Searcharxiv⌕ Search

arXiv subjects

Ning Ning

Publications and source records attributed to Ning Ning.

At least 19 recordsLinked to original sources

On the Convergence of Continuous-Time AdamW

Continuous-time AdamW provides a framework for understanding whether an optimizer widely used to train large-scale neural networks settles to an equilibrium or sustains persistent motion. We study this long-time behavior while retaining bias correction and fixed positive weight decay. Under suitable assumptions, we establish that the dynamics are well defined for all time and remain bounded when the decay is sufficiently small. Our main result connects their limiting behavior to the geometry of the objective: trajectories approach a locally invariant manifold whose dimension equals the Hessian nullity along the associated critical component. When critical points are isolated and have at most one such direction, the trajectory converges to a single equilibrium. With two degenerate directions, however, bounded persistent motion can occur even for a smooth, strictly convex objective with a unique minimum. We also quantify how close the long-time trajectory remains to the critical set as weight decay decreases, without assuming convergence to a point. These results identify objective geometry as a key to understanding when continuous-time AdamW converges and when persistent motion is possible.

math.OC↗

Control-Geometry Straightening for Sampling-Based Latent Planning

Joint-embedding predictive architectures enable planning with latent world models, but accurate transition prediction alone does not ensure that the planning objective is easy to optimize. We introduce Control-Geometry Straightening (CGS), a single auxiliary loss that learns planner-friendly representations by directly straightening control geometry for sampling-efficient planning. CGS matches pairwise cosine similarities among actions to those among corresponding latent differences only using local transitions from pixel-action pairs. The loss can be applied across world-model architectures using end-to-end learned or pretrained representations. Under linear-dynamics, our theoretical analysis connects this objective to temporal straightening and more balanced terminal-cost curvature across the full planning horizon, yielding finite-budget guarantees for MPPI, local contraction results for CEM, and convergence bounds for gradient descent. Across four control environments and multiple planners, CGS improves planning with fewer sampled candidates and refinement steps, achieving success-rate gains up to 20 and 12.6 percentage points over LeWorldModel (LeWM) and its temporal-straightening variant (LeWM+TS), respectively, with sampling-based planners using 128 candidates per update. Probes, comparisons with DINO-WM architecture, and planner-side ablations clarify how latent motion organization, state dependence, and dynamical context shape planning behavior. Straightening control geometry thus makes good action sequences easier to find under limited planning budgets.

cs.LG↗

MASLA: Metropolis-Adjusted Subdifferential Langevin Sampling for Nonsmooth Nonconvex Potentials

Sampling from distributions with nonsmooth nonconvex potentials challenges gradient-based Langevin methods and can complicate proximal approaches. We introduce Metropolis-adjusted subdifferential Langevin algorithm (MASLA), which combines a fixed measurable selection from a conservative field with an exact Metropolis--Hastings correction. The method accommodates locally Lipschitz potentials without requiring smoothing or a proximal mapping. We establish well-posedness, reversibility, and exact invariance of the target distribution, together with positive Harris recurrence. Our central theoretical result rigorously proves geometric ergodicity for positive-definite quadratic potentials perturbed by Lipschitz functions admitting bounded conservative fields. The result provides an explicit admissible range of step sizes and holds from every initial point, including points of nondifferentiability. Numerical experiments verify the predicted geometric convergence behavior on a convex composite target and demonstrate competitive performance against proximal and subgradient samplers. Further experiments on a nonsmooth nonconvex target show that the Metropolis correction substantially reduces sampling error relative to unadjusted subdifferential Langevin dynamics. These results establish MASLA as a theoretically grounded sampling method for a class of nonsmooth nonconvex distributions.

stat.ME↗

ViBR-WM: Visual Bayesian Regression for World Modeling

Modeling temporal dependence and uncertainty is central to forecasting with world models. The Visual Bayesian Regression World Model combines visual features, physical histories and known covariates through interpretable regression, within a modular architecture supporting trend, seasonal and cycle dynamics. Visual compression reduces representation dimension, while Bayesian variable selection reduces active regression dimension. Posterior prediction combines forecasts across predictor subsets using their posterior probabilities as weights and accounts for parameter uncertainty and future disturbances. The model forecasts joint visual--physical states recursively and physical targets directly. Across four forecasting tasks spanning object motion, vegetation greenness and solar power, ViBR-WM achieves lower mean overall physical-target error than Temporal Straightening, ConvLSTM, PredRNN and SimVP on every task. Repeated fitting and resampling support these overall gains.

stat.ME↗

Newton-Schulz Retraction-Based Inference Enables Hidden Quantum Markov Models to Outperform Classical HMMs

Hidden Markov models (HMMs) are widely used probabilistic models for discrete sequential data but can be limited when hidden dynamics are complex. Hidden quantum Markov models (HQMMs) generalize HMMs by replacing probability vectors with density matrices and stochastic transitions with quantum operations, enabling richer latent representations. However, existing HQMM learning methods have not consistently outperformed Expectation--Maximization (EM)-trained HMMs on data not generated by quantum processes, limiting their practical applicability. We introduce NS-RIS, Newton--Schulz Retraction-based Inference on the Stiefel manifold, a scalable algorithm for learning trace-preserving HQMMs. NS-RIS uses Newton--Schulz orthogonalization to compute a polar-factor search direction while preserving Stiefel-manifold feasibility, avoiding costly matrix decompositions. We further establish a finite-time stationarity guarantee under standard assumptions on smoothness, stochastic gradients, and finite Newton--Schulz accuracy. Empirically, NS-RIS provides the first benchmark evidence that an HQMM can significantly outperform an EM-trained HMM on data not generated by a quantum model. On synthetic HMM-generated benchmarks, NS-RIS outperforms both EM and the state-of-the-art HQMM method COSM, improving the evaluation metric by an average of 38.5% and by up to 50.6%. On a synthetic HQMM benchmark, it improves the test metric over COSM by 18.9% while reducing runtime by 12.0%. On the real-world Splice classification benchmark, NS-RIS also surpasses both EM and COSM in higher-dimensional latent regimes, reducing mean classification error by 17.9% for latent dimension 6 and 14.9% for latent dimension 8 relative to COSM. These results move HQMMs beyond a theoretical generalization of HMMs and establish them as practical and expressive models for scientific sequence data.

cs.LG↗

Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization

The performance of deep spiking neural networks (SNNs) often relies on batch normalization (BN). However, the advanced dynamic BN variants used in state-of-the-art models introduce runtime multiplications, which weaken the hardware-efficiency motivation of SNNs. To address this tension, we identify catastrophic firing-rate decay as a primary cause of severe performance degradation in normalization-free SNNs. Guided by this insight, this work proposes the Intrinsically Stable SNN (IS-SNN) architecture, which removes activation-normalization layers by enforcing signal homeostasis through topology-aware weight standardization and modified residual connections. By folding the standardization operations into static weights offline, IS-SNN removes the runtime statistics tracking and multiplications introduced by activation normalization, restoring an accumulation-oriented inference datapath. Comprehensive experiments show that IS-SNN achieves performance competitive with or superior to computationally expensive dynamic BN techniques across VGG, ResNet, and Transformer-based models. Notably, it achieves a competitive accuracy of 68.05\% on ImageNet and overcomes the severe depth limitations of prior BN-free attempts. Together with a 96.4\% reduction in FPGA lookup table resource consumption for neuron implementations, these results support IS-SNN as a practical framework for building accurate and hardware-friendly deep neuromorphic systems.

cs.CV↗

Change-point estimation for Weibull time series with copula-based Markov models

We study offline change-point estimation for time series data exhibiting nonlinear serial dependence. To address this problem, we propose a copula-based Markov chain model with Weibull marginal distributions, which is suitable for modeling nonnegative data such as event times and volatility measures. Nonlinear dependence is incorporated through the Clayton and Joe copulas, allowing the model to capture asymmetric lower-tail and upper-tail dependence structures, respectively. We derive the corresponding likelihood function and estimate the change point and model parameters using maximum likelihood estimation implemented through the Newton--Raphson algorithm. Confidence intervals are constructed via a parametric bootstrap Monte Carlo procedure. Extensive numerical studies are conducted to evaluate the finite-sample performance and robustness of the proposed method under different dependence structures and copula misspecification scenarios. The results demonstrate that the proposed estimators perform well in terms of RMSE and relative error, particularly for the estimation of the change point. An empirical application to the VIX index during the COVID-19 pandemic further illustrates the practical usefulness of the proposed approach in detecting structural changes in both the marginal distributions and serial dependence structure.

stat.ME↗

Bayesian Inference for Partially Observed McKean-Vlasov SDEs with Full Distribution Dependence

McKean-Vlasov stochastic differential equations (MVSDEs) describe systems whose dynamics depend on both individual states and the population distribution, and they arise widely in neuroscience, finance, and epidemiology. In many applications the system is only partially observed, making inference very challenging when both drift and diffusion coefficients depend on the evolving empirical law. This paper develops a Bayesian framework for latent state inference and parameter estimation in such partially observed MVSDEs. We combine time-discretization with particle-based approximations to construct tractable likelihood estimators, and we design two particle Markov chain Monte Carlo (PMCMC) algorithms: a single-level PMCMC method and a multilevel PMCMC (MLPMCMC) method that couples particle systems across discretization levels. The multilevel construction yields correlated likelihood estimates and achieves mean square error $(O(\varepsilon^2))$ at computational cost $(O(\varepsilon^{-6}))$, improving on the $(O(\varepsilon^{-7}))$ complexity of single-level schemes. We address the fully law-dependent diffusion setting which is the most general formulation of MVSDEs, and provide theoretical guarantees under standard regularity assumptions. Numerical experiments confirm the efficiency and accuracy of the proposed methodology.

stat.CO↗

Quantum Expander Mixing Lemma and its Structural Converse

Expander graphs are fundamental in both computer science and mathematics, with a wide array of applications. With quantum technology reshaping our world, quantum expanders have emerged, finding numerous uses in quantum information theory, quantum complexity, and noncommutative pseudorandomness. The classical expander mixing lemma plays a central role in graph theory, offering essential insights into edge distribution within graphs and aiding in the analysis of diverse network properties and algorithms. This paper establishes the quantum analogue of the classical expander mixing lemma and its structural converse for quantum expanders.

quant-ph↗

Stationary Point Constrained Inference via Diffeomorphisms

Stationary points or derivative zero crossings of a regression function correspond to points where a trend reverses, making their estimation scientifically important. Existing approaches to uncertainty quantification for stationary points cannot deliver valid joint inference when multiple extrema are present, an essential capability in applications where the relative locations of peaks and troughs carry scientific significance. We develop a principled framework for functions with multiple regions of monotonicity by constraining the number of stationary points. We represent each function in the diffeomorphic formulation as the composition of a simple template and a smooth bijective transformation, and show that this parameterization enables coherent joint inference on the extrema. This construction guarantees a prespecified number of stationary points and provides a direct, interpretable parameterization of their locations. We derive non-asymptotic confidence bounds and establish approximate normality for the maximum likelihood estimators, with parallel results in the Bayesian setting. Simulations and an application to brain signal estimation demonstrate the method's accuracy and interpretability.

stat.ME↗

I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks

Spiking neural networks (SNNs) promise highly energy-efficient computing, but their adoption is hindered by a critical scarcity of event-stream data. This work introduces I2E, an algorithmic framework that resolves this bottleneck by converting static images into high-fidelity event streams. By simulating microsaccadic eye movements with a highly parallelized convolution, I2E achieves a conversion speed over 300x faster than prior methods, uniquely enabling on-the-fly data augmentation for SNN training. The framework's effectiveness is demonstrated on large-scale benchmarks. An SNN trained on the generated I2E-ImageNet dataset achieves a state-of-the-art accuracy of 60.50%. Critically, this work establishes a powerful sim-to-real paradigm where pre-training on synthetic I2E data and fine-tuning on the real-world CIFAR10-DVS dataset yields an unprecedented accuracy of 92.5%. This result validates that synthetic event data can serve as a high-fidelity proxy for real sensor data, bridging a long-standing gap in neuromorphic engineering. By providing a scalable solution to the data problem, I2E offers a foundational toolkit for developing high-performance neuromorphic systems. The open-source algorithm and all generated datasets are provided to accelerate research in the field.

cs.CV↗

Robust Iterative Learning Hidden Quantum Markov Models

Hidden Quantum Markov Models (HQMMs) extend classical Hidden Markov Models to the quantum domain, offering a powerful probabilistic framework for modeling sequential data with quantum coherence. However, existing HQMM learning algorithms are highly sensitive to data corruption and lack mechanisms to ensure robustness under adversarial perturbations. In this work, we introduce the Adversarially Corrupted HQMM (AC-HQMM), which formalizes robustness analysis by allowing a controlled fraction of observation sequences to be adversarially corrupted. To learn AC-HQMMs, we propose the Robust Iterative Learning Algorithm (RILA), a derivative-free method that integrates a Remove Corrupted Rows by Entropy Filtering (RCR-EF) module with an iterative stochastic resampling procedure for physically valid Kraus operator updates. RILA incorporates L1-penalized likelihood objectives to enhance stability, resist overfitting, and remain effective under non-differentiable conditions. Across multiple HQMM and HMM benchmarks, RILA demonstrates superior convergence stability, corruption resilience, and preservation of physical validity compared to existing algorithms, establishing a principled and efficient approach for robust quantum sequential learning.

cs.LG↗

Well-posedness and propagation of chaos for McKean-Vlasov stochastic variational inequalities

In this paper, we study a broad class of McKean-Vlasov stochastic variational inequalities (MVSVIs), where both the drift coefficient $b$ and the diffusion coefficient $σ$ depend on time $t$, the state $X_t$ and its distribution $μ_t$. We establish the strong well-posedness, when $b$ is superlinear growth and locally Lipschitz continuous, and $σ$ is locally Hölder continuous, both with respect to $X_t$ and $μ_t$. Additionally, we present the first propagation of chaos result for MVSVIs.

math.PR↗

Hysteretic Multivariate Bayesian Structural GARCH Model with Soft Information

This study introduces the SH-MBS-GARCH model, a hysteretic multivariate Bayesian structural GARCH framework that integrates hard and soft information to capture the joint dynamics of multiple financial time series, incorporating hysteretic effects and addressing conditional heteroscedasticity through GARCH components. Various model specifications could utilize soft information to define the regime indicator in distinct ways. We propose a flexible, straightforward method for embedding soft information into the regime component, applicable across all SH-MBS-GARCH model variants. We further propose a generally applicable Bayesian estimation approach that combines adaptive MCMC, spike-and-slab regression, and a simulation smoother, ensuring accurate parameter estimation, validated through extensive simulations. Empirical analysis of the Dow Jones Industrial Average, NASDAQ Composite, and PHLX Semiconductor indices from January 2016 to December 2020 demonstrates that the SH-MBS-GARCH model outperforms competing models in fitting and prediction accuracy, effectively capturing regime-switching dynamics.

stat.CO↗

Stochastic Differential Equations Driven by G-Brownian Motion with Mean Reflections

In this paper, we study the mean reflected stochastic differential equations driven by G-Brownian motion, where the constraint depends on the expectation of the solution rather than on its paths. Well-posedness is achieved by first investigating the Skorokhod problem with mean reflection under G-expectation. Two approaches to constructing the solution are introduced, both offering insights into desired properties and aiding in the application of the contraction mapping method.

math.PR↗

Optimizing Global Genomic Surveillance for Early Detection of Emerging SARS-CoV-2 Variants

Background: Global viral threats underscore the need for effective genomic surveillance, but high costs and uneven resource distribution hamper its implementation. Targeting surveillance to international travelers in major travel hubs may offer a more efficient strategy for the early detection of SARS-CoV-2 variants. Methods: We developed and calibrated a multiple-strain metapopulation model of global SARS-CoV-2 transmission using extensive epidemiological, phylogenetic, and high-resolution air travel data. We then compared baseline surveillance with various resource-allocation approaches that prioritize travelers, focusing on Omicron BA.1/BA.2 retrospectively and on hypothetical future variants under different emergence, transmission and vaccine effectiveness scenarios. Findings: Focusing existing surveillance resources on travelers at key global hubs significantly shortened detection delays without increasing total surveillance efforts. In retrospective analyses of Omicron BA.1/BA.2, traveler-targeted approaches consistently outperformed baseline strategies, even when overall resources were reduced. Simulations indicate that focusing surveillance on key travel hubs outperform baseline practices in detecting future variants, across different possible origins, even with reduced resources. This approach also remains effective in future pandemic scenarios with varying reproductive numbers and vaccine effectiveness. Interpretation: These findings provide a quantitative, cost-effective framework for strengthening global genomic surveillance. By reallocating resources toward international travelers in select travel hubs, early detection of emerging variants can be enhanced, informing rapid public health interventions and bolstering preparedness for future pandemics.

q-bio.PE↗

Convergence of Dirichlet Forms for MCMC Optimal Scaling with Dependent Target Distributions on Large Graphs

Markov chain Monte Carlo (MCMC) algorithms have played a significant role in statistics, physics, machine learning and others, and they are the only known general and efficient approach for some high-dimensional problems. The random walk Metropolis (RWM) algorithm as the most classical MCMC algorithm, has had a great influence on the development and practice of science and engineering. The behavior of the RWM algorithm in high-dimensional problems is typically investigated through a weak convergence result of diffusion processes. In this paper, we utilize the Mosco convergence of Dirichlet forms in analyzing the RWM algorithm on large graphs, whose target distribution is the Gibbs measure that includes any probability measure satisfying a Markov property. The abstract and powerful theory of Dirichlet forms allows us to work directly and naturally on the infinite-dimensional space, and our notion of Mosco convergence allows Dirichlet forms associated with the RWM chains to lie on changing Hilbert spaces. Through the optimal scaling problem, we demonstrate the impressive strengths of the Dirichlet form approach over the standard diffusion approach.

math.ST↗

Detecting Structural Shifts and Estimating Change-Points in Interval-Based Time Series

This paper addresses the open problem of conducting change-point analysis for interval-valued time series data using the maximum likelihood estimation (MLE) framework. Motivated by financial time series, we analyze data that includes daily opening (O), up (U), low (L), and closing (C) values, rather than just a closing value as traditionally used. To tackle this, we propose a fundamental model based on stochastic differential equations, which also serves as a transformation of other widely used models, such as the log-transformed geometric Brownian motion model. We derive the joint distribution for these interval-valued observations using the reflection principle and Girsanov's theorem. The MLE is obtained by optimizing the log-likelihood function through first and second-order derivative calculations, utilizing the Newton-Raphson algorithm. We further propose a novel parametric bootstrap method to compute confidence intervals, addressing challenges related to temporal dependency and interval-based data relationships. The performance of the model is evaluated through extensive simulations and real data analysis using S&P500 returns during the 2022 Russo-Ukrainian War. The results demonstrate that the proposed OULC model consistently outperforms the traditional OC model, offering more accurate and reliable change-point detection and parameter estimates.

stat.ME↗