative lifetime of the quantum dot can be tuned by a factor of 40, ranging from 42 ps to 1692 ps, which is attributed to strong Purcell enhancement and Purcell inhibition effects. Our findings pave the way for moiré flatband cavity-enhanced quantum light sources, quantum optical switches, and quantum nodes for quantum internet applications.

physics.optics↗

arXiv2025

Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation

We study the finite-horizon Restless Multi-Armed Bandit (RMAB) problem with $N$ homogeneous arms. Prior work has shown that when an RMAB satisfies a non-degeneracy condition, Linear-Programming-based (LP-based) policies derived from the fluid approximation, which captures the mean dynamics of the system, achieve an exponentially small optimality gap. However, it is common for RMABs to be degenerate, in which case LP-based policies can result in a $Θ(1/\sqrt{N})$ optimality gap per arm. In this paper, we propose a novel Stochastic-Programming-based (SP-based) policy that, under a uniqueness assumption, achieves an $\tilde{\mathcal{O}}(1/N)$ optimality gap for degenerate RMABs. Our approach is based on the construction of a Gaussian stochastic system that captures not only the mean but also the variance of the RMAB dynamics, resulting in a more accurate approximation than the fluid approximation. We then solve a stochastic program for this system to obtain our policy. This is the first result to establish an $\tilde{\mathcal{O}}(1/N)$ optimality gap for degenerate RMABs.

math.OC↗

arXiv2025

From Classification to Optimization: Slicing and Resource Management with TRACTOR

5G and beyond networks promise advancements in bandwidth, latency, and connectivity. The Open Radio Access Network (O-RAN) framework enhances flexibility through network slicing and closed-loop RAN control. Central to this evolution is integrating machine learning (ML) for dynamic network control. This paper presents a framework to optimize O-RAN operation. First, we build and share a robust O-RAN dataset from real-world traffic captured across diverse locations and mobility scenarios, replicated within a full-stack srsRAN-based O-RAN system using the Colosseum RF emulator. This dataset supports ML training and deployment. We then introduce a traffic classification approach leveraging various ML models, demonstrating rapid training, testing, and refinement to improve accuracy. With up to 99% offline accuracy and 92% online accuracy for specific slices, our framework adapts efficiently to different models and network conditions. Finally, we present a physical resource block (PRB) assignment optimization strategy using reinforcement learning to refine resource allocation. Our learned policy achieves a mean performance score (0.631), surpassing a manually configured expert policy (0.609) and a random baseline (0.588), demonstrating improved PRB utilization. More importantly, our approach exhibits lower variability, with the Coefficient of Variation (CV) reduced by up to an order of magnitude in three out of four cases, ensuring more consistent performance. Our contributions, including open-source tools and datasets, accelerate O-RAN and ML-driven network control research.

eess.SY↗

arXiv2025

Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces fundamental challenges such as distribution shift, reward model overfitting, and problem misspecification. An alternative approach is direct policy optimization without reward inference, such as Direct Preference Optimization (DPO), which provides a much simpler pipeline and has shown empirical success in LLM applications. However, DPO utilizes the closed-form expression between the optimal policy and the reward function, which is only suitable under the bandit setting or deterministic MDPs. This paper develops two RLHF algorithms without reward inference for general RL problems beyond bandits and deterministic MDPs, and general preference models beyond the Bradley-Terry model. The key idea is to estimate the local value function difference from human preferences and then approximate the policy gradient with a zeroth-order gradient approximator. For both algorithms, we establish polynomial convergence rates in terms of the number of policy gradient iterations, the number of trajectory samples, and human preference queries per iteration. Numerical experiments in stochastic environments validate the performance of our proposed algorithms, outperforming popular RLHF baselines such as DPO and PPO. Our paper shows there exist provably efficient methods to solve general RLHF problems without reward inference.

cs.LG↗

arXiv2025

Joint Optimal Transport and Embedding for Network Alignment

Network alignment, which aims to find node correspondence across different networks, is the cornerstone of various downstream multi-network and Web mining tasks. Most of the embedding-based methods indirectly model cross-network node relationships by contrasting positive and negative node pairs sampled from hand-crafted strategies, which are vulnerable to graph noises and lead to potential misalignment of nodes. Another line of work based on the optimal transport (OT) theory directly models cross-network node relationships and generates noise-reduced alignments. However, OT methods heavily rely on fixed, pre-defined cost functions that prohibit end-to-end training and are hard to generalize. In this paper, we aim to unify the embedding and OT-based methods in a mutually beneficial manner and propose a joint optimal transport and embedding framework for network alignment named JOENA. For one thing (OT for embedding), through a simple yet effective transformation, the noise-reduced OT mapping serves as an adaptive sampling strategy directly modeling all cross-network node pairs for robust embedding learning.For another (embedding for OT), on top of the learned embeddings, the OT cost can be gradually trained in an end-to-end fashion, which further enhances the alignment quality. With a unified objective, the mutual benefits of both methods can be achieved by an alternating optimization schema with guaranteed convergence. Extensive experiments on real-world networks validate the effectiveness and scalability of JOENA, achieving up to 16% improvement in MRR and 20x speedup compared with the state-of-the-art alignment methods.

cs.AI↗

arXiv2025

Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis

In this paper, we study reinforcement learning from human feedback (RLHF) under an episodic Markov decision process with a general trajectory-wise reward model. We developed a model-free RLHF best policy identification algorithm, called $\mathsf{BSAD}$, without explicit reward model inference, which is a critical intermediate step in the contemporary RLHF paradigms for training large language models (LLM). The algorithm identifies the optimal policy directly from human preference information in a backward manner, employing a dueling bandit sub-routine that constantly duels actions to identify the superior one. $\mathsf{BSAD}$ adopts a reward-free exploration and best-arm-identification-like adaptive stopping criteria to equalize the visitation among all states in the same decision step while moving to the previous step as soon as the optimal action is identifiable, leading to a provable, instance-dependent sample complexity $\tilde{\mathcal{O}}(c_{\mathcal{M}}SA^3H^3M\log\frac{1}δ)$ which resembles the result in classic RL, where $c_{\mathcal{M}}$ is the instance-dependent constant and $M$ is the batch size. Moreover, $\mathsf{BSAD}$ can be transformed into an explore-then-commit algorithm with logarithmic regret and generalized to discounted MDPs using a frame-based approach. Our results show: (i) sample-complexity-wise, RLHF is not significantly harder than classic RL and (ii) end-to-end RLHF may deliver improved performance by avoiding pitfalls in reward inferring such as overfit and distribution shift.

cs.LG↗

arXiv2024

Learning-Based Pricing and Matching for Two-Sided Queues

We consider a dynamic system with multiple types of customers and servers. Each type of waiting customer or server joins a separate queue, forming a bipartite graph with customer-side queues and server-side queues. The platform can match the servers and customers if their types are compatible. The matched pairs then leave the system. The platform will charge a customer a price according to their type when they arrive and will pay a server a price according to their type. The arrival rate of each queue is determined by the price according to some unknown demand or supply functions. Our goal is to design pricing and matching algorithms to maximize the profit of the platform with unknown demand and supply functions, while keeping queue lengths of both customers and servers below a predetermined threshold. This system can be used to model two-sided markets such as ride-sharing markets with passengers and drivers. The difficulties of the problem include simultaneous learning and decision making, and the tradeoff between maximizing profit and minimizing queue length. We use a longest-queue-first matching algorithm and propose a learning-based pricing algorithm, which combines gradient-free stochastic projected gradient ascent with bisection search. We prove that our proposed algorithm yields a sublinear regret $\tilde{O}(T^{5/6})$ and anytime queue-length bound $\tilde{O}(T^{1/6})$, where $T$ is the time horizon. We further establish a tradeoff between the regret bound and the queue-length bound: $\tilde{O}(T^{1-γ})$ versus $\tilde{O}(T^γ)$ for $γ\in (0, 1/6].$

math.OC↗

arXiv2024

Disorder-tunable entanglement at infinite temperature

Emerging quantum technologies hold the promise of unraveling difficult problems ranging from condensed matter to high energy physics, while at the same time motivating the search for unprecedented phenomena in their setting. Here we utilize a custom-built superconducting qubit ladder to realize non-thermalizing states with rich entanglement structures in the middle of the energy spectrum. Despite effectively forming an "infinite" temperature ensemble, these states robustly encode quantum information far from equilibrium, as we demonstrate by measuring the fidelity and entanglement entropy in the quench dynamics of the ladder. Our approach harnesses the recently proposed type of non-ergodic behavior known as "rainbow scar", which allows us to obtain analytically exact eigenfunctions whose ergodicity-breaking properties can be conveniently controlled by randomizing the couplings of the model, without affecting their energy. The on-demand tunability of quantum correlations via disorder allows for in situ control over ergodicity breaking and it provides a knob for designing exotic many-body states that defy thermalization.

quant-ph↗

arXiv2024

Cost Aware Best Arm Identification

In this paper, we study a best arm identification problem with dual objects. In addition to the classic reward, each arm is associated with a cost distribution and the goal is to identify the largest reward arm using the minimum expected cost. We call it \emph{Cost Aware Best Arm Identification} (CABAI), which captures the separation of testing and implementation phases in product development pipelines and models the objective shift between phases, i.e., cost for testing and reward for implementation. We first derive a theoretical lower bound for CABAI and propose an algorithm called $\mathsf{CTAS}$ to match it asymptotically. To reduce the computation of $\mathsf{CTAS}$, we further propose a simple algorithm called \emph{Chernoff Overlap} (CO), based on a square-root rule, which we prove is optimal in simplified two-armed models and generalizes well in numerical experiments. Our results show that (i) ignoring the heterogeneous action cost results in sub-optimality in practice, and (ii) simple algorithms can deliver near-optimal performance over a wide range of problems.

cs.LG↗

arXiv2024

MOSP: A User-interface Package for Simulating Metal Nanoparticle Structure and Reactivity under Operando Conditions

Structures of metal nanoparticles (NPs) significantly influence their catalytic reactivities. Recent in situ experimental observations of dramatic structural changes in NPs have underscored the need to establish a dynamic structure-property relationship that accounts for the reconstruction of NPs in reactive environments. Here, we present the MOSP, a free and open-source graphical user interface (GUI) package designed to simulate the structure and reactivity of metal NPs under operando conditions. MOSP integrates two models: the multiscale structure reconstruction (MSR) model predicting equilibrium metal NP structures under specific reaction conditions and the kinetic Monte Carlo (KMC) model simulating the reaction dynamics. This combination allows for the exploration of the dynamic structure-property relationships of NPs. MOSP enhances user accessibility through its intuitive GUI, facilitating easy input, post-processing, and visualization of simulation data. This article is the release note of MOSP, focusing on its implementation and functionality.

cond-mat.mtrl-sci↗

arXiv2024

Few-Body Quantum Chaos, Localization, and Multi-Photon Entanglement in Optical Synthetic Frequency Dimension

Generation and control of entanglement are fundamental tasks in quantum information processing. In this paper, we propose a novel approach to generate controllable frequency-entangled photons by using the concept of synthetic frequency dimension in an optical system. Such a system consists of a ring resonator made by a tailored third-order nonlinear media to induce photon-photon interactions and a periodic modulator to manipulate coupling between different frequency modes. We show this system provides a unique platform for the exploration of distinct few- or many-body quantum phases including chaos, localization, and integrability in a highly integrable photonics platform. In particular, we develop the potential experimental method to calculate the spectral form factor, which characterizes the degree of chaos in the system and differentiates between these phases based on observable measurements. Interestingly, the transition signatures of each phase can lead to an efficient generation of frequency-entangled multi photons. This work is the first to explore rich and controllable quantum phases beyond single particle in a synthetic dimension.

quant-ph↗

arXiv2024

Reconstructing Graph Diffusion History from a Single Snapshot

Diffusion on graphs is ubiquitous with numerous high-impact applications. In these applications, complete diffusion histories play an essential role in terms of identifying dynamical patterns, reflecting on precaution actions, and forecasting intervention effects. Despite their importance, complete diffusion histories are rarely available and are highly challenging to reconstruct due to ill-posedness, explosive search space, and scarcity of training data. To date, few methods exist for diffusion history reconstruction. They are exclusively based on the maximum likelihood estimation (MLE) formulation and require to know true diffusion parameters. In this paper, we study an even harder problem, namely reconstructing Diffusion history from A single SnapsHot} (DASH), where we seek to reconstruct the history from only the final snapshot without knowing true diffusion parameters. We start with theoretical analyses that reveal a fundamental limitation of the MLE formulation. We prove: (a) estimation error of diffusion parameters is unavoidable due to NP-hardness of diffusion parameter estimation, and (b) the MLE formulation is sensitive to estimation error of diffusion parameters. To overcome the inherent limitation of the MLE formulation, we propose a novel barycenter formulation: finding the barycenter of the posterior distribution of histories, which is provably stable against the estimation error of diffusion parameters. We further develop an effective solver named DIffusion hiTting Times with Optimal proposal (DITTO) by reducing the problem to estimating posterior expected hitting times via the Metropolis--Hastings Markov chain Monte Carlo method (M--H MCMC) and employing an unsupervised graph neural network to learn an optimal proposal to accelerate the convergence of M--H MCMC. We conduct extensive experiments to demonstrate the efficacy of the proposed method.

cs.LG↗