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.
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.
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.
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.
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.
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.
Alignment of neural network representations is influenced by SNR and sample size.
problem Understanding how neural network representations align across different conditions.
method Controlled training of neural networks on perturbed datasets, analyzing alignment and generalization.
result Alignment varies monotonically with SNR but non-monotonically with sample size, with minimal alignment near the interpolation threshold.
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.
Attention models can overfit without harming test performance.
problem Understanding benign overfitting in single-head attention models.
method Analyzing conditions for benign overfitting in a single-head softmax attention model.
result A single-head attention model can overfit without harming test performance under certain conditions.
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.
GRRT recovers sparse signals without prior sparsity or noise variance knowledge.
problem Recovering sparse signals without prior sparsity or noise variance knowledge.
method Generalized residual ratio thresholding (GRRT) for SOMP and BOMP.
result Finite sample and finite SNR guarantees for exact support recovery.
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.
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.
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.
EM converges for mixtures of many linear regressions with SNR > Ω(k).
problem Convergence of EM algorithm for mixtures of linear regressions.
method Analysis of EM algorithm convergence for mixtures of linear regressions with arbitrary number of components.
result EM converges to true parameters with SNR > Ω(k), independent of parameter norms.
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.
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.
Researchers discover phase transitions in estimating object ranks from pairwise interactions.
problem Estimating the underlying ranks of objects from pairwise comparisons or collaborations.
method Characterized optimal statistical error rates for various signal-to-noise ratios.
result Phase transitions between optimal error rates of polynomial, exponential, zero, and trivial.
Study on benign overfitting in leaky ReLUs with moderate input dimensions.
problem Understanding when overfitting is beneficial in neural networks.
method Two-layer leaky ReLU networks trained with hinge loss, considering signal-to-noise ratio.
result Characterization of conditions for benign overfitting based on signal-to-noise ratio.
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.
A DL autoencoder tackles interference channels, improving SNR and INR.
problem Improving performance in interference channels with varying interference levels.
method Designing a DL neural network autoencoder for a k-user Gaussian interference channel, classifying interferences as weak to very strong.
result DL autoencoder significantly mitigates interference effects, especially with known α and low offset.
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.
Unbiased methods for alpha-divergence minimization struggle in high dimensions.
problem The difficulty of unbiased alpha-divergence minimization in high dimensions.
method Signal-to-Noise Ratio (SNR) analysis of gradient estimators.
result The SNR of the gradient estimator worsens exponentially with dimensionality.
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.
SGD recovers multiple signal vectors in noisy tensor PCA.
problem Estimating multiple signal vectors from noisy tensor observations.
method Online stochastic gradient descent (SGD) in high dimensions with detailed analysis of correlations.
result Sequential elimination of correlations allows recovery of all spikes from N p − 2 N^{p-2} N p − 2 samples. 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…
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
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.
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.
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…
Study on sensor fusion algorithms under high dimensional noise.
problem Behavior of sensor fusion algorithms under high dimensional noise.
method Analysis of NCCA and AD algorithms using Gaussian kernel.
result Robustness of NCCA and AD to high dimensional noise depends on SNR and bandwidth selection.
A new memory-efficient Adam variant reduces second moments when feasible.
problem Memory constraints in training machine learning models.
method Signal-to-Noise Ratio (SNR) analysis to identify dimensions where second moments can be replaced by means.
result Memory-efficient Adam variant (SlimAdam) matches performance and stability of Adam while saving up to 98% of second moments.
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.
New model predicts links in community-based networks robustly.
problem Link prediction in community-based networks with local clustering errors.
method Markov Stochastic Block Model (MSBM) with Hidden Markov Model (HMM) predictions.
result Misclassification error decays exponentially with relevant signal-to-noise ratio (SNR).
The paper sets sample complexity bounds for learning high-dimensional simplices in noisy data.
problem Learning high-dimensional simplices from noisy data.
method Sample compression techniques and Fourier-based method for noisy observations.
result Established sample complexity bounds for simplex learning in noisy regimes.
Nuclear magnetic resonance (NMR) spectroscopy exploits the magnetic properties of atomic nuclei to discover the structure, reaction state and chemical environment of molecules. We propose a probabilistic generative model and inference procedures for NMR spectroscopy. Specifically, we use a weighted sum of trigonometric…
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.
MPNNs struggle with class-bottlenecks and heterophily, leading to performance limitations.
problem Performance limitations of MPNNs under heterophily and structural bottlenecks.
method A statistical framework decomposing model performance into SNR components and proving bounds on sensitivity.
result Optimal graph structures for maximizing higher-order homophily are disjoint unions of single-class and two-class-bipartite clusters.
Paper finds sample complexity for learning high-dimensional simplices from noisy data.
problem Learning high-dimensional simplices from noisy samples.
method Combines sample compression, high-dimensional geometry, and Fourier analysis.
result Proves sample complexity bound for achieving a simplex within a certain distance from the true simplex.
New Fourier-based diffusion model improves high-frequency generation quality.
problem Diffusion models struggle with high-frequency details.
method Analyzed and modified the forward process in Fourier space to equalize noise corruption across frequencies.
result Improved generation quality for high-frequency components.
This paper improves monaural source enhancement using SDR as an objective function.
problem Maximizing signal-to-distortion ratio (SDR) for better monaural source enhancement.
method Uses signal-to-distortion ratio (SDR) as an objective function to improve monaural source enhancement.
result The proposed method achieved better performance than conventional methods.
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. 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.
New algorithms reduce communication for sparse mean estimation in noisy distributed systems.
problem Sparse normal means estimation with limited communication in a distributed setting.
method Two distributed algorithms for estimating a sparse mean vector with sublinear communication.
result Correct support of the sparse mean can be recovered with significantly less communication than previously required.
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.
This paper derives lower bounds on the worst case MSE of dictionary learning schemes.
problem Learning a dictionary matrix from observed signals with a common underlying dictionary.
method Information-theoretic approach to minimax estimation for DL problem.
result Derives three lower bounds on the worst case MSE of DL schemes.
U-Net trained to recover acoustic interference striations from distorted data.
problem Recovering acoustic interference striations from distorted signals.
method Training a U-Net using a random mode-coupling matrix model to generate training data.
result U-Net successfully recovers AISs under various conditions.
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.