The paper improves prediction intervals for non-parametric regression using histograms.
problem Computing accurate prediction intervals for non-parametric regression models.
method Uses conditional histograms to estimate conditional distributions and compute shortest prediction intervals.
result The method provides prediction intervals with provable marginal coverage and asymptotic conditional coverage.
Optimizes predictions for specific tasks using parametrized decision analysis.
problem Optimizing predictions for specific decision tasks of interest.
method Designs a class of parametrized actions for Bayesian decision analysis.
result Derives efficient and interpretable solutions for various action parametrizations and loss functions.
Non-parametric time series forecasting without assuming a specific distribution.
problem Time series forecasting with numerical stability issues in classical models.
method Generates predictions by sampling from the empirical distribution of time series data.
result The proposed method produces reasonable forecasts without numerical stability issues.
Paper proposes a new time series prediction method using weighted past data and optimization.
problem Predicting time series data with improved accuracy considering both deterministic and stochastic assumptions.
method The approach uses a weighted sum of past data, solving a constrained linear optimization problem to minimize an outer bound of prediction error.
result The method can outperform existing non-parametric methods in short-term forecasts.
SurvMixClust clusters survival data and predicts individual survival curves.
problem Integrating clustering into survival analysis for precision medicine.
method SurvMixClust learns latent representations for clustering and predicts survival functions using a mixture of non-parametric experts.
result SurvMixClust creates balanced clusters with distinct survival curves, outperforming clustering baselines and competing with non-clustering models in predictive accuracy.
Paper develops a method to predict cancer patient survival using molecular profiles.
problem Accurately predicting cancer patient survival with complex survival-molecular profile relationships.
method Kernel Cox partially linear regression with a novel regularized garrotized kernel machine (RegGKM) method.
result The proposed method outperforms other methods in predicting survival accuracy.
Unified review of Conformal Prediction theory and applications.
problem Distribution-free, non-parametric forecasting method for valid prediction sets.
method Minimal assumptions, straightforward predictions sets valid in finite sample cases.
result Unified review of Conformal Prediction theory and applications.
ARX models predict thermal behavior of WBG semiconductors accurately.
problem Thermal management challenges of WBG semiconductors.
method Use of ARX parametric models based on experimental measurements.
result ARX models provide accurate temperature predictions without detailed component information.
Modeling structure in complex networks using Bayesian non-parametrics makes it possible to specify flexible model structures and infer the adequate model complexity from the observed data. This paper provides a gentle introduction to non-parametric Bayesian modeling of complex networks: Using an infinite mixture model …
New deep learning model uses self-attention to consider entire dataset for predictions.
problem Traditional deep learning models focus on single input datapoints; this model considers the whole dataset.
method Introduces self-attention mechanism to reason about relationships between datapoints.
result Models solve cross-datapoint lookup and complex reasoning tasks.
Develops a calibration prediction interval for non-parametric regression and neural networks.
problem Lack of accurate conditional prediction in regression settings.
method Calibration Prediction Interval (cPI) using Deep Neural Networks (DNN) or kernel methods.
result Asymptotically valid coverage rate and high probability of coverage rate with large sample sizes.
Develops a new model for network estimation from multi-variate data.
problem Network estimation from multi-variate point process or time series data.
method Semi-parametric approach based on the monotone single-index multi-variate autoregressive model (SIMAM).
result Achieves optimal rates of convergence and superior performance in prediction and network estimation.
Having a regression model, we are interested in finding two-sided intervals that are guaranteed to contain at least a desired proportion of the conditional distribution of the response variable given a specific combination of predictors. We name such intervals predictive intervals. This work presents a new method to fi…
FastMuyGPs speeds up GP predictions for large datasets.
problem High cost of Gaussian process predictions for large data.
method Combines cross-validation, batching, nearest neighbors sparsification, and precomputation.
result Superior accuracy and competitive runtime compared to other methods.
Generalizes prediction-powered inference for binary classifier evaluation.
problem Evaluation of binary classifiers with partially observed outcomes.
method Generalizes PPI to any regular asymptotically linear estimator and proposes modified estimators for covariate shift.
result PPI can be a computationally-simple alternative to existing methods, achieving no greater than the semi-parametric efficiency lower bound in certain scenarios.
A deep learning method for regression without model assumptions.
problem Regression prediction without model specification.
method Deep Neural Network (DNN) for point and interval prediction.
result The method outperforms other DNN-based alternatives in stability and accuracy.
A new emulator connects observables directly from data.
problem Constructing fast and accurate surrogate models for robust predictions.
method Introduces Multiparameter Eigenvalue Problem (MEP) emulator trained with Eigenvector Continuation (EC) and Parametric Matrix Model (PMM) data.
result The MEP emulator can make predictions directly from observables to observables.
Study shows improper learning can outperform proper learning in misspecified models.
problem Misspecification in probabilistic prediction models.
method Investigates the performance of proper and improper learning strategies in misspecified models.
result Improper learning can achieve lower regret compared to proper learning, especially in high-dimensional settings.
Flexible spatial models improve predictive performance over nonstationary alternatives.
problem Improving predictive performance in nonstationary spatial modeling.
method Introduces a modular parametric covariance function that extends nonstationary spatial models.
result The proposed covariance function outperforms nonparametric methods in predictive performance.
Extends Demographic Parity for fairer wage predictions with expert knowledge.
problem Inadequate fairness metrics limit user domain knowledge and ignore intersectional fairness.
method Develops a parametric method to incorporate expert knowledge in fair predictions.
result Offers a robust solution for real-life applications with limited data and spending constraints.
SCIENCE improves prediction intervals for individual causal effects.
problem Wide prediction intervals limit practical utility of causal inference.
method Surrogate-assisted conformal inference for efficient individual causal effects.
result SCIENCE produces more efficient prediction intervals for individual causal effects.
A method for non-parametric conditional distribution estimation using CRPS-optimal binning.
problem Non-parametric conditional distribution estimation.
method Partitioning covariate-sorted observations into bins to minimize LOO-CRPS, selecting K by K-fold cross-validation of test CRPS.
result Produces narrower prediction intervals with near-nominal coverage compared to split-conformal competitors.
TabSurv adapts tabular neural networks for survival analysis.
problem Survival analysis on tabular data using deep learning methods.
method Adapts modern tabular architectures to survival analysis using Weibull distribution or non-parametric prediction. Optimizes SurvHL histogram loss function.
result TabSurv consistently outperforms classical and deep learning baselines on 10 real-world survival datasets.
Random Forests provide interpretable prediction intervals with theoretical guarantees.
problem Lack of uncertainty estimates in machine learning point predictions.
method Out-of-Bag procedure for generating parametric and non-parametric prediction intervals.
result Proposed prediction intervals deliver correct coverage rates and narrow lengths.
Random forest (RF) methodology is one of the most popular machine learning techniques for prediction problems. In this article, we discuss some cases where random forests may suffer and propose a novel generalized RF method, namely regression-enhanced random forests (RERFs), that can improve on RFs by borrowing the str…
New measure assesses predictive dependence between continuous variables, capturing non-functional relationships.
problem Quantifying the joint dependence between continuous random variables.
method Introduces a novel, fully non-parametric measure bounded [0,1] that assesses predictive accuracy loss.
result The measure captures a wide range of relationships, including non-functional ones, and is interpretable.
Neural network predicts electrochemical cell faults with 53% less error.
problem Predicting faults in electrochemical cells to avoid safety hazards and reduce costs.
method Self-supervised encoder-decoder neural network that learns degradation from operating conditions.
result Predicted voltage with 53% less error than parametric models, 64% faster fault prediction.
Treeffuser predicts tabular data distributions using gradient-boosted trees.
problem Probabilistic prediction with flexible, non-parametric models.
method Gradient-boosted trees for score estimation in conditional diffusion model.
result Treeffuser outperforms existing methods in probabilistic prediction tasks.
Optimizes prediction error method for time-varying models.
problem Achieving optimal prediction error rates for time-varying models.
method Nonlinear least squares method for time-varying parametric models.
result First rate-optimal non-asymptotic analysis for time-varying models.
This paper explores how to choose scoring rules for estimating properties with parametric assumptions.
problem Indirect elicitation of properties with parametric assumptions.
method Developed a framework for choosing proper scoring rules for indirect elicitation, considering constraints and optimal solutions.
result The optimal estimation of the target property changes monotonically with the increase of each weight, and often setting some weights as zero yields the best configuration.
GAM(L)A model improves interpretability of machine learning models.
problem Interpretable machine learning models for high predictive performance.
method Combines partial linear models with variable selection for accurate prediction and interpretability.
result GAM(L)A outperforms parametric models and is comparable to black-box models like random forest and gradient boosting.
Differentiable cutting-plane layers solve parametric mixed-integer linear optimization problems.
problem Solving parametric mixed-integer linear optimization problems with changing data.
method Introducing cutting-plane layers (CPLs) for differentiable cutting-plane generation.
result The algorithm computes solutions with low integrality gaps and generalizes to unseen instances.
A new method uses RF's out-of-bag errors for multiple imputation.
problem Missing data in biomedical studies and lack of prediction uncertainty.
method Constructs conditional distributions from the empirical distribution of out-of-bag prediction errors.
result Valid multiple imputation results achieved without parametric assumptions.
Paper introduces a novel framework for supervised graph prediction using Optimal Transport.
problem Supervised labeled graph prediction.
method Fused Gromov-Wasserstein (FGW) loss and FGW barycenter with neural network weights and learned graphs.
result The method can interpolate in the labeled graph space and achieve good performance on difficult problems.
In this paper, we propose a non-parametric conditional factor regression (NCFR)model for domains with high-dimensional input and response. NCFR enhances linear regression in two ways: a) introducing low-dimensional latent factors leading to dimensionality reduction and b) integrating an Indian Buffet Process as a prior…
We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, including the ability to plan…
We study online prediction of bounded stationary ergodic processes. To do so, we consider the setting of prediction of individual sequences and build a deterministic regression tree that performs asymptotically as well as the best L-Lipschitz constant predictors. Then, we show why the obtained regret bound entails the …
Proposes spBART for risk prediction using epigenetic signatures and covariates.
problem Complex high-dimensional epigenetic data and low-dimensional covariates for risk prediction.
method Semi-parametric Bayesian Additive Regression Trees (spBART) with cross-validation for variable selection.
result Achieves strong out-of-sample discrimination (AUC = 0.96) in held-out validation set.
A set of probabilistic predictions is well calibrated if the events that are predicted to occur with probability p do in fact occur about p fraction of the time. Well calibrated predictions are particularly important when machine learning models are used in decision analysis. This paper presents two new non-parametric …
Unbiased gradient estimation for Markov chains
problem Estimating gradients of stationary means in Markov chains
method Propose new unbiased estimators
result Improves efficiency for slow mixing Markov chains
New methods using vine copulas improve accuracy of feature dependence in predictive models.
problem Inaccurate feature dependence assumptions in Shapley values lead to incorrect explanations.
method Proposed two new approaches based on vine copulas to model feature dependence.
result Vine copula approaches give more accurate approximations to true Shapley values.
Bayesian framework for semiparametric regression of discrete data.
problem Complex distributional features of discrete data.
method Semiparametric modeling with nonparametric marginal and latent linear regression.
result Posterior consistency and analytical/posterior predictive distributions.
New method estimates survival risks without strong proportional hazard assumptions.
problem Time-to-event prediction with censored data and competing risks.
method Jointly learns deep nonlinear representations for fully parametric survival regression.
result Demonstrates benefits in real-world datasets with different censoring levels.
This research adapts scoring rules for training survival models, improving predictive performance.
problem Training survival models with traditional methods struggles with censoring.
method Adapting scoring rules for survival analysis, creating a flexible framework for model training.
result Scoring rules can be successfully incorporated into model training, yielding competitive performance.
IQ-BART models conditional quantiles using a non-parametric Bayesian approach.
problem Capturing multimodal predictive distributions in time series forecasting.
method Implicit Quantile BART (IQ-BART) augments data with quantile values for non-parametric quantile function estimation.
result IQ-BART provides flexible distribution-free regression with theoretical guarantees.
New model solves PDEs using probabilistic random grids.
problem Solving parametric PDEs with probabilistic collocation grids.
method Random Grid Neural Processes (RGNPs) with GICNets.
result Significant computational advantages and improved predictive capabilities.
Deep neural networks for structured prediction using kernel-induced losses.
problem Structured prediction tasks for images and texts.
method Designing a novel family of deep neural architectures that predict in a finite-dimensional subspace derived from the kernel-induced loss.
result Gradient descent algorithms can be used for structured prediction with deep neural networks.
This paper studies the effect of discretizing the parametrization of a dictionary used for Matching Pursuit decompositions of signals. Our approach relies on viewing the continuously parametrized dictionary as an embedded manifold in the signal space on which the tools of differential (Riemannian) geometry can be appli…