Efficient deep learning for wireless source identification using test SNR estimates.
problem Training deep classifiers for wireless signal modulation and technology identification.
method Greedy training SNR Boosting and bootstrap aggregating (Bagging) based on training SNR values.
result Uniform improvement in accuracy across all SNR values with small subsets of training SNR values.
Improving scalability and stability of Stein discrepancies for scalable goodness-of-fit testing
problem Improving scalability and stability of Stein discrepancies for scalable goodness-of-fit testing
method Reformulating Stein discrepancy construction as an explicit SNR^2 maximisation problem
result Avoiding exponential SNR^2 collapse and achieving stable SNR^2
This paper improves CS algorithms for high SNR consistency.
problem High SNR consistency of CS algorithms in underdetermined models.
method Derives conditions for high SNR consistency of CS algorithms.
result Develops novel tuning parameters for high SNR consistency.
New algorithm improves community detection in partially labeled SBM models.
problem Community detection in partially labeled stochastic block models.
method Developed a fast linearized message-passing algorithm.
result Exponential improvement in error rate for strong recovery.
Improved signal processing for long-distance optical signals.
problem Compensating walk-off effect in long-distance optical signals.
method Sub-banded DSP architecture with deep learning for walk-off compensation.
result 2.8 dB SNR improvement over linear equalization.
Improves diffusion models by controlling total variance and signal-to-noise-ratio.
problem Long sampling time in diffusion models.
method Total-Variance/Signal-to-Noise-Ratio (TV/SNR) disentangled framework.
result Improves generation performance by controlling TV and SNR independently.
Improved predictive posterior density estimation through optimized importance sampling.
problem Low signal-to-noise ratio in posterior predictive densities.
method Optimized importance sampling using a test-time variational proxy.
result Significantly improved estimates of predictive posterior densities.
New loss function improves accuracy of MRI parameter estimation.
problem Systematic errors in parameter estimates at low SNR.
method Developed and implemented negative log Rician likelihood (NLR) loss.
result NLR loss shows higher accuracy in parameter estimation than MSE loss at low SNR.
New method improves cryo-EM image classification and averaging.
problem Low SNR in cryo-EM images.
method Introduces Mahalanobis distance for image comparison.
result Improved state-of-the-art classification performance.
DGPs with variational inference suffer from SNR issues that degrade gradient estimates, leading to unreliable training.
problem SNR issues in gradient estimates for DGPs with variational inference.
method Adapted doubly reparameterized gradient estimators for DGP training.
result Fix improves predictive performance of DGP models.
Two methods use DNN-HMM for global SNR estimation of speech signals.
problem Estimating global SNR of speech signals in various noise conditions.
method Dropout approximation for uncertainty estimation and noise-specific regressors.
result Improved SNR estimation accuracy compared to existing methods.
EM algorithm achieves optimal sample complexity for learning two-component mixed linear regression.
problem Learning two-component mixed linear regression under varying signal-to-noise ratios.
method Analysis of EM algorithm convergence rates under different SNR regimes.
result EM algorithm achieves minimax optimal sample complexity in all SNR regimes.
Random forest performance depends on SNR and covariate characteristics.
problem Understanding when random forests perform well.
method Systematic analysis of out-of-sample MSE for different SNR scenarios.
result Randomization effectiveness depends on SNR and covariate characteristics.
Optimizing over-the-air convex optimization, analog schemes are nearly optimal at low SNR.
problem Optimizing over-the-air convex optimization with coded gradients.
method Analyzes coded gradients over an additive Gaussian noise channel, considers analog coding schemes.
result Analog coding schemes nearly match the optimal convergence rate at low SNR, but a slowdown is inevitable.
The paper connects DNN generalization to node SNR using information theory.
problem Exploring the reasons behind DNN generalization performance.
method Using information theory, the paper derives SNR expressions for DNN nodes and uses them to quantify weight optimization.
result Good SNR performance in DNN nodes correlates with good generalization.
DeepSource uses deep learning to detect sources in radio interferometry images.
problem Challenging point source detection at low signal-to-noise in radio interferometry images.
method Convolutional neural networks to enhance SNR, dynamic blob detection.
result DeepSource achieves essentially perfect purity and completeness down to SNR = 4, outperforming PyBDSF.
Tyler's M-estimator's phase transition at DS-SNR = 1 is resolved.
problem Robust Subspace Recovery
method Tyler's M-estimator
result TME converges exactly to the true subspace for DS-SNR >= 1 under a new stability condition.
Improved WBP decoding with simple scaling and SNR adaptation.
problem Efficiently decoding weighted Tanner graphs with reduced complexity.
method Simple-scaling models with machine learning for edge weights, and parameter adapter networks.
result Simple scaling with few parameters can achieve near-maximum-likelihood performance.
Super-resolution improves MRI resolution and accuracy for biomarker assessment.
problem Inadequate SNR for accurate quantification in high-resolution MRI.
method Utilized deep learning super-resolution to maintain SNR for T2 relaxation time biomarkers while generating high-resolution images.
result Super-resolution successfully maintains high-resolution and accurate biomarkers for MRI.
Human cochlear models improve DNN noise suppression systems.
problem DNN-based noise suppression systems lack robustness to unseen noise conditions.
method Coupled cochlear models with DNNs to improve noise suppression.
result Cochlear models enhance DNN generalizability to various noise conditions.
Spectrum selectively trains LLMs based on SNR to save resources.
problem Efficiently training large language models with limited resources.
method Targeting layer modules based on SNR for selective training.
result Spectrum achieves similar performance to full fine-tuning but with reduced VRAM usage.
Random forests reduce bias and variance, especially in low SNR settings.
problem Reducing bias and variance in machine learning models, particularly in low SNR scenarios.
method Empirical study of random forests and bagging ensembles, focusing on the importance of m t r y mtry m t r y tuning. result Random forests reduce both bias and variance, outperforming bagging ensembles in high SNR settings.
Paper improves variance control in importance weighted variational bounds.
problem Improving the variance of gradient estimators for IWAE.
method Develops a novel control variate that grows SNR as √K for large K.
result Empirically, the method yields superior variance reduction for generative models.
Improved F0 estimation in noisy speech with neural networks.
problem Difficult F0 estimation at low SNRs in unexpected noise.
method Waveform-to-sinusoid regression using RNN trained on supervised data.
result Significant improvement in FPE and GPE rates compared to existing methods.
KLT picker automates particle picking for cryo-EM, especially for low SNR images.
problem Challenges in particle picking, especially for low SNR micrographs.
method Data-driven optimal templates learned via Karhunen Loeve Transform.
result High-quality results with minimal manual effort on publicly available data sets.
Deep learning improves automatic modulation classification from subsampled data.
problem Automatic recognition of wireless communication signal modulations from imperfect data.
method Developed and tested Convolutional Long Short-term Deep Neural Network (CLDNN), LSTM, and ResNet architectures.
result Achieved high classification accuracy (around 90%) at high SNR with minimal training data.
Paper proposes MTL for weakly labelled SED, improving performance with 2-step attention.
problem Weakly labelled sound event detection.
method Multi-Task Learning framework with 2-step Attention Pooling.
result Improved SED performance with 22.3%, 12.8%, 5.9% gains at 0, 10, 20 dB SNR.
This paper analyzes AJIVE for estimating shared subspace across multiple datasets, revealing its strengths and limitations.
problem Estimating shared subspace across multiple datasets with varying degrees of misalignment.
method Angle-based Joint and Individual Variation Explained (AJIVE) method, a two-stage spectral approach.
result AJIVE's performance in high signal-to-noise ratio (SNR) regimes and its non-diminishing error in low-SNR settings.
Novel approach to estimate P300 BCI efficiency using SNR.
problem Improving the accuracy of P300 BCI for severely disabled people.
method Introduced a novel approach considering P300 SNR for estimating efficiency, using a Gaussian noise model.
result P300 SNR significantly correlates with spelling accuracy, improving BCI efficiency.
The performance of a modulation classifier is highly sensitive to channel signal-to-noise ratio (SNR). In this paper, we focus on amplitude-phase modulations and propose a modulation classification framework based on centralized data fusion using multiple radios and the hybrid maximum likelihood (ML) approach. In order…
SVO improves particle diversity and variational bounds in filtering SMC.
problem Improving variational bounds in particle filtering with limited samples.
method Introduces Particle Smoothing Variational Objectives (SVO) for smoothed approximate posterior through subsampling.
result SVO outperforms filtered objectives with fewer Monte Carlo samples on nonlinear systems.
The interplay between computational efficiency and statistical accuracy in high-dimensional inference has drawn increasing attention in the literature. In this paper, we study computational and statistical boundaries for submatrix localization. Given one observation of (one or multiple non-overlapping) signal submatrix…
The problem of Poisson denoising appears in various imaging applications, such as low-light photography, medical imaging and microscopy. In cases of high SNR, several transformations exist so as to convert the Poisson noise into an additive i.i.d. Gaussian noise, for which many effective algorithms are available. Howev…
New techniques for compressive sensing without noise or signal statistics.
problem Support recovery in underdetermined linear regression models without prior noise and signal statistics.
method Proposes RRM and RRTA to operate OMP algorithm without noise variance or signal sparsity knowledge.
result Establishes high SNR consistency for OMP without prior noise and signal statistics.
Paper develops limits for tensor SVD in statistical and computational terms.
problem Extracting hidden low-rank structure from high-dimensional tensor data.
method Proposes a general framework for tensor SVD and analyzes its statistical and computational limits.
result Tensor SVD exhibits three phases based on signal-to-noise ratio (SNR), each with distinct estimation capabilities.
Efficiently clusters noisy signals using structured sparsity and wavelet transforms.
problem Clustering signals with low Signal-to-Noise Ratio (SNR).
method Sparse K-means algorithm with structured sparsity, wavelet multi-scale property, and scattering transform.
result Improved clustering results on real datasets.
Paper improves REINFORCE for VI without restrictive assumptions.
problem Improves REINFORCE for VI without restrictive assumptions.
method Introduces VIMCO- ⋆ \star ⋆ gradient estimator to overcome SNR collapse. result VIMCO- ⋆ \star ⋆ achieves N \sqrt{N} N SNR scaling, superior to existing VIMCO. Deep neural networks improve modulation recognition accuracy.
problem Improving modulation recognition accuracy in wireless signals.
method Developed and tested deep neural network architectures, including CNN, ResNet, DenseNet, and CLDNN.
result Achieved high accuracy (up to 88.5%) in recognizing wireless signal modulations.
Deep learning improves one-bit OFDM receiver performance.
problem One-bit quantization complicates accurate channel estimation and data detection in OFDM receivers.
method Developed deep neural networks for channel estimation and data detection, using a two-step training policy.
result Deep learning-based designs achieve lower BER than unquantized OFDM at moderate SNRs.
Recurrent CNNs improve image classification in low light conditions.
problem Poor performance of CNNs in noisy images.
method Added recurrent connections to CNN layers to enhance robustness.
result gruCNNs outperform cCNNs in low signal-to-noise ratio images.
Study recovers spike order in noisy tensor estimation without SNR assumptions.
problem Estimating multiple signal vectors from noisy tensor observations.
method Gradient flow optimization of a nonconvex function.
result Determines sample complexity for efficient permutation recovery.
Deep JSCC maps images directly to channel symbols for wireless transmission.
problem Efficient image transmission in noisy wireless channels.
method Joint source and channel coding using CNNs trained jointly.
result Deep JSCC outperforms traditional JPEG/2000 + channel codes at low SNR.
New scheme optimizes BMI through probabilistic and geometric shaping.
problem Optimizing bit-wise mutual information (BMI) for coded modulation.
method Joint optimization of BMI through probabilistic and geometric shaping.
result Joint optimization enables a continuum of constellation geometries and probability distributions.
Paper proposes an edge detection method for robot navigation using low-SNR thermal cameras.
problem Efficient edge detection for robot navigation using low-SNR thermal camera.
method Raw image denoising, Canny edge detection, CSS method, edge ranking, edge linking.
result Enhanced edge detection method effectively detects smooth edges of the surrounding environment.
New method preserves privacy while improving machine learning accuracy.
problem Privacy-preserving machine learning for daily data.
method Compressive Privacy and multi-kernel method.
result Improved utility classification accuracy with privacy preservation.
Subset selection struggles in high noise; new method improves performance.
problem Subset selection's poor performance in high noise levels.
method Regularized version of least-squares criterion.
result Proposed estimators outperform best subset selection in high noise.
New method clusters tensors with heteroskedastic noise.
problem Clustering tensors with varying noise levels.
method Two-stage method: subspace estimation followed by approximate k k k -means. result Proves exact clustering for SNR above computational limit.
Deep learning identifies wireless interference sources efficiently.
problem Interference source identification in 2.4 GHz ISM Band.
method Deep learning algorithms trained on 10 MHz band samples.
result CNN architecture reduces training time by 60% with minimal accuracy loss.