Minimax Quantile Lower Bounds for Interactive Statistical Decision Making with Privacy

Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a $δ$-explicit minimax-quantile theory for interactive statistical decision making (ISDM). We first provide structural relations between minimax quantiles, lower minimax quantiles, and minimax risk. This includes a quantile-to-expectation conversion and an equivalence between strict and lower minimax quantiles outside a countable set of confidence levels. We then derive two converse tools for ISDM: a high-probability interactive Fano's method and a high-probability interactive Le Cam's method. Then, we show that mutual-information (MI) privacy can be handled in the same framework by restricting the admissible decision class. For coordinatewise Gaussian privatization, we derive a two-point template that isolates the privacy-induced variance inflation. We instantiate this template for Gaussian mean estimation, and use the same two-point strategy directly for two-armed Gaussian bandits. We then derive a minimax quantile lower bound for the $K$-armed Gaussian bandit problem, showing that the interactive Fano method captures the exploration cost over multiple possible best arms. The resulting lower bounds are explicit in the confidence level $δ$ and in the privacy budget for the private problems. They yield $\log(1/δ)/n$ scaling for squared-error Gaussian mean estimation, $\sqrt{T\log(1/δ)}$ scaling for two-armed bounded-mean Gaussian bandits, and $\sqrt{KT\log(1/δ)}$-type scaling for the $K$-armed bandits, with privacy appearing through a Gaussian variance-inflation factor for the private problems.

A Hierarchical Sampling Framework for bounding the Generalization Error of Federated Learning

We study expected generalization bounds for the Hierarchical Federated Learning (HFL) setup using Wasserstein distance. We introduce a generalized framework in which data is sampled hierarchically, and we model it with a multi-layered tree structure that induces dependencies among the clients' datasets. We derive generalization bounds in terms of Wasserstein distance under the Lipschitz assumption on the loss function, by applying a supersample construction that allows us to measure the sensitivity of the algorithm to the change of a single node in the sampling tree. By leveraging the FL structure, we recover and strictly imply existing state-of-the-art conditional mutual information (CMI) bounds in the case of bounded losses. We also show that our bound can be applied together with Differential Privacy assumptions, to recover generalization bounds based on algorithmic privacy. To assess the tightness of our bounds, we study the Gaussian Location Model (GLM) and show that we recover the actual asymptotic rate of the generalization error.

DriftDecode: One-Step Wireless Image Decoding via Drifting-Inspired Detail Recovery

Generative receivers for wireless image transmission can improve reconstruction quality, but diffusion-based and flow-based decoding relies on iterative inference and therefore incurs substantial latency. In wireless image transmission, however, the received signal already preserves the coarse structure of the source image. Wireless decoding is therefore better viewed as a recovery task than as image generation from scratch, and the main challenge lies in restoring channel-impaired details. Motivated by this recovery-oriented perspective, this paper proposes DriftDecode, a signal-to-noise ratio (SNR)-conditioned one-step decoder for wireless image reconstruction. DriftDecode couples a one-step U-Net decoder with a drift-inspired instance-level texture loss. The loss reformulates the drifting-field mechanism from generative drifting models in perceptual feature space, guiding each reconstructed local feature toward its spatially aligned ground-truth counterpart while suppressing mismatched textures. Experiments on DIV2K and MNIST under additive white Gaussian noise (AWGN) and Rayleigh fading channels show a favorable quality-latency tradeoff. DriftDecode achieves 30~ms decoding latency, providing a 4.8$\times$ speedup over a 10-step flow-matching decoder, while consistently outperforming MSE-only training and yielding up to 1.13~dB PSNR gain on MNIST under Rayleigh fading. These results support recovery-oriented one-step decoding as an effective alternative to iterative generative decoding for low-latency wireless image transmission.

Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems

Recent work established a generalized-Fano framework for lower bounding prior-predictive (Bayesian) CVaR in interactive statistical decision making. In this paper, we show how to instantiate that framework in concrete interactive problems and derive explicit Bayesian CVaR lower bounds from its abstract corollaries. Our approach compares a hard model with a reference model using squared Hellinger distance, and combines a lower bound on a reference hinge term with a bound on the distinguishability of the two models. We apply this approach to canonical examples, including Gaussian bandits, and obtain explicit bounds that make the dependence on key problem parameters transparent. These results show how the generalized-Fano Bayesian CVaR framework can be used as a practical lower-bound tool for interactive learning and risk-sensitive decision making.

Cramér-Rao Bound Analysis of Bistatic ISAC Under Partial Symbol Knowledge and Clutter

Integrated sensing and communication (ISAC) systems rely on communication waveforms to perform sensing tasks, thus making their sensing performance strongly dependent on the level of communication symbol knowledge available to the sensing receivers. However, the existing literature fails to capture this dependency, often relying on full symbol knowledge assumptions. In this paper, we present a Cramer Rao bound (CRB) analysis of a bistatic ISAC network with heterogeneous uplink and downlink illumination and structured clutter. We consider different symbol knowledge regimes by modeling unknown communication symbols as nuisance parameters. Assuming a temporal evolution of the communication channel, we derive a correlation aware channel estimator and an expression for the UEs uplink spectral efficiency (SE). Numerical results show the CRB degradation induced by clutter and symbol uncertainty and how this can affect resource allocation policies. We also show the performance gain of our channel estimator relative to conventional block fading architectures.

Living Off the Grid: Continuous Range-Angle Super-Resolution for Near-Field XL-MIMO

Near-field extremely large multiple input multiple output (XL-MIMO) breaks the assumptions that make classical super-resolution effective: the receiver acquires only a limited set of compressed pilot observations, while each propagation path is jointly determined by angle and distance under a spherical-wave model. This invalidates the far-field Vandermonde structure exploited by conventional methods, and many existing near-field formulations remain only gridless by discretizing range and angle and thus inheriting mismatch, coherence, and resolution loss. This paper develops a continuous 2D super-resolution framework for hybrid near-field measurements that avoids range and angle gridding. The key idea is to reparameterize distance through inverse range, which reveals a compact spectral structure for the near-field spherical-wave manifold. Building on this observation, we introduce a panelized weighted fitting strategy that converts the range-dependent Fresnel terms into a stable transform-domain representation, resulting in a lifted mode, in which each continuous range-angle pair is embedded as a structured rank-one atom and the measurement model remains linear under hybrid combining. Recovery is then posed as a 2D atomic norm minimization, with path localization certified through a dual polynomial over the transformed domain. Numerical experiments show exact support recovery in the noiseless setting using only few compressed hybrid measurements. These results establish the proposed inverse-range atomic norm viewpoint as a new gridless foundation for near-field sensing and channel estimation in hybrid XL-MIMO and integrated sensing and communication systems.

Convexity Meets Curvature: Lifted Near-Field Super-Resolution

Extra-large apertures, high carrier frequencies, and integrated sensing and communications (ISAC) are pushing array processing into the Fresnel region, where spherical wavefronts induce a range-dependent phase across the aperture. This curvature breaks the Fourier/Vandermonde structure behind classical subspace methods, and it is especially limiting with hybrid front-ends that provide only a small number of pilot measurements. Consequently, practical systems need continuous angle resolution and joint angle-range inference where many near-field approaches still rely on costly 2D gridding. We show that convexity can meet curvature via a lifted, gridless superresolution framework for near-field measurements. The key is a Bessel-Vandermonde factorization of the Fresnel-phase manifold that exposes a hidden Vandermonde structure in angle while isolating the range dependence into a compact coefficient map. Building on this, we introduce a lifting that maps each range bin and continuous angle to a structured rank-one atom, converting the nonlinear near-field model into a linear inverse problem over a row-sparse matrix. Recovery is posed as atomic-norm minimization and an explicit dual characterization via bounded trigonometric polynomials yields certificate-based localization that super-resolves off-grid angles and identifies active range bins. Simulations with strongly undersampled hybrid observations validate reliable joint angle-range recovery for next-generation wireless and ISAC systems.

Quantization-Aware Collaborative Inference for Large Embodied AI Models

Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications. However, the massive parameter scale and computational demands of LAIMs pose significant challenges for resource-limited embodied agents. To address this issue, we investigate quantization-aware collaborative inference (co-inference) for embodied AI systems. First, we develop a tractable approximation for quantization-induced inference distortion. Based on this approximation, we derive lower and upper bounds on the quantization rate-inference distortion function, characterizing its dependence on LAIM statistics, including the quantization bit-width. Next, we formulate a joint quantization bit-width and computation frequency design problem under delay and energy constraints, aiming to minimize the distortion upper bound while ensuring tightness through the corresponding lower bound. Extensive evaluations validate the proposed distortion approximation, the derived rate-distortion bounds, and the effectiveness of the proposed joint design. Particularly, simulations and real-world testbed experiments demonstrate the effectiveness of the proposed joint design in balancing inference quality, latency, and energy consumption in edge embodied AI systems.

Coding-Enforced Resilient and Secure Aggregation for Hierarchical Federated Learning

Hierarchical federated learning (HFL) has emerged as an effective paradigm to enhance link quality between clients and the server. However, ensuring model accuracy while preserving privacy under unreliable communication remains a key challenge in HFL, as the coordination among privacy noise can be randomly disrupted. To address this limitation, we propose a robust hierarchical secure aggregation scheme, termed H-SecCoGC, which integrates coding strategies to enforce structured aggregation. The proposed scheme not only ensures accurate global model construction under varying levels of privacy, but also avoids the partial participation issue, thereby significantly improving robustness, privacy preservation, and learning efficiency. Both theoretical analyses and experimental results demonstrate the superiority of our scheme under unreliable communication across arbitrarily strong privacy guarantees

Land-then-transport: A Flow Matching-Based Generative Decoder for Wireless Image Transmission

Due to strict rate and reliability demands, wireless image transmission remains difficult for both classical layered designs and joint source-channel coding (JSCC), especially under low latency. Diffusion-based generative decoders can deliver strong perceptual quality by leveraging learned image priors, but iterative stochastic denoising leads to high decoding delay. To enable low-latency decoding, we propose a flow-matching (FM) generative decoder under a new land-then-transport (LTT) paradigm that tightly integrates the physical wireless channel into a continuous-time probability flow. For AWGN channels, we build a Gaussian smoothing path whose noise schedule indexes effective noise levels, and derive a closed-form teacher velocity field along this path. A neural-network student vector field is trained by conditional flow matching, yielding a deterministic, channel-aware ODE decoder with complexity linear in the number of ODE steps. At inference, it only needs an estimate of the effective noise variance to set the ODE starting time. We further show that Rayleigh fading and MIMO channels can be mapped, via linear MMSE equalization and singular-value-domain processing, to AWGN-equivalent channels with calibrated starting times. Therefore, the same probability path and trained velocity field can be reused for Rayleigh and MIMO without retraining. Experiments on MNIST, Fashion-MNIST, and DIV2K over AWGN, Rayleigh, and MIMO demonstrate consistent gains over JPEG2000+LDPC, DeepJSCC, and diffusion-based baselines, while achieving good perceptual quality with only a few ODE steps. Overall, LTT provides a deterministic, physically interpretable, and computation-efficient framework for generative wireless image decoding across diverse channels.