Deep learning tackles X-ray noise without clean data.
problem Lack of clean X-ray images for deep learning denoising.
method Uses Stein's Unbiased Risk Estimator (SURE) to train a deep neural network.
result SURE-based approach effectively denoises X-ray images.
This work improves texture segmentation by automatically tuning hyperparameters for Total-Variation.
problem The challenge is to automatically select hyperparameters for Total-Variation texture segmentation.
method The approach involves extending Stein's unbiased gradient estimator to handle correlated Gaussian noise, leading to an automatic tuning method.
result The method provides an automatic way to select hyperparameters for Total-Variation texture segmentation.
New method learns from noisy data without knowing noise level.
problem Learning from noisy data without knowing noise level.
method Uses Stein's Unbiased Risk Estimate (SURE) without noise level knowledge.
result Outperforms other self-supervised methods on imaging problems.
Using integration by parts on Gaussian space we construct a Stein Unbiased Risk Estimator (SURE) for the drift of Gaussian processes using their local and occupation times. By almost-sure minimization of the SURE risk of shrinkage estimators we derive an estimation and de-noising procedure for an input signal perturbed…
This paper analyzes the generalization risk of unrolled neural networks using Stein's Unbiased Risk Estimator.
problem Analyzing the generalization risk of unrolled neural networks and its relationship to network design and train sample size.
method Using Stein's Unbiased Risk Estimator (SURE), the paper analyzes the generalization risk with bias and variance components for recurrent unrolled networks, focusing on the degrees-of-freedom (DOF) component and the trace of the end-to-end network Jacobian.
result DOF is well-approximated by the weighted path sparsity of the network under incoherence conditions on the trained weights, and DOF increases with train sample size and converges to the generalization risk for both recurrent and non-recurrent schemes.
New method uses SURE to denoise signals, outperforming NPMLE.
problem Learning to optimally denoise signals corrupted by Gaussian noise.
method Hyvärinen's score matching (SM) is shown equivalent to SURE minimization.
result SURE achieves nearly parametric rates of convergence in empirical Bayes settings.
The paper analyzes the risk of CV-tuned regularized estimators and connects it to SURE.
problem Understanding the risk of CV-tuned regularized estimators.
method Derives asymptotic risk function of CV-tuned estimators and connects it to SURE.
result The risk function provides a more detailed picture of predictive performance than uniform bounds.
Learning from unlabeled and noisy data is one of the grand challenges of machine learning. As such, it has seen a flurry of research with new ideas proposed continuously. In this work, we revisit a classical idea: Stein's Unbiased Risk Estimator (SURE). We show that, in the context of image recovery, SURE and its gener…
C-SURE improves complex-valued deep learning models by shrinking estimates, outperforming MLE and SurReal.
problem Improving accuracy and robustness of complex-valued deep learning models.
method Proposes a Stein's unbiased risk estimate (SURE) for complex-valued data and integrates it into a prototype CNN classifier.
result C-SURE outperforms SurReal and MLE in accuracy and robustness on complex-valued datasets.
Many applied settings in empirical economics involve simultaneous estimation of a large number of parameters. In particular, applied economists are often interested in estimating the effects of many-valued treatments (like teacher effects or location effects), treatment effects for many groups, and prediction models wi…
The problem of estimating a high-dimensional sparse vector θ∈Rn from an observation in i.i.d. Gaussian noise is considered. The performance is measured using squared-error loss. An empirical Bayes shrinkage estimator, derived using a Bernoulli-Gaussian prior, is analyzed and compared with the…
ENSURE framework trains deep image recon algorithms without clean data.
problem Lack of clean, fully sampled ground-truth data for deep learning image reconstruction.
method Introduces ENSURE framework, a generalization of SURE and GSURE to random sampling patterns.
result ENSURE loss function is an unbiased estimate for true mean-square error.
New method for unbiased regression reduces excess risk.
problem Least squares regression with optimal solution and Hessian matrix.
method Averaged stochastic gradient descent with time-average estimator.
result Unbiased estimator with O(1/k) expected excess risk.
Generalized R2R handles non-Gaussian noise for deep network training.
problem Training deep networks from noisy data alone.
method Extending R2R to handle various noise distributions.
result GR2R loss is an unbiased estimator of supervised loss.
For the problem of multi-class linear classification and feature selection, we propose approximate message passing approaches to sparse multinomial logistic regression (MLR). First, we propose two algorithms based on the Hybrid Generalized Approximate Message Passing (HyGAMP) framework: one finds the maximum a posterio…
Paper develops an unbiased risk estimator for learning with augmented classes.
problem Learning with augmented classes where unseen classes might appear in testing.
method Uses unlabeled training data to approximate potential distribution of augmented classes.
result Establishes an unbiased risk estimator for the testing distribution under mild assumptions.
New method for estimating higher-order network dependencies in streaming data.
problem Estimating higher-order dependencies in massive, dynamic, and streaming networks.
method Adaptive sampling and unbiased estimators for streaming networks, with a James-Stein shrinkage estimator.
result Our approach outperforms baseline methods in estimating higher-order network structure from streaming data.
This paper presents a novel scaling method for unbiased risk estimation.
problem Challenges in risk assessment due to limited data, non-stationarity, and heavy tails.
method Develops a statistical framework for efficient risk scaling, extending beyond the square-root-of-time rule.
result Ensures robust and conservative risk estimation, applicable to small sample settings.
The estimation of risk measures recently gained a lot of attention, partly because of the backtesting issues of expected shortfall related to elicitability. In this work we shed a new and fundamental light on optimal estimation procedures of risk measures in terms of bias. We show that once the parameters of a model ne…
Paper proposes an unbiased risk estimator for PLLAC, handling unseen classes.
problem Handling unseen classes in PLLAC where some classes are not present in the training set.
method Proposes an unbiased risk estimator that estimates the distribution of augmented classes by differentiating known classes from unlabeled data.
result The estimator provides theoretical guarantees and converges to true risk minimizer as data increases.
We propose an estimator of prediction error using an approximate message passing (AMP) algorithm that can be applied to a broad range of sparse penalties. Following Stein's lemma, the estimator of the generalized degrees of freedom, which is a key quantity for the construction of the estimator of the prediction error, …
Develops new methods to estimate treatment effects in survival data with competing risks.
problem Estimating treatment effects in survival data with competing risks.
method Censoring Unbiased Transformations (CUTs) for survival outcomes with and without competing risks.
result Consistent estimates of heterogeneous cumulative incidence effects and total effects using HTE learners.
From only positive (P) and unlabeled (U) data, a binary classifier could be trained with PU learning, in which the state of the art is unbiased PU learning. However, if its model is very flexible, empirical risks on training data will go negative, and we will suffer from serious overfitting. In this paper, we propose a…
JojoSCL improves scRNA-seq clustering by reducing intra-cluster dispersion.
problem High dimensionality and sparsity of scRNA-seq data challenge clustering models.
method Integrates shrinkage estimator and contrastive learning for improved clustering.
result JojoSCL outperforms existing methods on ten scRNA-seq datasets.
The strategy of early stopping is a regularization technique based on choosing a stopping time for an iterative algorithm. Focusing on non-parametric regression in a reproducing kernel Hilbert space, we analyze the early stopping strategy for a form of gradient-descent applied to the least-squares loss function. We pro…
We propose an improved LASSO estimation technique based on Stein-rule. We shrink classical LASSO estimator using preliminary test, shrinkage, and positive-rule shrinkage principle. Simulation results have been carried out for various configurations of correlation coefficients (r), size of the parameter vector (β), …
New method calculates degrees of freedom for sparse estimation in continuous models.
problem Quantifying effective parameters in over-parameterized models with large continuous parameter spaces.
method Develops a continuous Lasso method for sparsity-inducing optimization over measure spaces.
result Proof of a continuous degrees of freedom formula for Beurling Lasso.
Proposes a new framework for learning from labeled and unlabeled data.
problem Learning from unlabeled and multi-label samples with arbitrary loss functions.
method Multi-complementary and unlabeled learning framework.
result Effective estimation of classification risk with optimal convergence rate.
UREs lead to overfitting in complex models, especially in complementary label learning.
problem Overfitting in weakly supervised learning with complementary labels.
method Proposed a surrogate complementary loss (SCL) framework to reduce gradient variance.
result SCL mitigates overfitting and improves URE-based methods.
Randomized trials, also known as A/B tests, are used to select between two policies: a control and a treatment. Given a corresponding set of features, we can ideally learn an optimized policy P that maps the A/B test data features to action space and optimizes reward. However, although A/B testing provides an unbiased …
Study optimizes KSD estimation from samples, revealing Hilbert-Schmidt vs trace scales.
problem Optimizing estimation of Kernel Stein Discrepancy from samples.
method Identifying and comparing minimax scales for U-statistic and V-statistic.
result Hilbert-Schmidt norm of Stein covariance operator gives optimal scale.
Paper tackles weakly supervised learning from similarity-confidence data.
problem Learning binary classifier from unlabeled data pairs with confidence of similarity.
method Proposes an unbiased estimator of classification risk from Sconf data and risk correction scheme.
result Demonstrates effectiveness of proposed methods through experiments.
In this analytical study we derive the optimal unbiased value estimator (MVU) and compare its statistical risk to three well known value estimators: Temporal Difference learning (TD), Monte Carlo estimation (MC) and Least-Squares Temporal Difference Learning (LSTD). We demonstrate that LSTD is equivalent to the MVU if …
A method for classification using pairwise similarities and unlabeled data.
problem Handling pairwise similarities and unlabeled data for classification.
method Empirical risk minimization approach to create an unbiased risk estimator.
result Derives an unbiased risk estimator for handling both similarities and unlabeled data.
Improved stochastic gradient estimation for deep learning in high dimensions.
problem Inadmissibility of mini-batch gradients in high-dimensional settings.
method Stein-rule shrinkage applied to gradient computation.
result The proposed SR-Adam outperforms Adam in large-batch settings.
Improved estimator for least squares using random projections achieves smaller error.
problem Improving the accuracy of least squares solutions for large-scale problems.
method James-Stein estimator applied to Gaussian sketching of least squares problems.
result Upper and lower bounds match when SNR is small and data matrix is well-conditioned.
This paper considers the problem of estimating a high-dimensional vector of parameters θ∈Rn from a noisy observation. The noise vector is i.i.d. Gaussian with known variance. For a squared-error loss function, the James-Stein (JS) estimator is known to dominate the simple maximum-likelihood (…
Efficient implicit differentiation for Lasso hyperparameter optimization.
problem Difficult hyperparameter optimization for Lasso-type models.
method Implicit differentiation algorithm tailored for Lasso-type problems, avoiding matrix inversion and solving linear systems.
result Outperforms standard methods in optimizing error on held-out data or Stein Unbiased Risk Estimator (SURE).
Integrates ESG data into Black-Litterman for portfolio optimization.
problem Optimizing portfolios with ESG considerations.
method Black-Litterman framework with Stein shrinkage for ESG bias, multivariate affine normal-inverse Gaussian model, CVaR risk measure, daily reallocation.
result Successful portfolio optimization with returns of 40-45% annually.
SureMap estimates model performance across subpopulations efficiently.
problem Estimating model performance across subpopulations with scarce data.
method Simultaneous Gaussian mean estimation with external data.
result High accuracy in both multi-task and single-task disaggregated evaluations.
Estimates conversion probabilities from click sequences with privacy constraints.
problem Training models in advertising with limited direct click-conversion links.
method Formalizes learning from attribution sets, constructs unbiased estimator, applies Empirical Risk Minimization.
result Empirical Risk Minimization achieves generalization guarantees and robustness against prior errors.
We present a multi-task learning approach to jointly estimate the means of multiple independent data sets. The proposed multi-task averaging (MTA) algorithm results in a convex combination of the single-task maximum likelihood estimates. We derive the optimal minimum risk estimator and the minimax estimator, and show t…
Iterative thresholding algorithms are well-suited for high-dimensional problems in sparse recovery and compressive sensing. The performance of this class of algorithms depends heavily on the tuning of certain threshold parameters. In particular, both the final reconstruction error and the convergence rate of the algori…
A sparse modeling is a major topic in machine learning and statistics. LASSO (Least Absolute Shrinkage and Selection Operator) is a popular sparse modeling method while it has been known to yield unexpected large bias especially at a sparse representation. There have been several studies for improving this problem such…
Paper proposes unbiased learning for recommendation causal effects.
problem Estimating the causal effect of recommendation when the ground truth is unobservable.
method Inverse propensity scoring technique to construct unbiased estimators, followed by empirical risk minimization with propensity capping.
result The proposed method outperforms other biased learning methods in various settings.
The article compares neural networks and logistic regression for credit scoring and introduces a new probability calibration technique.
problem Improving credit scoring accuracy using machine learning techniques.
method Comparison of logistic regression and neural networks, feature importance assessment, temporal feature inclusion, and SURE probability calibration.
result Neural networks can slightly improve credit scoring performance, and SURE calibration technique enhances probability calibration.
Recently developed deep-learning-based denoisers often outperform state-of-the-art conventional denoisers such as the BM3D. They are typically trained to minimize the mean squared error (MSE) between the output image of a deep neural network (DNN) and a ground truth image. Thus, it is important for deep-learning-based …
Bayesian method improves extreme quantile estimation with zero coverage error.
problem Estimating extreme quantiles with zero coverage error in small samples.
method Bayesian quantile estimation using Jeffreys prior.
result Bayesian method results in zero coverage error, unlike maximum likelihood.