arXiv research

Improves diffusion models by controlling total variance and signal-to-noise-ratio.

Spectrum selectively trains LLMs based on SNR to save resources.

DGPs with variational inference suffer from SNR issues that degrade gradient estimates, leading to unreliable training.

The paper connects DNN generalization to node SNR using information theory.

Improved predictive posterior density estimation through optimized importance sampling.

Alignment of neural network representations is influenced by SNR and sample size.

Optimizing over-the-air convex optimization, analog schemes are nearly optimal at low SNR.

Attention models can overfit without harming test performance.

EM algorithm achieves optimal sample complexity for learning two-component mixed linear regression.

Paper improves variance control in importance weighted variational bounds.

This paper analyzes AJIVE for estimating shared subspace across multiple datasets, revealing its strengths and limitations.

Unbiased methods for alpha-divergence minimization struggle in high dimensions.

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…

A new memory-efficient Adam variant reduces second moments when feasible.

New model predicts links in community-based networks robustly.

High signal to noise ratio (SNR) consistency of model selection criteria in linear regression models has attracted a lot of attention recently. However, most of the existing literature on high SNR consistency deals with model order selection. Further, the limited literature available on the high SNR consistency of subs…

Paper improves REINFORCE for VI without restrictive assumptions.

Recovering the support of sparse vectors in underdetermined linear regression models, \textit{aka}, compressive sensing is important in many signal processing applications. High SNR consistency (HSC), i.e., the ability of a support recovery technique to correctly identify the support with increasing signal to noise rat…

Study on benign overfitting in leaky ReLUs with moderate input dimensions.

Improving scalability and stability of Stein discrepancies for scalable goodness-of-fit testing

We study the community detection and recovery problem in partially-labeled stochastic block models (SBM). We develop a fast linearized message-passing algorithm to reconstruct labels for SBM (with $n$ nodes, $k$ blocks, $p,q$ intra and inter block connectivity) when $δ$ proportion of node labels are revealed. The signa…

In this paper, we propose a general framework for tensor singular value decomposition (tensor SVD), which focuses on the methodology and theory for extracting the hidden low-rank structure from high-dimensional tensor data. Comprehensive results are developed on both the statistical and computational limits for tensor …

Efficient deep learning for wireless source identification using test SNR estimates.

Random forests reduce bias and variance, especially in low SNR settings.

Point source detection at low signal-to-noise is challenging for astronomical surveys, particularly in radio interferometry images where the noise is correlated. Machine learning is a promising solution, allowing the development of algorithms tailored to specific telescope arrays and science cases. We present DeepSourc…

The paper sets sample complexity bounds for learning high-dimensional simplices in noisy data.

Tyler's M-estimator's phase transition at DS-SNR = 1 is resolved.

U-Net trained to recover acoustic interference striations from distorted data.

SGD recovers multiple signal vectors in noisy tensor PCA.

MPNNs struggle with class-bottlenecks and heterophily, leading to performance limitations.

Obtaining magnetic resonance images (MRI) with high resolution and generating quantitative image-based biomarkers for assessing tissue biochemistry is crucial in clinical and research applications. How- ever, acquiring quantitative biomarkers requires high signal-to-noise ratio (SNR), which is at odds with high-resolut…

Study on sensor fusion algorithms under high dimensional noise.

Bayesian approach improves AdaLoRA's performance and efficiency.

Paper finds sample complexity for learning high-dimensional simplices from noisy data.

We study the problem of approximate ranking from observations of pairwise interactions. The goal is to estimate the underlying ranks of $n$ objects from data through interactions of comparison or collaboration. Under a general framework of approximate ranking models, we characterize the exact optimal statistical error …

New Fourier-based diffusion model improves high-frequency generation quality.

New method clusters tensors with heteroskedastic noise.

Binary feedback outperforms ordinal comparisons in ranking recovery.

Spectral algorithm recovers community structure in sparse hypergraphs.

We propose a joint source and channel coding (JSCC) technique for wireless image transmission that does not rely on explicit codes for either compression or error correction; instead, it directly maps the image pixel values to the complex-valued channel input symbols. We parameterize the encoder and decoder functions b…

The P300 Brain-Computer Interface (BCI) is a well-established communication channel for severely disabled people. The P300 event-related potential is mostly characterized by its amplitude or its area, which correlate with the spelling accuracy of the P300 speller. Here, we introduce a novel approach for estimating the …

Paper develops methods for estimating GLMs and SNR under proportional asymptotics.

This paper develops novel deep learning-based architectures and design methodologies for an orthogonal frequency division multiplexing (OFDM) receiver under the constraint of one-bit complex quantization. Single bit quantization greatly reduces complexity and power consumption, but makes accurate channel estimation and…

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…

Random forest performance depends on SNR and covariate characteristics.

Study recovers spike order in noisy tensor estimation without SNR assumptions.

EM algorithm speeds up convergence in federated learning with heterogenous data.

Study phase transitions in shuffled regression problems.