arXiv research

Paper introduces $ρ$-Perfect to estimate model-human correlation in subjective datasets.

We consider classification in the presence of class-dependent asymmetric label noise with unknown noise probabilities. In this setting, identifiability conditions are known, but additional assumptions were shown to be required for finite sample rates, and so far only the parametric rate has been obtained. Assuming thes…

New method improves false-/true-positive-rate estimation in fraud detection with noisy labels.

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

New method for spot volatility estimation with reduced microstructure noise.

Paper estimates noise covariance in correlated multi-task linear models.

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…

Paper reconciles minimax rates and optimal recovery rates for noisy observations.

Paper derives convergence rates and confidence intervals for LSA with Markovian noise.

The paper proves the consistency and efficiency of a volatility estimator in noisy data.

New methods improve estimation accuracy in noisy settings.

Efficiently estimates linear models robust to corrupted data.

Adapts SGD to noise and problem specifics for faster convergence.

Paper improves Fisher information estimation methods.

The fundamental frequency (F0) represents pitch in speech that determines prosodic characteristics of speech and is needed in various tasks for speech analysis and synthesis. Despite decades of research on this topic, F0 estimation at low signal-to-noise ratios (SNRs) in unexpected noise conditions remains difficult. T…

We formulate and study a general family of (continuous-time) stochastic dynamics for accelerated first-order minimization of smooth convex functions. Building on an averaging formulation of accelerated mirror descent, we propose a stochastic variant in which the gradient is contaminated by noise, and study the resultin…

Differential privacy is a cryptographically-motivated definition of privacy which has gained significant attention over the past few years. Differentially private solutions enforce privacy by adding random noise to a function computed over the data, and the challenge in designing such algorithms is to control the added…

Paper tackles noisy bandit feedback for multiclass classification.

Unified view on learning unnormalized distributions using NCE.

Algorithm optimally estimates linear dynamical systems with active input selection.

The study investigates noise effects on parameter estimation for Ornstein-Uhlenbeck processes.

New methods lift weak supervision to structured prediction, providing robustness guarantees.

Noisy PN learning is the problem of binary classification when training examples may be mislabeled (flipped) uniformly with noise rate rho1 for positive examples and rho0 for negative examples. We propose Rank Pruning (RP) to solve noisy PN learning and the open problem of estimating the noise rates, i.e. the fraction …

Paper analyzes faster convergence rates for reinforcement learning from offline data.

The basic model for high-frequency data in finance is considered, where an efficient price process is observed under microstructure noise. It is shown that this nonparametric model is in Le Cam's sense asymptotically equivalent to a Gaussian shift experiment in terms of the square root of the volatility function $σ$. A…

ADOPT optimizes Adam to converge with any β2 without bounded noise.

New algorithms reduce communication for sparse mean estimation in noisy distributed systems.

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 …

CWGD measures gradient diversity weighted by curvature, improving SGD convergence.

We address noisy Euclidean distances in high dimensions, estimating noise levels and correcting distances.

Adapts to estimate functions from noisy ERT data.

Paper recovers lattice signal partitions efficiently.

Noise affects the effectiveness of interpolating models, especially those with strong inductive biases.

We find the minimax rate of convergence in Hausdorff distance for estimating a manifold M of dimension d embedded in R^D given a noisy sample from the manifold. We assume that the manifold satisfies a smoothness condition and that the noise distribution has compact support. We show that the optimal rate of convergence …

In this paper, we study a classification problem in which sample labels are randomly corrupted. In this scenario, there is an unobservable sample with noise-free labels. However, before being observed, the true labels are independently flipped with a probability $ρ\in[0,0.5)$, and the random label noise can be class-co…

We show that if $F$ is a convex class of functions that is $L$-subgaussian, the error rate of learning problems generated by independent noise is equivalent to a fixed point determined by `local' covering estimates of the class, rather than by the gaussian averages. To that end, we establish new sharp upper and lower e…

We consider the dynamic linear regression problem, where the predictor vector may vary with time. This problem can be modeled as a linear dynamical system, with non-constant observation operator, where the parameters that need to be learned are the variance of both the process noise and the observation noise. While var…

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

Proposes DenoiseBid to correct uncertain CTR and CVR estimates for autobidding.

A new framework for PPLS combines noise estimation, optimization, and calibration.

The study tackles rough noise in high-frequency financial data using fractional Brownian motion.

We analyze a simple prefiltered variation of the least squares estimator for the problem of estimation with biased, semi-parametric noise, an error model studied more broadly in causal statistics and active learning. We prove an oracle inequality which demonstrates that this procedure provably mitigates the variance in…

Paper presents a deep learning method for estimating asset return precision matrices in noisy financial markets.

Study on distributed nonparametric function estimation with optimal rate and cost of adaptation.

New averaging technique speeds up Newton method convergence.

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…

We propose a novel receiver for orthogonal frequency division multiplexing (OFDM) transmissions in impulsive noise environments. Impulsive noise arises in many modern wireless and wireline communication systems, such as Wi-Fi and powerline communications, due to uncoordinated interference that is much stronger than the…

We study Empirical Risk Minimizers (ERM) and Regularized Empirical Risk Minimizers (RERM) for regression problems with convex and $L$-Lipschitz loss functions. We consider a setting where $|\cO|$ malicious outliers contaminate the labels. In that case, under a local Bernstein condition, we show that the $L_2$-error rat…