arXiv research

Paper tackles SMPC for linear systems with unknown noise distribution.

Safety filter for unknown discrete-time systems with learned models and noise covariance.

Bayes classifier cannot be learned from noisy labels without knowing noise distribution.

Study investigates classification with unknown label noise in non-compact feature spaces.

Proposes a new CSC model for handling unknown noise.

We study the problem of learning an unknown mixture of $k$ rankings over $n$ elements, given access to noisy samples drawn from the unknown mixture. We consider a range of different noise models, including natural variants of the "heat kernel" noise framework and the Mallows model. For each of these noise models we giv…

We develop an unsupervised, nonparametric, and scalable statistical learning method for detection of unknown objects in noisy images. The method uses results from percolation theory and random graph theory. We present an algorithm that allows to detect objects of unknown shapes and sizes in the presence of nonparametri…

Improved PINNs for solving PDEs with unknown measurement noise.

New method learns from noisy data without knowing noise level.

Robust kNN classifier achieves optimal rates in noisy classification.

Paper tackles small eigen-gap estimation and inference for noisy symmetric matrices.

Method identifies unknown intervention targets in structural causal models from diverse data.

We develop a novel method for detection of signals and reconstruction of images in the presence of random noise. The method uses results from percolation theory. We specifically address the problem of detection of multiple objects of unknown shapes in the case of nonparametric noise. The noise density is unknown and ca…

Improved SGD with AdaGrad stepsizes adapts to unknown parameters and unbounded gradients.

We study statistical detection of grayscale objects in noisy images. The object of interest is of unknown shape and has an unknown intensity, that can be varying over the object and can be negative. No boundary shape constraints are imposed on the object, only a weak bulk condition for the object's interior is required…

This article considers algorithmic and statistical aspects of linear regression when the correspondence between the covariates and the responses is unknown. First, a fully polynomial-time approximation scheme is given for the natural least squares optimization problem in any constant dimension. Next, in an average-case…

Optimal pricing strategy for unknown valuation models with noisy feedback.

We revisit the Bayesian online inference problems for the linear dynamic systems (LDS) under non- Gaussian environment. The noises can naturally be non-Gaussian (skewed and/or heavy tailed) or to accommodate spurious observations, noises can be modeled as heavy tailed. However, at the cost of such noise robustness, the…

We consider the robust phase retrieval problem of recovering the unknown signal from the magnitude-only measurements, where the measurements can be contaminated by both sparse arbitrary corruption and bounded random noise. We propose a new nonconvex algorithm for robust phase retrieval, namely Robust Wirtinger Flow to …

Wave maps with noise can lead to self-similar blowup from arbitrary initial data.

Study online linear regression with paid noise reduction.

The paper develops adaptive confidence intervals for Efron's Gaussian two-groups model with unknown contamination.

New insights into noise distribution for self-supervised learning.

Paper tackles online control of linear systems with unbounded noise.

Proposes a learned Bayesian Cramér-Rao bound for unknown measurement models.

The paper learns an autoregressive filter for unknown dynamical systems with robust guarantees.

A new pricing strategy learns customer valuations without noise distribution knowledge.

As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to evaluate the robustness of AQEM policies and assess the resource used by the po…

We consider a setting, where the output of a linear dynamical system (LDS) is, with an unknown but fixed probability, replaced by noise. There, we present a robust method for the prediction of the outputs of the LDS and identification of the samples of noise, and prove guarantees on its statistical performance. One app…

Most existing image denoising approaches assumed the noise to be homogeneous white Gaussian distributed with known intensity. However, in real noisy images, the noise models are usually unknown beforehand and can be much more complex. This paper addresses this problem and proposes a novel blind image denoising algorith…

The paper tackles resource allocation for arms with unknown and random rewards, achieving optimal regret bounds.

HeMPPCAT improves PCA for data with varying noise.

Efficiently classifies binary labels with XOR queries, even under noisy conditions.

Framework estimates PDEs from noisy data using neural networks.

Bayesian model learns multiscale interactions in complex systems.

The paper analyzes the statistical cost of tuning kernel hyperparameters in robust regression.

A new RL approach optimizes reserve prices in multi-phase auctions, reducing revenue regret.

Study uncovers statistical optimality of nonconvex tensor completion methods.

Unsupervised beamforming improves ASR in noisy conditions.

Novel confidence sets improve linear bandit performance by adapting to unknown noise levels.

GnIES recovers causal structure from unknown interventions.

This work addresses various open questions in the theory of active learning for nonparametric classification. Our contributions are both statistical and algorithmic: -We establish new minimax-rates for active learning under common \textit{noise conditions}. These rates display interesting transitions -- due to the inte…

The paper develops tests for variable selection using LARS in high dimensions.

Method preserves Hamiltonian structure for unknown systems from noisy data.

Proposes a progressive label correction method for feature-dependent label noise.

Paper proposes DR-NMF for robust NMF with unknown noise model.

Consider a noisy linear observation model with an unknown permutation, based on observing $y = Π^* A x^* + w$, where $x^* \in \mathbb{R}^d$ is an unknown vector, $Π^*$ is an unknown $n \times n$ permutation matrix, and $w \in \mathbb{R}^n$ is additive Gaussian noise. We analyze the problem of permutation recovery in a …

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.…