Machine learning improves official statistics but needs rigorous validation.
problem Lack of methodological robustness in machine learning for official statistics.
method Total Machine Learning Error (TMLE) framework to validate ML models.
result TMLE addresses representativeness and measurement errors in ML models.
Study identifies and analyzes three types of errors in learning Fourier operators.
problem Statistical, discretization, and truncation errors in learning Fourier operators.
method Analysis of a Discrete Fourier Transform (DFT) based least squares estimator.
result Established upper and lower bounds on statistical, discretization, and truncation errors.
Paper develops error rates for physics-informed learning, comparing it to data-driven methods.
problem Understanding the trade-off between soft penalties and hard constraints in PISL.
method Develops complexity-dependent error rates using the small-ball method.
result Physics-informed estimators have comparable error rates to hard constrained methods, differing only by constants.
Study controls error rates of binary classifiers using hypothesis testing.
problem Traditional binary classifiers have uncontrolled error rates.
method Combines binary classification with statistical hypothesis testing.
result Trained classifiers can be made to meet target error rate thresholds.
Study GLS estimator properties in multivariate regression with heteroskedastic and autocorrelated errors.
problem Asymptotic properties of GLS estimator in multivariate regression with specific error structures.
method Derive Wald statistics for linear restrictions and assess their performance.
result Wald statistics remain robust to heteroskedasticity and autocorrelation.
Study trade-offs between statistical and computational efficiency in variational inference.
problem Optimizing statistical accuracy vs. computational efficiency in Bayesian inference.
method Case study on Gaussian inferential models with diagonal plus low-rank precision matrices, analyzing Bayesian posterior inference and frequentist uncertainty quantification errors.
result Lower-rank models reduce variance and accelerate convergence but increase posterior inference error.
This paper examines error bounds for deep learning classifiers with noisy labels.
problem Understanding the performance of classifiers trained on noisy data.
method Derives error bounds for excess risk, decomposing it into statistical and approximation errors. Uses independent block construction for statistical dependencies and vector-valued setting for approximation error.
result Established theoretical results for error bounds in deep learning with noisy labels, mitigating the impact of high-dimensional input spaces.
We revisit resampling procedures for error estimation in binary classification in terms of U-statistics. In particular, we exploit the fact that the error rate estimator involving all learning-testing splits is a U-statistic. Thus, it has minimal variance among all unbiased estimators and is asymptotically normally dis…
New framework assesses extreme errors in machine learning models.
problem Current validation methods fail to quantify extreme errors in high-stakes domains.
method Uses Extreme Value Theory (EVT) to estimate worst-case failures.
result Establishes EVT as a fundamental tool for assessing model reliability.
Context: Conducting experiments is central to research machine learning research to benchmark, evaluate and compare learning algorithms. Consequently it is important we conduct reliable, trustworthy experiments. Objective: We investigate the incidence of errors in a sample of machine learning experiments in the domain …
This paper reviews methods for constructing confidence intervals for error rates in 1:1 matching tasks.
problem Challenges in assessing uncertainty of error rates in matching algorithms, especially when data are dependent and error rates are low.
method Derives and examines statistical properties of methods for constructing confidence intervals for error rates in 1:1 matching tasks.
result Coverage and interval width vary with sample size, error rates, and data dependence.
Gaussian graphical model is a graphical representation of the dependence structure for a Gaussian random vector. It is recognized as a powerful tool in different applied fields such as bioinformatics, error-control codes, speech language, information retrieval and others. Gaussian graphical model selection is a statist…
We formulate statistical watermarking as hypothesis testing and establish near-optimal bounds.
problem Statistical watermarking in the context of hypothesis testing.
method Formulated as a hypothesis testing problem, using coupling of output tokens and rejection regions.
result Established nearly matching upper and lower bounds on the number of i.i.d. tokens required for small Type I and Type II errors.
DP-PCA improves privacy in PCA computations with optimal statistical error.
problem Differentially private principal component analysis with sub-linear sample complexity.
method Private minibatch gradient ascent with private mean estimation.
result Achieves optimal statistical error rates for sub-Gaussian data with n=ildeO(d) samples. Multiplicative noise models are often used instead of additive noise models in cases in which the noise variance depends on the state. Furthermore, when Poisson distributions with relatively small counts are approximated with normal distributions, multiplicative noise approximations are straightforward to implement. Th…
The paper analyzes constrained optimal portfolios in high dimensions using novel statistical learning techniques.
problem Forming optimal portfolios with constraints in high-dimensional asset spaces.
method CROWN method integrating factor models with nodewise regression for estimation in large dimensions.
result Demonstrates estimation consistency and convergence rates for constrained portfolio weights, risk, and Sharpe Ratio.
Efficient tests achieve best error rates in high-dimensional hypothesis testing.
problem Achieving optimal error rates in computationally efficient hypothesis testing.
method Linear spectral statistics and low-degree likelihood ratio analysis.
result An efficient test achieves the best possible error rates among all computationally efficient tests.
Statistical mechanics reveals phase transitions in ε-SVR error.
problem Understanding task precision in neural representations with variability.
method Statistical mechanics applied to ε-SVR. result Double-descent phenomenon in generalization error due to ε. Study loop corrections in random feature models affecting training and test errors.
problem Analyzing loop corrections in random feature models to understand training and test errors.
method Statistical physics and effective field theory approach to study loop corrections.
result Derived loop corrections to training error, test error, and generalization gap.
New error bounds for GANs with nonlinear objective functions derived.
problem Statistical consistency of GANs with nonlinear objective functions.
method Derivation of statistical error bounds for (f,Γ)-GANs using Rademacher complexity. result Proves the statistical consistency of (f,Γ)-GANs. Optimum-statistical collaboration improves black-box optimization efficiency.
problem Improving black-box optimization efficiency through better statistical collaboration.
method Introducing optimum-statistical collaboration framework for hierarchical bandits-based optimization.
result Demonstrated improved regret bounds and better performance in experiments.
This work analyzes CoT prompting methods from a statistical estimation perspective.
problem Improving the effectiveness of LLMs in solving multi-step reasoning problems.
method Introducing a multi-step latent variable model to characterize CoT prompting from a statistical estimation viewpoint.
result The CoT estimator is equivalent to a Bayesian estimator when the pretraining dataset is large.
The paper shows how sketching data can simplify regression inference even when errors are heteroskedastic.
problem Performing robust inference with heteroskedastic errors using sketched data.
method Using random projections to sketch data, the paper shows that sketched estimates behave as if errors are homoskedastic.
result Estimation by random sampling does not have the same property, and sketched estimates are asymptotically normal with homoskedastic variance.
In this paper, we explore various statistical techniques for anomaly detection in conjunction with the popular Long Short-Term Memory (LSTM) deep learning model for transportation networks. We obtain the prediction errors from an LSTM model, and then apply three statistical models based on (i) the Gaussian distribution…
The paper bounds the mean absolute error in DNN vector-to-vector regression.
problem Bounding the mean absolute error in deep neural network based vector-to-vector regression.
method Error decomposition techniques in statistical learning theory and non-convex optimization theory were used to derive upper bounds for approximation, estimation, and optimization errors.
result Theoretical upper bounds for mean absolute error in DNN vector-to-vector regression were derived and validated experimentally.
Study shows heavy-tailed distributions affect reliability of machine learning calibration statistics.
problem Reliability of calibration statistics for machine learning regression tasks is affected by heavy-tailed uncertainty and error distributions.
method Examined two calibration error estimation methods (CE and ZMS) and found ZMS to be less sensitive to heavy-tailed distributions.
result Heavy-tailed distributions make MSE and MV unreliable, but ZMS remains a reliable approach.
Enhanced TSFMs improve time series forecasting accuracy and reliability.
problem Variance, bias, and uncertainty in TSFMs' predictions on real data.
method Statistical and ensemble techniques including bagging, stacking, residual modeling, and prediction intervals.
result Hybrid models consistently outperform standalone TSFMs across multiple horizons.
This work explains how large neural networks generalize well despite overparameterization.
problem Understanding the generalization behavior of large neural networks.
method Theoretical analysis of approximation and generalization errors in regression and classification tasks.
result Deep overparameterized neural networks are statistically consistent across different tasks when regularization is applied.
Paper introduces statistical learning for point processes.
problem Statistical learning for point processes in general spaces.
method Combines bivariate innovations and point process cross-validation.
result Statistical learning approach outperforms state of the art.
Consistently checking the statistical significance of experimental results is one of the mandatory methodological steps to address the so-called "reproducibility crisis" in deep reinforcement learning. In this tutorial paper, we explain how the number of random seeds relates to the probabilities of statistical errors. …
A research frontier has emerged in scientific computation, wherein numerical error is regarded as a source of epistemic uncertainty that can be modelled. This raises several statistical challenges, including the design of statistical methods that enable the coherent propagation of probabilities through a (possibly dete…
Study problem-dependent rates in statistical learning theory, achieving optimal generalization error bounds.
problem Generalization error in statistical learning theory.
method Uniform localized convergence framework.
result Optimal generalization error bounds for various learning problems.
This work presents a technique for statistically modeling errors introduced by reduced-order models. The method employs Gaussian-process regression to construct a mapping from a small number of computationally inexpensive `error indicators' to a distribution over the true error. The variance of this distribution can be…
TCE measures calibration error with a test-based approach.
problem Measuring calibration error of probabilistic binary classifiers.
method TCE uses a novel loss function based on a statistical test.
result TCE offers clear interpretation, consistent scale, and enhanced visual representation.
The paper offers error bounds for quantized dynamical models.
problem Accuracy of dynamical models from dependent data sequences.
method Developed uniform error bounds for quantized models and imperfect optimization algorithms.
result Unified bounds for slow and fast rates, scaling with model encoding bits.
We derive formulas for F measures' standard error and confidence intervals.
problem Estimating F measures' accuracy with confidence.
method Analytic formulas based on asymptotic normality.
result Valid formulas for sample size planning.
WAEs offer a statistical understanding of density estimation and error bounds.
problem Concurrent density estimation with neural network-induced transformations.
method Statistical analysis of WAEs focusing on upper bounds and error propagation.
result Established deterministic upper bounds on WAE errors and explored their resilience.
Efficiently estimates private least squares with linear error growth.
problem Private estimation of ordinary least squares with bounded residuals and leverage.
method Scaled noise added to a stable nonprivate estimator of the regression vector.
result Near-optimal accuracy guarantee with linear error growth in dimension.
We develop a communication-efficient distributed learning algorithm that is robust against Byzantine worker machines. We propose and analyze a distributed gradient-descent algorithm that performs a simple thresholding based on gradient norms to mitigate Byzantine failures. We show the (statistical) error-rate of our al…
Overrides of credit ratings are important correctives of ratings that are determined by statistical rating models. Financial institutions and banking regulators agree on this because on the one hand errors with ratings of corporates or banks can have fatal consequences for the lending institutions and on the other hand…
New algorithm estimates transport maps with nearly optimal error.
problem Estimating smooth transport maps efficiently and accurately.
method Solving semi-dual formulation of optimal transport with kernel sums-of-squares.
result Statistical L2 error on maps nearly matches minimax lower-bounds. Measurement error in the observed values of the variables can greatly change the output of various causal discovery methods. This problem has received much attention in multiple fields, but it is not clear to what extent the causal model for the measurement-error-free variables can be identified in the presence of meas…
The method to derive uniform bounds with Gaussian and Rademacher complexities is extended to the case where the sample average is replaced by a nonlinear statistic. Tight bounds are obtained for U-statistics, smoothened L-statistics and error functionals of l2-regularized algorithms.
New method reveals good classifiers are common in over-parameterized models.
problem Understanding how over-parameterized models generalize well.
method Developed a methodology to compute the full distribution of test errors.
result Test errors concentrate around a small typical value ε* rather than the worst-case model.
In this paper, we consider the problem of column subset selection. We present a novel analysis of the spectral norm reconstruction for a simple randomized algorithm and establish a new bound that depends explicitly on the sampling probabilities. The sampling dependent error bound (i) allows us to better understand the …
In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithm…
Optimal kernel improves estimation accuracy in modal statistical methods.
problem Estimation accuracy of kernel-based modal statistical methods depends on the kernel used.
method The study theoretically shows an optimal kernel that minimizes asymptotic error criterion.
result An optimal kernel minimizes the error criterion when using an optimal bandwidth.
New findings challenge the traditional U-shaped curve of model complexity and error, revealing a second descent in error as model size increases.
problem The traditional U-shaped curve of model complexity and prediction error is incomplete, with recent work suggesting a second descent in error as model size increases.
method Careful consideration of multiple complexity axes and a nonparametric statistics perspective were used to interpret the observed double descent curves.
result The observed double descent curves in classical statistical machine learning methods fold back into traditional convex shapes, resolving tensions with statistical intuition.