Post-processing predictors reduces calibration errors for decision-making.
problem Predictors with low calibration error for machine learning may have high error for decision-making.
method Post-processing with ε distance to calibration adds noise to make predictions differentially private.
result Post-processing achieves O(√ε) ECE and CDL, asymptotically optimal.
Adversarial training achieves optimal test error for shallow networks.
problem Achieving optimal adversarial test error for general data distributions.
method Applying new Rademacher complexity bounds and properties of optimal adversarial predictors.
result Adversarial training can achieve optimal adversarial test error for general data distributions.
The paper explores why a specific type of predictor works well in noisy data.
problem Understanding why a specific type of predictor (minimum-norm interpolator) works well in noisy data.
method The paper uses uniform convergence and zero-error predictors in a norm ball to explain the success of the minimum-norm interpolator.
result The minimum-norm interpolator is consistent, and this can be explained by uniform convergence of zero-error predictors in a norm ball.
New method reduces generalization error for interpolating predictors.
problem Understanding and reducing generalization error for predictors that interpolate training data.
method Derandomization and conditional distribution to control generalization error.
result Surrogates constructed by conditioning and denoising have uniformly small generalization error.
New truthful calibration errors improve model ranking in multiclass prediction.
problem Non-truthful calibration errors can mislead model comparisons.
method Introduced perfectly truthful calibration errors for multiclass predictions.
result Truthful calibration errors preserve decision-theoretic dominance and stabilize model rankings.
Neural CDEs correct errors in learned time-series models for better forecasting.
problem Error accumulation in multi-step forecasts of learned time-series models.
method Predictor-Corrector framework with a neural controlled differential equation.
result The proposed framework consistently improves forecasting performance across various models.
The problem of forecasting conditional probabilities of the next event given the past is considered in a general probabilistic setting. Given an arbitrary (large, uncountable) set C of predictors, we would like to construct a single predictor that performs asymptotically as well as the best predictor in C, on any data.…
Efficiency criteria improve conformal predictors' performance.
problem Improving the performance of conformal predictors.
method Learning classifiers by minimizing observed fuzziness as a training objective function.
result Conformal predictors trained by minimizing observed fuzziness perform better than traditional ones.
Simple algorithm achieves distance to calibration error of at most 2√T+1.
problem Achieving distance to calibration error of O(√T) in adversarial setting.
method An extremely simple, efficient, deterministic algorithm.
result Obtains distance to calibration error at most 2√T+1.
New methods for CI testing under model misspecification.
problem Challenges in CI testing with misspecified models.
method Proposes new approximations and upper bounds for testing errors of regression-based CI tests.
result Introduces the Rao-Blackwellized Predictor Test (RBPT) robust against misspecified inductive biases.
This work precisely characterizes and improves the tradeoff between robustness and accuracy in linear regression.
problem Tradeoff between robustness and accuracy in adversarial training.
method Characterizes the effect of augmentation on standard error in linear regression; proves RST improves robust error without sacrificing standard error.
result RST improves both standard and robust error for neural networks under various perturbations.
A new Bayesian approach to linear system identification has been proposed in a series of recent papers. The main idea is to frame linear system identification as predictor estimation in an infinite dimensional space, with the aid of regularization/Bayesian techniques. This approach guarantees the identification of stab…
RF models implicitly regularize kernel methods as feature count increases.
problem Understanding implicit regularization in RF models.
method Random matrix theory applied to Gaussian RF models and KRR.
result The average RF predictor is close to a KRR predictor with an effective ridge.
We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, o…
We introduce a new approach to variable selection, called Predictive Correlation Screening, for predictor design. Predictive Correlation Screening (PCS) implements false positive control on the selected variables, is well suited to small sample sizes, and is scalable to high dimensions. We establish asymptotic bounds f…
Approximate computing is being considered as a promising design paradigm to overcome the energy and performance challenges in computationally demanding applications. If the case where the accuracy can be configured, the quality level versus energy efficiency or delay also may be traded-off. For this technique to be use…
New bounds show linear predictors rarely overfit with certain optimization methods.
problem Bounding test error for linear predictors with stochastic optimization methods.
method Coupling argument for fixed point methods like stochastic and batch mirror descent.
result Locally-adapted rates that depend on predictor properties, not global problem structure.
New robust estimator improves variable selection and coefficient estimation in linear regression with heavy-tailed errors and outliers.
problem Heavy-tailed errors and anomalous predictors in high-dimensional regression.
method Adaptive PENSE estimator for robust variable selection and estimation.
result Adaptive PENSE estimator provides reliable results even under very heavy-tailed errors and aberrant predictors.
New theory explains how noisy, high-dimensional data can still lead to robust predictions.
problem Modern machine learning models achieve high performance with noisy, high-dimensional data.
method Synthesizes principles from Information Theory, Latent Factor Models, and Psychometrics to clarify predictive robustness.
result Predictive robustness arises from data architecture and model capacity, not just data cleanliness.
PredictaBoard benchmarks LLM score predictors to assess their ability to anticipate errors.
problem Inconsistent performance of LLMs in common sense reasoning tasks.
method Collaborative benchmarking framework evaluating pairs of LLMs and assessors using rejection rate at different tolerance errors.
result Highlights the need to evaluate predictability alongside performance for safer AI systems.
Deep neural networks estimate regression functions on manifolds.
problem Estimating regression functions on manifolds from data.
method Fully connected deep neural networks with ReLU activation, analyzing convergence rates.
result Estimates achieve a rate of convergence dependent on manifold dimension, not predictor dimension.
Paper proposes a sparse synthetic control method to select important predictors.
problem Choosing and weighting predictors affects synthetic control estimator performance.
method Sparse synthetic control procedure that penalizes predictors, derived in a linear factor model.
result Sparse synthetic control achieves lower bias and better post-treatment performance.
New loss function reduces outage probability in ML-assisted resource allocation.
problem Minimizing outage probability in ML-assisted resource allocation systems.
method Developed a novel loss function and trained an ML model to address the outage probability challenge.
result Exact and asymptotic expressions for the system's outage probability were established.
Gradient methods avoid overfitting on separable data.
problem Overfitting on separable data with gradient methods.
method Gradient methods (flow, descent, SGD) on separable data.
result Gradient methods asymptotically do not overfit on separable data.
Empirically, the PAC-Bayesian analysis is known to produce tight risk bounds for practical machine learning algorithms. However, in its naive form, it can only deal with stochastic predictors while such predictors are rarely used and deterministic predictors often performs well in practice. To fill this gap, we develop…
Multiclass prediction is the problem of classifying an object into a relevant target class. We consider the problem of learning a multiclass predictor that uses only few features, and in particular, the number of used features should increase sub-linearly with the number of possible classes. This implies that features …
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, …
Predict accuracy of neural architectures using non-neural models.
problem Improving efficiency and effectiveness of neural architecture search.
method Used gradient boosting decision tree (GBDT) for accuracy prediction and pruned the search space based on features learned from GBDT.
result GBDT-based predictor achieves comparable or better accuracy than neural network-based predictors and is 22x more sample efficient on NASBench-101.
Mack's estimator improves chain ladder prediction for large exposure insurance models.
problem Uncertainty quantification in compound Poisson loss models.
method Large exposure asymptotics applied to Mack's estimator.
result Chain ladder prediction uncertainty can be quantified without model assumptions.
Proposes a method to learn fair predictors for multiple subgroups with limited data.
problem Fairness and accuracy issues in learning from multiple subgroups with limited data.
method Formulates a bilevel objective to learn subgroup-specific predictors and a fair predictor that is close to all of them.
result The method effectively controls group sufficiency and generalization error, improving fairness and accuracy.
The paper proposes multicalibration to improve matching in graphs with imperfect predictors.
problem Finding the best matching in graphs with imperfect predictors.
method Introduces multicalibration as a fairness notion to ensure unbiasedness on protected sets of contexts.
result Constructing a multicalibrated predictor that outperforms standard optimal rules in matching algorithms.
While the use of deep learning in drug discovery is gaining increasing attention, the lack of methods to compute reliable errors in prediction for Neural Networks prevents their application to guide decision making in domains where identifying unreliable predictions is essential, e.g. precision medicine. Here, we prese…
It is widely believed that the prediction accuracy of decision tree models is invariant under any strictly monotone transformation of the individual predictor variables. However, this statement may be false when predicting new observations with values that were not seen in the training-set and are close to the location…
Study fairness in ordinal regression using threshold models.
problem Fairness in ordinal regression predictions.
method Adapted fairness notions from fair ranking; use threshold model with scoring function and thresholds; apply binary classification for scoring function and local search for thresholds.
result Generalization guarantees on predictor error and fairness violation; effectiveness demonstrated in experiments.
DynForest R package predicts outcomes with time-dependent predictors.
problem Handling time-dependent predictors in random forest models.
method Random forests with time-dependent predictors summarized using flexible linear mixed models.
result DynForest can predict continuous, categorical, and survival outcomes.
Study shows gap between uniform convergence and test error in random feature models.
problem Understanding the gap between uniform convergence and test error in random feature models.
method Analytical expressions for uniform convergence over norm balls, interpolators, and minimum norm interpolator risk derived and proved.
result Uniform convergence over interpolators still gives a non-trivial bound of test error even when classical uniform convergence is vacuous.
Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set labels. Motivated by medical diagnosis, where diseases (targets) cause symptoms (observations), we focus on label shift, where the label marginal p(y) changes but the …
Estimates model performance under distribution shift using domain-invariant predictors.
problem Poor performance of models on test distributions different from training distributions.
method Uses domain-invariant predictors as a proxy for unknown target labels.
result Shows that the complexity of latent representations influences target risk.
A new estimator improves financial econometrics by providing reliable inference.
problem Poor performance of standard regression methods in financial economics with thick-tailed predictors.
method Developed an unbiased, consistent, and asymptotically normal estimator for linear regression.
result The new method delivers reliable inference under heteroskedasticity and quantile regression.
We present a method to stop the evaluation of a prediction process when the result of the full evaluation is obvious. This trait is highly desirable in prediction tasks where a predictor evaluates all its features for every example in large datasets. We observe that some examples are easier to classify than others, a p…
In this article, we derive concentration inequalities for the cross-validation estimate of the generalization error for stable predictors in the context of risk assessment. The notion of stability has been first introduced by \cite{DEWA79} and extended by \cite{KEA95}, \cite{BE01} and \cite{KUNIY02} to characterize cla…
Autoencoder performance is predicted by eigenvalues of weight matrices.
problem Predicting an autoencoder's generalization ability without dataset knowledge.
method Analyze Jacobian matrices' eigenvalues to bound mean squared errors.
result Eigenvalues are good predictors of MSE on test points.
A hybrid Convolutional VAE predicts crypto volatility surfaces, outperforming single-symbol approaches.
problem Predicting crypto volatility surfaces
method Convolutional VAE with hybrid predictor
result Model achieves 0.94-1.56 vol-point RMSE across BTC and ETH markets
We study online linear regression problems in a distributed setting, where the data is spread over a network. In each round, each network node proposes a linear predictor, with the objective of fitting the \emph{network-wide} data. It then updates its predictor for the next round according to the received local feedbac…
New bounds prevent degradation in high-dimensional signal estimation.
problem Statistical learning bounds degradation with increasing dimensionality.
method Investigates linear prediction rules under structural assumptions.
result Derives upper and lower bounds on generalization error.
We introduce a computationally effective algorithm for a linear model selection consisting of three steps: screening--ordering--selection (SOS). Screening of predictors is based on the thresholded Lasso that is l_1 penalized least squares. The screened predictors are then fitted using least squares (LS) and ordered wit…
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.
Bayesian model averaging under predictor redundancy
problem Reporting Bayesian model averaging posterior without changing the Bayesian target
method Using hard or soft regions of support space
result Region reports often give shorter and clearer summaries while preserving the main posterior information