Researchers study fairness-accuracy tradeoffs in predictive models for multiple groups.
problem Understanding the tradeoff between fairness and accuracy in models serving multiple demographic groups.
method Characterizing the fairness-accuracy (FA) Pareto frontier, approximating it from limited data, and bounding the worst-case gap.
result Derivation of worst-case-optimal estimators and uniform finite-sample bounds for the entire FA frontier.
Develops a fast, accurate method for comparing networks.
problem Comparing networks with repeated observations and varying sizes/sparsity.
method A novel two-sample hypothesis testing method with theoretical guarantees.
result Outperforms existing tools in speed and accuracy, power-optimal.
In risk management, tail risks are of crucial importance. The assessment of risks should be carried out in accordance with the regulatory authority's requirement at high quantiles. In general, the underlying distribution function is unknown, the database is sparse, and therefore special tail models are used. Very often…
Unified method for MMD variance estimation improves accuracy and computational efficiency.
problem Variance estimation for MMD in nonparametric testing.
method Unified finite-sample characterization of MMD variance through U-statistic and Hoeffding decomposition; exact acceleration method for univariate case.
result Unified estimators improve accuracy and computational efficiency for MMD variance.
FaiREE provides fair classification with guarantees for small datasets.
problem Fairness in classification often requires large sample sizes and distributional assumptions.
method FaiREE offers finite-sample and distribution-free fairness guarantees.
result FaiREE achieves optimal accuracy and satisfies various fairness notions.
Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we address this problem by providing a finite-sample analysis for decentralized batch MARL with networked agents…
Paper presents robust boosting methods for label noise.
problem Boosting methods degrade in noisy environments.
method Robust Minimax Boosting (RMBoost) with theoretical guarantees.
result RMBoost provides strong classification accuracy and robustness.
The paper investigates topic models, ensuring their statistical identifiability and accuracy.
problem Lack of formal theoretical investigation of topic model identifiability and estimation accuracy.
method Proposes a maximum likelihood estimator (MLE) based on integrated likelihood, introducing new geometric identifiability conditions.
result Introduces weaker conditions for topic model identifiability, allowing a broader investigation.
Efficiently learns polytrees with known skeleton in polynomial time and sample complexity.
problem Learning polytrees with known skeleton structure.
method Proposes an efficient algorithm for learning d-polytrees in polynomial time and sample complexity when the skeleton is known. result Establishes finite-sample guarantees for efficient learning of d-polytrees. Deep learning method improves regression accuracy.
problem Nonparametric regression challenges.
method Over-parametrized deep neural networks with logistic activation, gradient descent, special topology, random initialization, and data-dependent learning rate.
result Theoretical bound on L2 error and improved finite sample performance. Novel AMP framework for multi-environment transfer learning.
problem Characterizing risk of Lasso-based transfer learning estimators.
method Multi-Environment Generalized Long AMP (multi-environment GLAMP) framework.
result Precise characterization of the risk of three Lasso-based transfer learning estimators.
The paper tackles Neyman-Pearson classification control issues.
problem Neyman-Pearson classification's control constraint is hard to satisfy in finite samples.
method Developed refined learning procedures under two accuracy control strategies.
result Proposed methods achieve desired control levels in finite samples.
LGES speeds up causal discovery while maintaining accuracy.
problem Causal discovery from observational data with computational and accuracy limitations.
method LGES modifies GES by avoiding certain edge insertions, using prior knowledge, and leveraging interventional data.
result LGES outperforms GES in speed, accuracy, and robustness to misspecified knowledge.
In the information-based paradigm of inference, model selection is performed by selecting the candidate model with the best estimated predictive performance. The success of this approach depends on the accuracy of the estimate of the predictive complexity. In the large-sample-size limit of a regular model, the predicti…
Estimating the strength of dependency between two variables is fundamental for exploratory analysis and many other applications in data mining. For example: non-linear dependencies between two continuous variables can be explored with the Maximal Information Coefficient (MIC); and categorical variables that are depende…
A conformal procedure improves CoT reasoning by aggregating reasoning paths and calibrating abstention rules.
problem Aggregation uncertainty in chain-of-thought reasoning makes correct answers less reliable.
method Introduces a conformal procedure for CoT reasoning that uses weighted score aggregation and abstention rules.
result Achieves higher selective accuracy with abstention, reducing confident-error rate.
New algorithm improves causal discovery in biomedical data.
problem Stability and accuracy issues in causal discovery algorithms.
method Exploits temporal structure and tiered background knowledge.
result Increases accuracy in finite samples for causal structure estimation.
The paper provides bounds on estimation error in a distributed online learning setting.
problem Estimating an unknown parameter in a distributed and online manner with finite sample guarantees.
method Proposes a distributed online estimation algorithm that improves accuracy through communication, providing non-asymptotic bounds on estimation error.
result Demonstrates a trade-off between estimation error and communication costs, and determines a stopping time for communication based on desired accuracy.
Paper provides unbiased spectral moment estimates from finite data.
problem Challenges in estimating spectral moments from limited data.
method Dynamic programming approach to estimate spectral moments of kernel integral operator.
result Demonstrates consistency with theoretical spectra and practical utility in neural networks.
Study learns convolution operators on compact Abelian groups using regularization.
problem Learning convolution operators on compact Abelian groups.
method Regularization-based approach with ridge regression estimator.
result Characterizes the accuracy of the estimator in terms of finite sample bounds.
The paper proposes a test to assess rater accuracy while accounting for rater covariates.
problem Assessing the accuracy of raters in medical imaging and forensic studies.
method Covariate-adjusted homogeneity test to determine differences in accuracy among multiple rater groups.
result The proposed test identifies statistically significant differences among five participant groups in a face recognition study.
Develops a method to detect changes in linear systems with temporal correlations.
problem Detect abrupt changes in time series data with temporal correlations.
method Data-dependent threshold for online change point detection in linear dynamical systems.
result Achieves a pre-specified upper bound on the probability of false alarms and provides a finite-sample-based bound for detection probability.
VISTA learns causal structures by integrating local subgraphs, improving accuracy and efficiency.
problem Efficiently learning causal structures from high-dimensional observational data.
method VISTA decomposes the global causal structure learning problem into local subgraphs based on Markov Blankets, integrating them via a weighted voting mechanism.
result VISTA achieves notable improvements in accuracy and efficiency over existing methods.
Dual-Channel Tensor Neural Network (DC-TNN) decomposes tensor data into low-rank and sparse components for better estimation and inference.
problem Tensor-valued data with multilinear dependencies are challenging to process due to loss of multiway geometry under vectorization.
method DC-TNN decomposes tensors into a low-rank core and a sparse refinement, processing them through coupled neural channels.
result Established non-asymptotic risk bounds and developed structure-aware conformal ROC and AUC confidence bands.
Paper proposes an alternative to MLE for GLMs with non-canonical link functions.
problem Challenges in MLE for GLMs with non-canonical link functions.
method Variational Inequality (VI) estimation framework.
result Established finite-sample error bounds and asymptotic normality for VI estimator.
Proposes a new method for variable importance using targeted learning.
problem Uncertainty quantification in variable importance metrics.
method Employing the targeted learning (TL) framework for conditional permutation variable importance.
result Improved accuracy in finite sample contexts compared to traditional methods.
Paper introduces a method to control early classification accuracy gaps.
problem Maintaining accuracy in early classification without full input processing.
method Statistical framework for a calibrated stopping rule.
result Reduces up to 94% of timesteps while controlling accuracy gaps.
The paper analyzes LOCV for high-dimensional risk estimation, proving error bounds.
problem Estimating out-of-sample prediction error in high-dimensional settings.
method Theoretical analysis of leave-one-out cross validation (LOCV) in penalized regression.
result Finite sample upper bounds on LOCV error, showing it converges to zero as n,p → ∞.
This paper analyzes momentum Q-learning with finite-sample guarantees.
problem Improving Q-learning performance with momentum schemes.
method Proposes MomentumQ algorithm integrating Nesterov and Polyak's momentum schemes, analyzes convergence for function approximations.
result Establishes finite-sample convergence rates for MomentumQ, demonstrating better performance than vanilla Q-learning.
Neural causal discovery methods fail to accurately uncover causal structures due to the faithfulness property.
problem Accuracy in neural causal discovery is limited, especially when distinguishing between existing and non-existing causal relationships.
method Systematic evaluation of neural causal discovery methods, focusing on their performance in finite sample regimes and their ability to recover ground-truth graphs.
result Neural networks lack the precision to reliably recover ground-truth causal graphs, even for small graphs and large sample sizes.
Study improves understanding of non-differentiable penalties in high-dimensional settings.
problem Theoretical understanding of non-differentiable penalties like generalized LASSO and nuclear norm in high-dimensional settings.
method Proportional high-dimensional regime analysis with finite sample upper bounds on expected squared error.
result LO provides accurate estimation of out-of-sample risk in high-dimensional settings.
Estimates path-valued data using signature metrics and local kernels.
problem Nonparametric regression and classification for path-valued data.
method Combines signature transform and local kernel regression.
result Establishes convergence bounds and demonstrates competitive accuracy.
Enhances survival analysis predictions with a robust learning approach.
problem Improving robustness and accuracy in survival analysis predictions.
method Integrates Distributionally Robust Learning (DRL) into Cox regression using Wasserstein distance-based ambiguity set.
result Demonstrates superior performance in prediction accuracy and robustness compared to traditional methods.
Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.
problem Analyzing Greedy-GQ for reinforcement learning with Markovian noise.
method Develops finite-sample analysis for Greedy-GQ with linear function approximation under Markovian noise.
result Provides theoretical justification for choosing stepsizes for faster convergence.
Cross validation (CV) and the bootstrap are ubiquitous model-agnostic tools for assessing the error or variability of machine learning and statistical estimators. However, these methods require repeatedly re-fitting the model with different weighted versions of the original dataset, which can be prohibitively time-cons…
The paper analyzes GTD algorithms with finite-sample bounds.
problem Convergence rate analysis of GTD family of algorithms.
method Formulated as stochastic gradient algorithms and analyzed using saddle-point error.
result Obtained finite-sample bounds on GTD performance.
We show that a simple modification of the 1-nearest neighbor classifier yields a strongly Bayes consistent learner. Prior to this work, the only strongly Bayes consistent proximity-based method was the k-nearest neighbor classifier, for k growing appropriately with sample size. We will argue that a margin-regularized 1…
Matrix completion is the problem of recovering a low rank matrix by observing a small fraction of its entries. A series of recent works [KOM12,JNS13,HW14] have proposed fast non-convex optimization based iterative algorithms to solve this problem. However, the sample complexity in all these results is sub-optimal in it…
New findings show modern neural networks have finite sample complexity in o-minimal structures.
problem Understanding the learnability of modern neural networks in a broad context.
method Analyzing feedforward neural networks definable in o-minimal structures.
result Modern neural networks, including MLPs, CNNs, GNNs, and transformers, have finite sample complexity in the agnostic PAC setting.
Estimates barycenter in geodesic spaces with finite sample bounds.
problem Estimating the barycenter of a distribution in geodesic spaces.
method Finite sample error bounds, Hoeffding- and Bernstein-type concentration inequalities, efficient algorithms.
result Statistical guarantees for efficient barycenter computation.
The most important aspect of any classifier is its error rate, because this quantifies its predictive capacity. Thus, the accuracy of error estimation is critical. Error estimation is problematic in small-sample classifier design because the error must be estimated using the same data from which the classifier has been…
New methods for estimating causal effects with limited overlap, using Stable Probability Weighting.
problem Estimating causal effects with limited overlap in multivalued treatments.
method Stable Probability Weighting (SPW) and Finite-Sample Stable Probability Weighting (FPW) methods.
result SPW and FPW provide practical solutions for estimating and inferring causal effects with limited overlap.
New algorithms optimize metrics for binary classification with class imbalance.
problem Optimizing metrics like Fβ, AM, Jaccard for imbalanced classes.
method Reformulates metric optimization as cost-sensitive learning, using surrogate loss functions.
result METRO algorithms provide strong theoretical guarantees and outperform baselines.
We study the accuracy of estimating the covariance and the precision matrix of a D-variate sub-Gaussian distribution along a prescribed subspace or direction using the finite sample covariance. Our results show that the estimation accuracy depends almost exclusively on the components of the distribution that correspo…
New bounds for LDP with heterogeneous privacy levels guaranteeing high probability of accuracy.
problem Statistical estimation under LDP with users having varying privacy levels.
method Developed finite sample upper bounds in ℓ_2-norm with high probability, complemented by lower bounds.
result Optimal guarantees for heterogeneous LDP in terms of probability and constants.
BPR matches NN accuracy in crop classification while being more transparent.
problem Lack of auditability and alignment with domain knowledge in neural networks for high-dimensional climate data.
method Bagged polynomial regression with random projections (BPR), averaging many low-degree polynomial models.
result BPR matches neural networks in accuracy but is more transparent.
The paper shows how to learn causal representations with few environments and finite samples.
problem Learning causal representations from limited data and environments.
method Explicit, finite-sample guarantees with a logarithmic number of interventions.
result Consistent recovery of latent causal graph, mixing matrix, and unknown intervention targets.
Paper improves ML estimation from incomplete data with robust M-estimator.
problem Estimating parameters from incomplete data with improved accuracy.
method Developed a robust M-estimator and a sandwich estimator for standard errors.
result Improved estimation accuracy with smaller standard errors than ML estimates.