arXiv research

The paper provides tighter error bounds for GPR under bounded support noise.

For binary classification we establish learning rates up to the order of $n^{-1}$ for support vector machines (SVMs) with hinge loss and Gaussian RBF kernels. These rates are in terms of two assumptions on the considered distributions: Tsybakov's noise assumption to establish a small estimation error, and a new geometr…

New method bounds stochastic subgradient methods with heavy-tailed noise.

New SVM model balances sparsity and robustness in noisy data.

The Lasso performs well in ultra-sparse linear models with finite support size.

Paper provides tail bounds for stochastic mirror descent in heavy-tailed noise.

PBM mechanism improves privacy and accuracy in federated learning.

BAEN-SVM improves SVM robustness to noisy data.

DP-SGD can update fewer coordinates while maintaining privacy.

Several recent works have shown that state-of-the-art classifiers are vulnerable to worst-case (i.e., adversarial) perturbations of the datapoints. On the other hand, it has been empirically observed that these same classifiers are relatively robust to random noise. In this paper, we propose to study a \textit{semi-ran…

Improved bound for Gaussian mechanism in differential privacy.

We consider the problem of publicly releasing a dataset for support vector machine classification while not infringing on the privacy of data subjects (i.e., individuals whose private information is stored in the dataset). The dataset is systematically obfuscated using an additive noise for privacy protection. Motivate…

Paper analyzes finite-time performance of SA in RL with Markovian noise.

Study on deep learning for speckle noise reduction in imaging modalities.

Noise-ignorant empirical risk minimization achieves state-of-the-art performance on noisy 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…

A new method for support vector regression using a data-driven insensitive parameter.

The support recovery problem consists of determining a sparse subset of variables that is relevant in generating a set of observations. In this paper, we study the support recovery problem in the phase retrieval model consisting of noisy phaseless measurements, which arises in a diverse range of settings such as optica…

The paper shows how label noise in training can lead to solutions that solve a Lasso program.

We develop model free PAC performance guarantees for multiple concurrent MDPs, extending recent works where a single learner interacts with multiple non-interacting agents in a noise free environment. Our framework allows noisy and resource limited communication between agents, and develops novel PAC guarantees in this…

Unified framework for discrete diffusion modeling with flexible noising processes.

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

Simultaneous orthogonal matching pursuit (SOMP) and block OMP (BOMP) are two widely used techniques for sparse support recovery in multiple measurement vector (MMV) and block sparse (BS) models respectively. For optimal performance, both SOMP and BOMP require \textit{a priori} knowledge of signal sparsity or noise vari…

Paper reduces sample complexity for bilinear systems identification to nearly constant.

New algorithm reduces pricing error by a factor of T^2/3.

New algorithm recovers model coefficients and supports from noisy data.

New model shows neural networks can use noise to improve long-tailed data classification.

Existing strategies for finite-armed stochastic bandits mostly depend on a parameter of scale that must be known in advance. Sometimes this is in the form of a bound on the payoffs, or the knowledge of a variance or subgaussian parameter. The notable exceptions are the analysis of Gaussian bandits with unknown mean and…

The study establishes minimax bounds for estimating operators from noisy samples.

Explaining the unreasonable effectiveness of deep learning has eluded researchers around the globe. Various authors have described multiple metrics to evaluate the capacity of deep architectures. In this paper, we allude to the radius margin bounds described for a support vector machine (SVM) with hinge loss, apply the…

The paper improves alignment methods for deep neural networks using geometric and spectral analysis.

New bounds for SGLD show error decreases with more data.

Paper improves SLCB regret bound for bounded noise.

RHPSVM improves SVM performance with robust loss function.

We develop coreset techniques for noisy clustering with provable guarantees.

The support recovery problem consists of determining a sparse subset of a set of variables that is relevant in generating a set of observations, and arises in a diverse range of settings such as compressive sensing, and subset selection in regression, and group testing. In this paper, we take a unified approach to supp…

The high-dimensional linear model $y = X β^0 + ε$ is considered and the focus is put on the problem of recovering the support $S^0$ of the sparse vector $β^0.$ We introduce Lasso-Zero, a new $\ell_1$-based estimator whose novelty resides in an "overfit, then threshold" paradigm and the use of noise dictionaries concate…

This paper provides a method for noise-calibrated inference from DP synthetic data.

The ability to detect sparse signals from noisy high-dimensional data is a top priority in modern science and engineering. A sparse solution of the linear system $A ρ= b_0$ can be found efficiently with an $l_1$-norm minimization approach if the data is noiseless. Detection of the signal's support from data corrupted b…

Enhanced consistency bounds derived for classification under a new noise condition.

This paper examines a general class of noisy matrix completion tasks where the goal is to estimate a matrix from observations obtained at a subset of its entries, each of which is subject to random noise or corruption. Our specific focus is on settings where the matrix to be estimated is well-approximated by a product …

Learning optimal dictionaries for sparse coding has exposed characteristic sparse features of many natural signals. However, universal guarantees of the stability of such features in the presence of noise are lacking. Here, we provide very general conditions guaranteeing when dictionaries yielding the sparsest encoding…

Lower bounds show OLS outperforms basis pursuit in overparameterized linear regression.

End-to-end algorithm for controlling bilinear systems with probabilistic noise.

We present a machine learning based method for noise classification using a low-power and inexpensive IoT unit. We use Mel-frequency cepstral coefficients for audio feature extraction and supervised classification algorithms (that is, support vector machine and k-nearest neighbors) for noise classification. We evaluate…

We study the problem of community detection when there is covariate information about the node labels and one observes multiple correlated networks. We provide an asymptotic upper bound on the per-node mutual information as well as a heuristic analysis of a multivariate performance measure called the MMSE matrix. These…

Study recovers tree structure in noisy MRFs with support size 3 or more.

SVDD and Deep SVDD improve radar target detection in clutter.