Pith. sign in

REVIEW 13 cited by

Distributionally Robust Receive Combining

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.12345 v3 pith:JV5Q5V4N submitted 2024-01-22 eess.SP

classification eess.SP
keywords channelestimationcombiningcovariancediagonaldistributionallyreceiverobust
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This article investigates signal estimation in wireless transmission (i.e., receive combining) from the perspective of statistical machine learning, where the transmit signals may be from an integrated sensing and communication system; that is, 1) signals may be not only discrete constellation points but also arbitrary complex values; 2) signals may be spatially correlated. Particular attention is paid to handling various uncertainties such as the uncertainty of the transmit signal covariance, the uncertainty of the channel matrix, the uncertainty of the channel noise covariance, the existence of channel impulse noises, the non-ideality of the power amplifiers, and the limited sample size of pilots. To proceed, a distributionally robust receive combining framework that is insensitive to the above uncertainties is proposed, which reveals that channel estimation is not a necessary operation. For optimal linear estimation, the proposed framework includes several existing combiners as special cases such as diagonal loading and eigenvalue thresholding. For optimal nonlinear estimation, estimators are limited in reproducing kernel Hilbert spaces and neural network function spaces, and corresponding uncertainty-aware solutions (e.g., kernelized diagonal loading) are derived. In addition, we prove that the ridge and kernel ridge regression methods in machine learning are distributionally robust against diagonal perturbation in feature covariance.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Engineering snags for spatial curvature in weaves: Fabrication, mechanics, and inverse design

    cond-mat.soft 2025-08 conditional novelty 7.0 of 10

    Intentional snags in plain weaves reprogram flat fabrics into curved 3D surfaces, with a calibrated simulation and genetic algorithm for inverse shape design.

  2. Geometrically vertex decomposable star configurations

    math.AC 2026-07 accept novelty 6.5 of 10

    Ideals of star configurations X(ℓ,c) are geometrically vertex decomposable precisely when their defining linear forms admit a triangular coefficient submatrix (for ℓ ≤ n+1), and this is equivalent to being Knutson.

  3. ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction

    cs.AI 2025-08 conditional novelty 6.0 of 10

    Pro2Guard learns a discrete-time Markov chain from LLM agent traces and triggers intervention when the computed probability of reaching an unsafe state exceeds a user-set threshold.

  4. StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization

    cs.CL 2025-05 conditional novelty 6.0 of 10

    StepSearch applies token-level information-gain and redundancy-penalty rewards inside PPO to improve multi-hop search QA, outperforming global-reward RL baselines on four benchmarks.

  5. Assessing the Generalization of Graph Neural Networks for Fault Location Across Increasing Distributed Energy Resource Penetration Levels

    cs.LG 2026-07 conditional novelty 5.0 of 10

    On a simulated 123-bus feeder, a spatio-temporal graph attention network beats GRU and GATv2 baselines for fault location and shows asymmetric generalization across DER penetration levels, keeping 81-84% F1 under a 10...

  6. Physics Enhanced Deep Surrogates for the Phonon Boltzmann Transport Equation

    physics.comp-ph 2025-11 conditional novelty 5.0 of 10

    Embedding a differentiable Fourier solver as a low-fidelity physics core lets a neural surrogate predict phonon-BTE conductivity of porous nanostructures to ~5% error with 300 BTE simulations and design targets at ~4%...

  7. Bad Foundations and Manipulable Objects

    math.HO 2026-02 conditional novelty 4.0 of 10

    A calculus teacher proposes using Maxima to make algebra and calculus expressions into visual, manipulable objects with blanks, to help students with weak procedural foundations.

  8. AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models

    cs.RO 2025-09 conditional novelty 4.0 of 10

    AutoODD combines an LLM agent with per-axis Gaussian Process uncertainty to automatically discover failure modes of black-box models, demonstrated on missing-digit MNIST and aircraft detect-and-avoid.

  9. Embodied Hazard Mitigation using Vision-Language Models for Autonomous Mobile Robots

    cs.RO 2025-09 conditional novelty 4.0 of 10

    A VLM+LLM pipeline on an AMR classifies anomalies as Hazardous or Conflict and triggers mitigation actions, reporting 91.2% accuracy and a 6-second average latency in small indoor trials.

  10. An evaluation of LLMs for generating movie reviews: GPT-4o, Gemini-2.0 and DeepSeek-V3

    cs.CL 2025-05 conditional novelty 4.0 of 10

    LLMs can produce fluent movie reviews that readers often mistake for human-written ones, but the models differ in emotional balance and depth.

  11. Structuring the Unstructured: A Multi-Agent System for Extracting and Querying Financial KPIs and Guidance

    cs.AI 2025-05 conditional novelty 4.0 of 10

    A multi-agent LLM system with hand-crafted rule validation reports about 95% extraction accuracy and 91% correct query answers, but only on a private, unreleased dataset.

  12. Robust Taxi Fare Prediction Under Noisy Conditions: A Comparative Study of GAT, TimesNet, and XGBoost

    cs.LG 2025-07 reject novelty 3.0 of 10

    On 55 million NYC taxi trips, XGBoost outperforms GAT and TimesNet on clean and noisy fare prediction, but the comparison is weakened by missing error bars and contradictory claims.

  13. Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation

    cs.CL 2025-05 unverdicted novelty 2.0 of 10

    A survey of small language models that organizes known methods into taxonomies but adds no new models, data, or validated benchmarks.

Pith tools