arXiv research

Study on signal-plus-noise decomposition in nonlinear spiked random matrices.

Study analyzes perturbations in singular subspaces under random noise.

Improves signal detection in non-Gaussian noise using transformed data.

We propose a reinforcement learning (RL) based closed loop power control algorithm for the downlink of the voice over LTE (VoLTE) radio bearer for an indoor environment served by small cells. The main contributions of our paper are to 1) use RL to solve performance tuning problems in an indoor cellular network for voic…

Improves detection of low-rank signals from noisy data matrices.

This paper analyzes the interpolation error of nonlinear Attention compared to linear regression.

For random matrix models, the parameter estimation based on the traditional likelihood functions is not straightforward in particular when we have only one sample matrix. We introduce a new parameter optimization method for random matrix models which works even in such a case. The method is based on the spectral distri…

Independent Component Analysis (ICA) is a popular model for blind signal separation. The ICA model assumes that a number of independent source signals are linearly mixed to form the observed signals. We propose a new algorithm, PEGI (for pseudo-Euclidean Gradient Iteration), for provable model recovery for ICA with Gau…

New findings on computational limits for estimating hidden structures.

We consider the Principal Component Analysis problem for large tensors of arbitrary order $k$ under a single-spike (or rank-one plus noise) model. On the one hand, we use information theory, and recent results in probability theory, to establish necessary and sufficient conditions under which the principal component ca…

Multilayer graphs are commonly used for representing different relations between entities and handling heterogeneous data processing tasks. New challenges arise in multilayer graph clustering for assigning clusters to a common multilayer node set and for combining information from each layer. This paper presents a theo…

Principal component analysis (PCA) is a popular method for projecting data onto uncorrelated components in lower dimension, although the optimal number of components is not specified. Likewise, multiple signal classification (MUSIC) algorithm is a popular PCA-based method for estimating directions of arrival (DOAs) of …

Estimates parameters in max-linear Bayesian networks with noise.

Proposes a method to compare noisy high-dimensional datasets with low-dimensional manifolds.

We analyze why some models resist unlearning using linear stability theory.

Logit regularization induces logit clustering, affecting classifier performance.

Randomized SVD shows phase transitions in noisy data.

The paper analyzes Karcher means on restricted PSD matrices with statistical guarantees.

Unified approach to tensor PCA and related problems using tensor cumulants.

New method recovers sparse signals from nonlinear observations with robust error bounds.

Solves a fundamental problem in statistics and imaging with new methods.

Multilayer graphs are commonly used for representing different relations between entities and handling heterogeneous data processing tasks. Non-standard multilayer graph clustering methods are needed for assigning clusters to a common multilayer node set and for combining information from each layer. This paper present…

Optimal test for detecting signal in noisy matrix model.

We propose an algorithm to automate fault management in an outdoor cellular network using deep reinforcement learning (RL) against wireless impairments. This algorithm enables the cellular network cluster to self-heal by allowing RL to learn how to improve the downlink signal to interference plus noise ratio through ex…

Using a Bayesian approach, we consider the problem of recovering sparse signals under additive sparse and dense noise. Typically, sparse noise models outliers, impulse bursts or data loss. To handle sparse noise, existing methods simultaneously estimate the sparse signal of interest and the sparse noise of no interest.…

GRRT recovers sparse signals without prior sparsity or noise variance knowledge.

Many statistical estimators for high-dimensional linear regression are M-estimators, formed through minimizing a data-dependent square loss function plus a regularizer. This work considers a new class of estimators implicitly defined through a discretized gradient dynamic system under overparameterization. We show that…

In high-dimensional data, structured noise caused by observed and unobserved factors affecting multiple target variables simultaneously, imposes a serious challenge for modeling, by masking the often weak signal. Therefore, (1) explaining away the structured noise in multiple-output regression is of paramount importanc…

The paper describes a method to infer the signal-to-noise ratio in portfolio optimization.

CVAE detects weak complex signals in maritime radar, improving detection over classical methods.

We consider deterministic Markov decision processes (MDPs) and apply max-plus algebra tools to approximate the value iteration algorithm by a smaller-dimensional iteration based on a representation on dictionaries of value functions. The setup naturally leads to novel theoretical results which are simply formulated due…

Stochastic regularisation is an important weapon in the arsenal of a deep learning practitioner. However, despite recent theoretical advances, our understanding of how noise influences signal propagation in deep neural networks remains limited. By extending recent work based on mean field theory, we develop a new frame…

The study analyzes how label noise affects deep learning feature learning.

Study on signal recovery from low-rank matrix with sparse noise.

Paper proposes a self-supervised method to denoise autoregressive signals with heavy-tailed noise.

Proposes isotonic recalibration for insurance pricing to ensure auto-calibration under low signal-to-noise ratio.

We propose a learning-based approach for estimating the spectrum of a multisinusoidal signal from a finite number of samples. A neural-network is trained to approximate the spectra of such signals on simulated data. The proposed methodology is very flexible: adapting to different signal and noise models only requires m…

Study on Langevin dynamics for recovering planted signals in spiked matrix models.

Paper develops an online EM algorithm for graph signal inference from streaming data.

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…

The signal-noise ratio of a portfolio of p assets, its expected return divided by its risk, is couched as an estimation problem on the sphere. When the portfolio is built using noisy data, the expected value of the signal-noise ratio is bounded from above via a Cramer-Rao bound, for the case of Gaussian returns. The bo…

PEGR improves deep learning models' robustness against noisy data.

The paper develops a method to model high-dimensional data with many variables and weak signals.

In this work, we present a novel robust distributed beamforming (RDB) approach based on low-rank and cross-correlation techniques. The proposed RDB approach mitigates the effects of channel errors in wireless networks equipped with relays based on the exploitation of the cross-correlation between the received data from…

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

PCA++ improves robustness to background noise in contrastive learning.

This work optimizes signal estimation for sparse MRA with collision-free signals.

T-Rex uses EM to fit robust factor models in noisy data.