arXiv research

Characterizes uncertainty in low-rank matrix completion with noisy data.

Exponential Lasso improves Lasso's robustness to outliers and heavy-tailed noise.

Researchers improve NCE by addressing its flat loss landscape issues.

Existence of incomplete Radner equilibrium with endogenous noise tracker.

Gaussians as noise in NCE lead to exponentially bad conditioning, hindering its efficiency.

SGD with machine learning noise converges to global minimum exponentially fast.

We consider the problem of unconstrained online convex optimization (OCO) with sub-exponential noise, a strictly more general problem than the standard OCO. In this setting, the learner receives a subgradient of the loss functions corrupted by sub-exponential noise and strives to achieve optimal regret guarantee, witho…

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

The matrix completion problem consists in reconstructing a matrix from a sample of entries, possibly observed with noise. A popular class of estimator, known as nuclear norm penalized estimators, are based on minimizing the sum of a data fitting term and a nuclear norm penalization. Here, we investigate the case where …

A new method for robust training under label noise using weighted gradient descent.

Study shows exponential gap in sample complexity between noisy and non-noisy recurrent neural networks.

Study shows exponential convergence in classification errors using random features and SGD.

Unified view on learning unnormalized distributions using NCE.

This work reveals symmetries in quantum circuits and develops a noise-aware optimization method.

We introduce a model of super-exponential financial bubbles with two assets (risky and risk-free), in which rational investors and noise traders co-exist. Rational investors form expectations on the return and risk of a risky asset and maximize their constant relative risk aversion expected utility with respect to thei…

Quantum systems with scrambling improve temporal information processing, but scaling requires exponential overhead.

Paper establishes universal lower bounds and optimal rates for clustering sub-exponential mixture models.

SGD favors flat minima exponentially more than sharp minima in deep learning.

New method denoises images without clean reference using Tweedie distributions.

We consider binary classification problems with positive definite kernels and square loss, and study the convergence rates of stochastic gradient methods. We show that while the excess testing loss (squared loss) converges slowly to zero as the number of observations (and thus iterations) goes to infinity, the testing …

We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are statistical in the sense that they rely on estimates of expectations of functions of filtered random e…

Adapts SGD to noise and problem specifics for faster convergence.

Nonlinear SGD achieves high-probability rates in non-convex optimization with heavy-tailed noise.

The paper analyzes and validates two step size schedules for SGD: exponential and cosine, proving their adaptivity and performance.

Kernel estimator optimally recovers function from noisy exponential Radon transform.

Paper provides a new lower bound on MMSE using Poincaré inequality.

New algorithm reduces feature count and accelerates error convergence.

Improved averaging method for noisy observations converges strongly.

Behavior cloning training instabilities amplified by SGD noise over long horizons.

We develop a general method for estimating a finite mixture of non-normalized models. Here, a non-normalized model is defined to be a parametric distribution with an intractable normalization constant. Existing methods for estimating non-normalized models without computing the normalization constant are not applicable …

The study of private inference has been sparked by growing concern regarding the analysis of data when it stems from sensitive sources. We present the first method for private Bayesian inference in exponential families that properly accounts for noise introduced by the privacy mechanism. It is efficient because it work…

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 introduce a covariance matrix estimator that both takes into account the heteroskedasticity of financial returns (by using an exponentially weighted moving average) and reduces the effective dimensionality of the estimation (and hence measurement noise) via techniques borrowed from random matrix theory. We calculate…

The problem of Poisson denoising appears in various imaging applications, such as low-light photography, medical imaging and microscopy. In cases of high SNR, several transformations exist so as to convert the Poisson noise into an additive i.i.d. Gaussian noise, for which many effective algorithms are available. Howev…

New bounds for kernel regression under non-Gaussian noise.

Shot-Noise processes constitute a useful tool in various areas, in particular in finance. They allow to model abrupt changes in a more flexible way than processes with jumps and hence are an ideal tool for modelling stock prices, credit portfolio risk, systemic risk, or electricity markets. Here we consider a general f…

This study investigates self-organizing dynamics in a stochastic exponential DAM model using Temporal Complexity.

Generalized R2R handles non-Gaussian noise for deep network training.

The paper studies how noise synchronizes tokens in deep transformer models.

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

We consider stochastic gradient descent and its averaging variant for binary classification problems in a reproducing kernel Hilbert space. In the traditional analysis using a consistency property of loss functions, it is known that the expected classification error converges more slowly than the expected risk even whe…

The paper explores how symmetries and noise in SGD influence parameter dynamics.

Novel loss functions improve decision tree learning from noisy data.

Ridge regression linked to Poisson resetting in statistical physics.

Study well-posedness of SPDE on Riemannian manifolds with rough initial conditions.

In this paper, a Bayesian inference technique based on Taylor series approximation of the logarithm of the likelihood function is presented. The proposed approximation is devised for the case, where the prior distribution belongs to the exponential family of distributions. The logarithm of the likelihood function is li…

Paper establishes convergence rates and concentration bounds for stochastic approximation and reinforcement learning with Markovian noise.

In this note, we present a version of the Thompson sampling algorithm for the problem of online linear generalization with full information (i.e., the experts setting), studied by Kalai and Vempala, 2005. The algorithm uses a Gaussian prior and time-varying Gaussian likelihoods, and we show that it essentially reduces …