Study shows interpolating predictor's risk is optimal in low-dimensional factor regression models.
problem Understanding the risk of interpolating predictors in high-dimensional factor regression models.
method Detailed finite-sample analysis of minimum-norm interpolating predictor's risk in factor regression models.
result The risk of the minimum-norm interpolating predictor approaches optimal benchmarks in low-dimensional factor regression models.
A new method controls risk for set predictors using cross-validation.
problem Inefficient set predictors when data limited.
method Cross-validation conformal risk control (CV-CRC).
result CV-CRC offers theoretical guarantees and reduces set size.
Study tail risk in high-frequency finance using L1-regularized regression.
problem Measuring tail risk dynamics in high-frequency financial markets.
method Dynamic extreme value regression model with L1-regularized maximum likelihood estimator. result Severity of extreme losses well predicted by low price impact in high volatility periods.
Develops a SAS approach for high-dimensional risk prediction using unlabeled data.
problem Challenges in risk modeling with EHR data due to lack of direct disease outcomes and high dimensionality.
method Surrogate Assisted Semi-supervised Learning (SAS) approach leveraging unlabeled and labeled data.
result Valid inference for predicted risk even when underlying model is dense and mis-specified.
Several well-established benchmark predictors exist for Value-at-Risk (VaR), a major instrument for financial risk management. Hybrid methods combining AR-GARCH filtering with skewed-t residuals and the extreme value theory-based approach are particularly recommended. This study introduces yet another VaR predictor, …
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.
This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem. Unlike most previous work, we give results that are general enough to include cases in which no minimum exists, as occurs typically, for in…
The paper analyzes bagging in overparameterized learning, deriving risk properties and optimal subsample sizes.
problem Characterizing the risk of bagged predictors in overparameterized settings.
method General strategy using classical results on simple random sampling, specialized for ridge and ridgeless predictors.
result Derives exact asymptotic risk of bagged ridge and ridgeless predictors under various conditions.
We study the task of learning from non-i.i.d. data. In particular, we aim at learning predictors that minimize the conditional risk for a stochastic process, i.e. the expected loss of the predictor on the next point conditioned on the set of training samples observed so far. For non-i.i.d. data, the training set contai…
Proposes a new probabilistic framework for domain generalization.
problem Learning predictors robust to unseen domain shifts.
method Quantile Risk Minimization (QRM) and Empirical QRM (EQRM) algorithms.
result Empirical QRM outperforms state-of-the-art baselines on various datasets.
Optimal trading strategy with predictor and costs, derived equations and shape.
problem Optimal trading strategy in presence of price predictor, costs, and risk control.
method Path-integral method to derive equations for band edges, solved explicitly for Ornstein-Uhlenbeck predictor.
result Explicit equations and shape of the optimal band strategy derived and analyzed.
Least squares estimator fails to achieve optimal risk in bounded distributions, but non-linear predictors can.
problem Optimal risk in bounded distributions for constrained least squares.
method Comparison of least squares and non-linear predictors.
result Non-linear predictors can achieve optimal risk O(d/n) in bounded distributions. 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…
Unified framework certifies predictor performance under distribution shift.
problem Certifying predictor performance under distribution shift.
method Unified framework with explicit inequalities, sound verification, and identifiable structure.
result Explicit upper bound on excess risk under shift.
Optimal multi-asset trading with Markovian predictors is well understood in the case of quadratic transaction costs, but remains intractable when these costs are L1. We present a mean-field approach that reduces the multi-asset problem to a single-asset problem, with an effective predictor that includes a risk avers…
This study analyzes prediction risk for PCR method in latent factor regression models.
problem Prediction risk analysis in latent factor regression models.
method Adaptive PCR method with risk bounds established under factor regression model.
result Unified framework for analyzing various linear prediction methods under factor regression.
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.
Paper presents new training methods for neural networks with tighter risk certificates.
problem Training probabilistic neural networks with tighter risk certificates.
method Derived from PAC-Bayes bounds, two training objectives implemented for the first time in neural networks.
result Competitive test set errors and non-vacuous risk bounds with tighter values than previous results.
Paper introduces SUEL model for integrating predictors without labeled data.
problem Combining predictors with unknown accuracy and high correlation.
method Structured unsupervised ensemble learning (SUEL) with correlation-based decomposition algorithms.
result Efficient integration of dependent predictors without labeled data.
Ensemble methods that average over a collection of independent predictors that are each limited to a subsampling of both the examples and features of the training data command a significant presence in machine learning, such as the ever-popular random forest, yet the nature of the subsampling effect, particularly of th…
Model improves mortgage credit risk prediction with spatio-temporal machine learning.
problem Improving accuracy of default probabilities and loan portfolio loss distributions in mortgage credit risk.
method Combines tree-boosting with a latent spatio-temporal Gaussian process model.
result Predictive models outperform conventional methods due to non-linear and spatio-temporal effects.
Neural network model forecasts extreme flood risk.
problem Accurately estimating high quantiles of extreme events.
method EQRN model combining neural networks and extreme value theory.
result Forecasting flood risk with improved adaptability.
ML helps select variables for minimum-variance portfolios, reducing risk and improving performance.
problem Optimizing minimum-variance portfolios with relevant predictors.
method Parameterized minimum-variance portfolio weights using a large pool of firm-level characteristics and their transformations.
result ML-selected predictors lead to lower risk and better performance in minimum-variance portfolios.
New method refines model-free evaluation of complex machine learning models.
problem Evaluating the excess risk of opaque machine learning predictors.
method Perturbing derivatives to create pseudo-outcomes and refitting the model twice.
result Upper bound on excess risk derived efficiently without prior function class knowledge.
New method uses G-expectation for financial risk measurement.
problem Measuring uncertainty in financial time series.
method Introducing G-normal distribution, applying max-mean estimators, and using autoregressive models.
result G-VaR model outperforms other VaR predictors in risk prediction.
Digital risk scores predict depression and anxiety over 10 years.
problem Identifying individuals at risk of depression and anxiety.
method Developed a 10-year predictive algorithm using UKB cohort, selecting predictors via Cox proportional hazards model and DeepSurv.
result Highly discriminating models for depression and anxiety were developed.
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.
Proposes a method to quantify uncertainty in DNN models for discrete inputs.
problem Uncertainty quantification for DNN models with categorical and discrete feature variables.
method Develops a mathematical framework to quantify prediction uncertainty from discrete input noise and model parameters.
result Identifies risk-sensitive cases prone to misclassification due to discrete predictor errors.
New method finds invariant predictors to improve model robustness.
problem Machine learning models are brittle in new environments with spurious correlations.
method Formulates invariant risk minimization as a Nash equilibrium game.
result Algorithm yields similar or better accuracy with lower variance.
Study ridge ensembles in proportional feature-to-sample size regime, proving risk equivalence and GCV consistency.
problem Characterizing and optimizing ridge ensembles in proportional feature-to-sample size regimes.
method Proportional asymptotics analysis, GCV for tuning, proving risk equivalence.
result Risk of optimal full ridgeless ensemble matches optimal ridge predictor's risk.
Extends risk control to adaptive data collection, anytime-valid guarantees.
problem Ensuring safety of machine learning models with critical risk measures.
method Sequential risk controlling prediction sets (RCPS) for adaptive data collection and active labeling.
result Anytime-valid guarantees for risk control in sequential data collection.
Empirical study of IRMv1, an invariant risk minimization framework.
problem Learning predictors invariant to spurious correlations across different training environments.
method Extending ColoredMNIST experiment to various settings.
result IRMv1 performs better as spurious correlation varies more widely.
DynForest predicts event probabilities from longitudinal data, handling endogenous predictors.
problem Predicting individual risk using longitudinal patient history.
method Random survival forests with time-fixed features from longitudinal predictors.
result DynForest provides accurate individual event probability predictions.
PAC-Bayes bound requires prior to place mass on high-performing predictors.
problem Explaining generalization in machine learning.
method Analyzing necessary conditions for PAC-Bayes bounds to provide meaningful generalization guarantees.
result Achieving a target generalisation level requires the prior to place sufficient mass on high-performing predictors.
Paper introduces a method to predict molecule properties from diverse data sources.
problem Limited ability to accommodate scarce or fragmented training data.
method Adaptive Invariance using invariant risk minimization to generalize beyond heterogeneous data.
result Predictor outperforms state-of-the-art transfer learning methods by significant margin.
In recent years, increasingly augmentation of health data, such as patient Electronic Health Records (EHR), are becoming readily available. This provides an unprecedented opportunity for knowledge discovery and data mining algorithms to dig insights from them, which can, later on, be helpful to the improvement of the q…
A new method sorts models to find the best one with minimal risk.
problem Finding the best model with minimal risk among nested models.
method Nested Empirical Risk (NER) and Sorted NER (S-NER) methods.
result The S-NER method selects the true model order and the most parsimonious model.
Proposes RVP to address theoretical concerns of V-REx for OOD generalization.
problem Theoretical concerns about V-REx's motivation and utility.
method Risk Variance Penalization (RVP) modifies V-REx's regularization.
result RVP discovers a robust predictor and finds invariant predictors under certain conditions.
We consider selection of random predictors for high-dimensional regression problem with binary response for a general loss function. Important special case is when the binary model is semiparametric and the response function is misspecified under parametric model fit. Selection for such a scenario aims at recovering th…
DEUP directly predicts epistemic uncertainty, improving model optimization and exploration.
problem Existing measures of epistemic uncertainty do not account for model misspecification.
method Proposes a framework to estimate excess risk as a measure of epistemic uncertainty, using a secondary predictor for generalization error.
result DEUP improves sequential model optimization and exploration in interactive learning environments.
The paper shows supply chain features improve cyber risk prediction.
problem Predicting cyber risk from supply chain attributes.
method Machine learning, external supply chain features, AUC improvement.
result Supply chain network features improve AUC by 2.3%.
Unified framework for portfolio optimization using multiple hypotheses.
problem Risk diversification in portfolio allocation.
method Structured ensemble learning approach with diversity control.
result Structured ensembles link predictor diversity to risk diversification.
In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the ℓ1 norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…
This work uses PAC-Bayes for structured prediction with ILE, yielding insights and algorithms.
problem Structured prediction with interdependent outputs and implicit loss embeddings.
method PAC-Bayes perspective applied to ILE framework, deriving generalization bounds and learning algorithms.
result Two learning algorithms derived from PAC-Bayes bounds, analyzed and implemented.
Proposes a copula-based filter for diabetes risk prediction.
problem Feature selection for robust and interpretable predictive modeling in medicine, especially for extreme patient strata.
method Copula-based supervised filter using Gumbel-copula implied upper-tail concordance score (lambda U).
result The proposed filter outperforms standard filters and provides clinically coherent predictors.
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.
Study improves flood loss risk models using historical data and rainfall data.
problem Predicting financial losses from flooding events.
method Used neural networks, decision trees, and kernel-based regressors on NFIP dataset, incorporating rainfall data.
result Extreme Gradient Boosting provided the best results, and bias correction improved model performance.
Improved classification model for high-cardinality categorical predictors.
problem Handling high-cardinality categorical predictors and non-linear data.
method Data-driven binning of spline functions and shrinkage estimators.
result Improved classification precision with interpretable predictors.