arXiv subjects

Jingbo Liu

Publications and source records attributed to Jingbo Liu.

At least 19 recordsLinked to original sources

arXiv2026

A Bayesian Proof of the Bernoulli Theorem

We give a new proof of the Bernoulli theorem, conjectured by Talagrand and proved in the seminal work of Bednorz and Lata{\l}a. Our approach is based on information-theoretic ideas: lower bounds on the supremum of a Bernoulli process are translated to the fundamental limits of Bayesian estimation in a Cauchy additive channel. This leads to a new information-theoretic functional that characterizes Bernoulli-process suprema and plays a role analogous to Fernique's majorizing-measure functional for Gaussian processes. The same viewpoint yields a distributional strengthening: for any prescribed law of the index, we characterize the largest expected value attainable over all couplings of that index with the Bernoulli process. This extends to Bernoulli processes a phenomenon previously understood for Gaussian processes through the work of Fernique and Talagrand.

math.PR↗

arXiv2026

Accelerating Conformal Prediction via Approximate Leave-One-Out

While conformal prediction provides a general framework for uncertainty quantification in predictive inference, its application is often limited by computational cost. Recent methods, including Jackknife+ and Jackknife-minmax, achieve faster computation by trading a slight loss of efficiency relative to full conformal prediction, but still requires computing leave-one-out refits for all observations. In this paper, we further accelerate conformal prediction by incorporating approximate leave-one-out (ALO) estimators, and establish asymptotic coverage and efficiency. While our proof draws on methods developed for analyzing the consistency of ALO cross-validation risk estimators in high-dimensional statistics, it requires adaptations to handle conformal prediction, where leave-$i$-out residuals are needed for predictions at $x_{n+1}$ rather than just at the training covariate $x_i$. Simulation results validate our theoretical findings, showing that the ALO-based methods achieve coverage and efficiency comparable to the exact methods, while significantly reducing the runtime.

stat.ML↗

arXiv2026

Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization

Indoor visual relocalization plays a critical role in emerging spatial and embodied AI applications. However, prior research was predominantly devoted to low-level vision schemes, struggling to perceive scene semantics and compositions, which limits both interpretability and applicability. In this paper, we explore the issue of how to organize rich object information in a scene, including semantics, layout, and geometry, into a structured map representation, thereby utilizing object units exclusively to drive the camera relocalization task. To this end, we propose OpenReLoc, a camera relocalization system designed to provide scene understanding and accurate pose estimation capabilities. Leveraging recent foundation models, we first introduce a multi-modal mechanism to integrate open-vocabulary semantic knowledge for effective 2D-3D object matching. Additionally, we design object-oriented reference frames as position priors, paired with a reference frame selection strategy based on the Distance-IoU (DIOU), enabling extension to scalable scenes. Moreover, to ensure stable and accurate pose optimization, we also propose a dual-path 2D Iterative Closest Pixel loss guided by object shape. Experimental results demonstrate that OpenReLoc achieves superior relocalization recall and accuracy across various datasets. Our source code will be released upon acceptance.

cs.CV↗

arXiv2026

Smoothed Score Queries and the Complexity of Sampling

We study the query complexity of sampling from high-dimensional Gaussian distributions using gradient information. In the standard oracle model, exact gradients expose only matrix-vector products with the precision matrix, leading to polynomial approximation barriers and a characteristic $\sqrt{\kappa}$ dependence on the condition number. We show that this barrier disappears when the sampler is allowed to query \emph{smoothed scores}, namely gradients of the logarithms of the Gaussian-convolved densities. For a Gaussian target with precision matrix $\Lambda$, a smoothed-score query at noise level $\tau$ gives access to the resolvent $(\Lambda+\tau^{-1}I)^{-1}$. Combining geometrically spaced noise levels with sinc-quadrature rational approximation, we obtain a sampler with $q=O\!\left(\bigl(\log\kappa+\log(e\sqrt d/\delta_{\rm TV})\bigr)\log(e\sqrt d/\delta_{\rm TV})\right)$ smoothed-score queries for total variation error $\delta_{\rm TV}$, improving the condition-number dependence from $\sqrt{\kappa}$ to logarithmic. We also study finite-bit gradient oracles. Using coordinatewise quantization of the transformed smoothed-score answers and a final dithering step, we obtain a sampling scheme whose total communicated gradient information is polylogarithmic in $\kappa$; in particular, for fixed dimension and accuracy, the bit complexity is $O(\log^2\kappa)$. To complement these upper bounds, we introduce a channel-synthesis, or reverse-Shannon, converse technique for sampling lower bounds. This converts total-variation simulation guarantees into communication requirements and yields an $\Omega(\log\kappa)$ lower bound on the required gradient information. Together, these results identify smoothed scores as a provably more informative oracle for sampling and give nearly matching upper and lower bounds for its finite-bit complexity.

cs.DS↗

arXiv2026

Two-Sided Bounds for Entropic Optimal Transport via a Rate-Distortion Integral

We show that the maximum expected inner product between a random vector and the standard normal vector over all couplings subject to a mutual information constraint or regularization is equivalent to a truncated integral involving the rate-distortion function, up to universal multiplicative constants. The proof is based on a lifting technique, which constructs a Gaussian process indexed by a random subset of the type class of the probability distribution involved in the information-theoretic inequality, and then applying a form of the majorizing measure theorem.

cs.IT↗

arXiv2025

Fast and Efficient Parallel Sampling Using Higher Order Langevin Dynamics

We study parallel sampling from high-dimensional strongly log-concave distributions. Langevin-based samplers converge rapidly in continuous time, but their discretizations are typically sequential and often require polynomially many steps in the dimension $d$, the target accuracy $\varepsilon^{-1}$, or both. Picard-based parallel sampling methods reduce this sequential depth to polylogarithmic scale by solving for many time-discretization points in parallel; however, existing guarantees often require a polynomial number of processors, leading to substantial memory and gradient-evaluation costs in high dimensions. We show that higher-order Langevin structure can reduce this parallel resource burden while preserving polylogarithmic sequential depth. Our method combines arbitrary-order Langevin dynamics with blockwise Lagrange polynomial interpolation. This sharper discretization reduces the number of parallel points required to achieve a target accuracy. Our results cover both higher-order smooth potentials and ridge-separable potentials, including models such as Bayesian logistic regression and two-layer neural networks, and improve upon the space complexity of the current literature on parallel log-concave sampling.

math.ST↗

arXiv2025

A Black-Box Debiasing Framework for Conditional Sampling

Conditional sampling is a fundamental task in Bayesian statistics and generative modeling. Consider the problem of sampling from the posterior distribution $P_{X|Y=y^*}$ for some observation $y^*$, where the likelihood $P_{Y|X}$ is known, and we are given $n$ i.i.d. samples $D=\{X_i\}_{i=1}^n$ drawn from an unknown prior distribution $\pi_X$. Suppose that $f(\hat{\pi}_{X^n})$ is the distribution of a posterior sample generated by an algorithm (e.g. a conditional generative model or the Bayes rule) when $\hat{\pi}_{X^n}$ is the empirical distribution of the training data. Although averaging over the randomness of the training data $D$, we have $\mathbb{E}_D\left(\hat{\pi}_{X^n}\right)= \pi_X$, we do not have $\mathbb{E}_D\left\{f(\hat{\pi}_{X^n})\right\}= f(\pi_X)$ due to the nonlinearity of $f$, leading to a bias. In this paper we propose a black-box debiasing scheme that improves the accuracy of such a naive plug-in approach. For any integer $k$ and under boundedness of the likelihood and smoothness of $f$, we generate samples $\hat{X}^{(1)},\dots,\hat{X}^{(k)}$ and weights $w_1,\dots,w_k$ such that $\sum_{i=1}^kw_iP_{\hat{X}^{(i)}}$ is a $k$-th order approximation of $f(\pi_X)$, where the generation process treats $f$ as a black-box. Our generation process achieves higher accuracy when averaged over the randomness of the training data, without degrading the variance, which can be interpreted as improving memorization without compromising generalization in generative models.

stat.ME↗

arXiv2025

Simple and Sharp Generalization Bounds via Lifting

We develop an information-theoretic framework for bounding the supremum of stochastic processes, offering a simpler and sharper alternative to classical chaining and slicing arguments for generalization bounds. The key idea is a lifting argument that produces information-theoretic analogues of empirical process bounds, such as Dudley's entropy integral. Lifting introduces permutation symmetry, yielding sharp bounds when the classical Dudley integral is loose. This gives a simple proof of the majorizing measure theorem via the sharpness of Dudley's entropy integral for stationary processes, a result known well before the proof of the majorizing measure theorem. Furthermore, the information-theoretic formulation provides soft versions of classical localized complexity bounds in generalization theory, but is simpler and does not require the slicing argument. We apply this approach to empirical risk minimization over Sobolev ellipsoids, obtaining sharp convergence rates in settings where previous methods are suboptimal.

math.ST↗

arXiv2025

Proof of The TAP Free Energy for High-Dimensional Linear Regression with Spherical Priors at All Temperatures

Approximate inference is central to Bayesian learning, with variational inference (VI) providing a scalable framework for posterior approximation. While mean-field VI often fails in high dimensions, the more refined Bethe approximation, equivalent to the Thouless-Anderson-Palmer (TAP) free energy in statistical physics, has long been conjectured to capture Bayes-optimal behavior. We prove that the TAP formula holds for Bayesian linear regression with a uniform spherical prior at all noise levels ($\Delta>0$), extending the result of Qiu and Sen (2023) in the high-noise regime. Our argument constructs a ridge regression functional that dominates the TAP free energy, yielding the first rigorous analysis of the global optimizer of the non-concave TAP functional for a planted inference model at an arbitrary noise level. This verifies that TAP, rather than mean-field, is the correct variational description in this setting.

math.ST↗

arXiv2025

Feedback-Free Resource Scheduling for Flexible Multi-BS Cooperation in FD-RAN

Flexible cooperation among base stations (BSs) is critical to improve resource utilization efficiency and meet personalized user demands. However, its practical implementation is hindered by the current radio access network (RAN), which relies on the coupling of uplink and downlink transmissions and channel state information feedback with inherent issues such as overheads and delays. To overcome these limitations, we consider the fully-decoupled RAN (FD-RAN), in which uplink and downlink functionalities are independent, and feedback-free MIMO transmission is adopted at the physical layer. To further deliver flexible cooperation in FD-RAN, we study feedback-free downlink multi-BS resource scheduling under the practical scheduling process. The problem is considered based on network load conditions. In heavy-load states where it is impossible for all user demands to be met, an optimal greedy algorithm is proposed, maximizing the weighted sum of user demand satisfaction rates. In light-load states where at least one solution exists to satisfy all user demands, an optimal two-stage resource allocation algorithm is designed to further minimize network energy consumption by leveraging the flexibility of cooperation. Extensive simulations validate the superiority of proposed algorithms in performance and running time, and highlight the potential for realizing flexible cooperation in practice.

eess.SP↗

arXiv2024

A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding

In this paper, we propose a novel multi-view stereo (MVS) framework that gets rid of the depth range prior. Unlike recent prior-free MVS methods that work in a pair-wise manner, our method simultaneously considers all the source images. Specifically, we introduce a Multi-view Disparity Attention (MDA) module to aggregate long-range context information within and across multi-view images. Considering the asymmetry of the epipolar disparity flow, the key to our method lies in accurately modeling multi-view geometric constraints. We integrate pose embedding to encapsulate information such as multi-view camera poses, providing implicit geometric constraints for multi-view disparity feature fusion dominated by attention. Additionally, we construct corresponding hidden states for each source image due to significant differences in the observation quality of the same pixel in the reference frame across multiple source frames. We explicitly estimate the quality of the current pixel corresponding to sampled points on the epipolar line of the source image and dynamically update hidden states through the uncertainty estimation module. Extensive results on the DTU dataset and Tanks&Temple benchmark demonstrate the effectiveness of our method. The code is available at our project page: https://zju3dv.github.io/GD-PoseMVS/.

cs.CV↗

arXiv2024

Long or Short or Both? An Exploration on Lookback Time Windows of Behavioral Features in Product Search Ranking

Customer shopping behavioral features are core to product search ranking models in eCommerce. In this paper, we investigate the effect of lookback time windows when aggregating these features at the (query, product) level over history. By studying the pros and cons of using long and short time windows, we propose a novel approach to integrating these historical behavioral features of different time windows. In particular, we address the criticality of using query-level vertical signals in ranking models to effectively aggregate all information from different behavioral features. Anecdotal evidence for the proposed approach is also provided using live product search traffic on Walmart.com.

cs.IR↗

arXiv2024

Towards More Relevant Product Search Ranking Via Large Language Models: An Empirical Study

Training Learning-to-Rank models for e-commerce product search ranking can be challenging due to the lack of a gold standard of ranking relevance. In this paper, we decompose ranking relevance into content-based and engagement-based aspects, and we propose to leverage Large Language Models (LLMs) for both label and feature generation in model training, primarily aiming to improve the model's predictive capability for content-based relevance. Additionally, we introduce different sigmoid transformations on the LLM outputs to polarize relevance scores in labeling, enhancing the model's ability to balance content-based and engagement-based relevances and thus prioritize highly relevant items overall. Comprehensive online tests and offline evaluations are also conducted for the proposed design. Our work sheds light on advanced strategies for integrating LLMs into e-commerce product search ranking model training, offering a pathway to more effective and balanced models with improved ranking relevance.

cs.IR↗

arXiv2024

$L^1$ Estimation: On the Optimality of Linear Estimators

Consider the problem of estimating a random variable $X$ from noisy observations $Y = X+ Z$, where $Z$ is standard normal, under the $L^1$ fidelity criterion. It is well known that the optimal Bayesian estimator in this setting is the conditional median. This work shows that the only prior distribution on $X$ that induces linearity in the conditional median is Gaussian. Along the way, several other results are presented. In particular, it is demonstrated that if the conditional distribution $P_{X|Y=y}$ is symmetric for all $y$, then $X$ must follow a Gaussian distribution. Additionally, we consider other $L^p$ losses and observe the following phenomenon: for $p \in [1,2]$, Gaussian is the only prior distribution that induces a linear optimal Bayesian estimator, and for $p \in (2,\infty)$, infinitely many prior distributions on $X$ can induce linearity. Finally, extensions are provided to encompass noise models leading to conditional distributions from certain exponential families.

math.ST↗

arXiv2024

Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions

We study the asymptotic error of score-based diffusion model sampling in large-sample scenarios from a non-parametric statistics perspective. We show that a kernel-based score estimator achieves an optimal mean square error of $\widetilde{O}\left(n^{-1} t^{-\frac{d+2}{2}}(t^{\frac{d}{2}} \vee 1)\right)$ for the score function of $p_0*\mathcal{N}(0,t\boldsymbol{I}_d)$, where $n$ and $d$ represent the sample size and the dimension, $t$ is bounded above and below by polynomials of $n$, and $p_0$ is an arbitrary sub-Gaussian distribution. As a consequence, this yields an $\widetilde{O}\left(n^{-1/2} t^{-\frac{d}{4}}\right)$ upper bound for the total variation error of the distribution of the sample generated by the diffusion model under a mere sub-Gaussian assumption. If in addition, $p_0$ belongs to the nonparametric family of the $β$-Sobolev space with $β\le 2$, by adopting an early stopping strategy, we obtain that the diffusion model is nearly (up to log factors) minimax optimal. This removes the crucial lower bound assumption on $p_0$ in previous proofs of the minimax optimality of the diffusion model for nonparametric families.

math.ST↗

arXiv2024

Sampling from the Random Linear Model via Stochastic Localization Up to the AMP Threshold

Recently, Approximate Message Passing (AMP) has been integrated with stochastic localization (diffusion model) by providing a computationally efficient estimator of the posterior mean. Existing (rigorous) analysis typically proves the success of sampling for sufficiently small noise, but determining the exact threshold involves several challenges. In this paper, we focus on sampling from the posterior in the linear inverse problem, with an i.i.d. random design matrix, and show that the threshold for sampling coincides with that of posterior mean estimation. We give a proof for the convergence in smoothed KL divergence whenever the noise variance $\Delta$ is below $\Delta_{\rm AMP}$, which is the computation threshold for mean estimation introduced in (Barbier et al., 2020). We also show convergence in the Wasserstein distance under the same threshold assuming a dimension-free bound on the operator norm of the posterior covariance matrix, a condition strongly suggested by recent breakthroughs on operator norm bounds in similar replica symmetric systems. A key observation in our analysis is that phase transition does not occur along the sampling and interpolation paths assuming $\Delta<\Delta_{\rm AMP}$.

math.ST↗

arXiv2024

Leveraging Self-Supervised Learning for MIMO-OFDM Channel Representation and Generation

In communications theory, the capacity of multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM) systems is fundamentally determined by wireless channels, which exhibit both diversity and correlation in spatial, frequency and temporal domains. It is further envisioned to exploit the inherent nature of channels, namely representation, to achieve geolocation-based MIMO transmission for 6G, exemplified by the fully-decoupled radio access network (FD-RAN). Accordingly, this paper first employs self-supervised learning to obtain channel representation from unlabeled channel, then proposes a channel generation assisted approach for determining MIMO precoding matrix solely based on geolocation. Specifically, we exploit the small-scale temporal domain variations of channels at a fixed geolocation, and design an ingenious pretext task tailored for contrastive learning. Then, a Transformer-based encoder is trained to output channel representations. We further develop a conditional diffusion generator to generate channel representations from geolocation. Finally, a Transformer-encoder-based decoder is utilized to reconstruct channels from generated representations, where the optimal channel is selected for calculating the precoding matrix for both single and dual BS transmission. We conduct experiments on a public ray-tracing channel dataset, and the extensive simulation results demonstrate the effectiveness of our channel representation method, and also showcase the performance improvement in geolocation-based MIMO transmission.

cs.IT↗

arXiv2024

Stability of a Generalized Debiased Lasso with Applications to Resampling-Based Variable Selection

We propose a generalized debiased Lasso estimator based on a stability principle. When a single column of the design matrix is perturbed, the estimator admits a simple update formula that can be computed from the original solution. Under sub-Gaussian designs with well-conditioned covariance, this approximation is asymptotically accurate for all but a vanishing fraction of coordinates in the proportional growth regime. The proof relies on concentration and anti-concentration arguments to control error terms and sign changes. In contrast, establishing comparable distributional limits (e.g., Gaussianity) under similar assumptions remains open. As an application, we show that the approximation significantly reduces the computational cost of resampling-based variable selection procedures, including the conditional randomization test and a local knockoff filter.

math.ST↗