Proposes a method to create fair, robust predictors that remain consistent across different scenarios.
problem Creating fair and robust machine learning models that behave consistently across different scenarios.
method Graphical criteria and a model-agnostic framework called CIP based on HSCIC.
result Demonstrates the effectiveness of CIP in enforcing counterfactual invariance across various datasets.
Understanding optimal prompts for binary sequence predictors is challenging.
problem Finding good prompts for binary sequence predictors is difficult.
method Viewing prompting as finding the best conditioning sequence on a near-optimal sequence predictor, using empirical and statistical analysis.
result Optimal prompts can be better understood given the pretraining distribution, which is not usually available.
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…
The paper develops predictors for functional data on manifolds.
problem Functional data prediction on time-varying manifolds.
method Least-squares local linear Fréchet curve predictor and weighted Fréchet mean approach.
result Asymptotical optimality of the proposed predictors.
New theory validates the use of invariant predictors for OOD generalization.
problem Ensuring predictors generalize well across unseen environments.
method Developed new theoretical conditions and derived an Inter Gradient Alignment algorithm.
result Validated the necessity of invariant predictors for OOD optimality.
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…
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.…
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.
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…
The problem is sequence prediction in the following setting. A sequence x1,..., xn,... of discrete-valued observations is generated according to some unknown probabilistic law (measure) mu. After observing each outcome, it is required to give the conditional probabilities of the next observation. The measure mu belongs…
This paper re-examines conformal e-prediction and its advantages over conformal prediction.
problem The relationship between conformal prediction and conformal e-prediction.
method Systematic re-examination of conformal prediction and conformal e-prediction from a modern perspective.
result Conformal e-prediction has advantages such as ease of designing conditional predictors and guaranteed validity of cross-predictors.
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 paper provides estimation and inference methods for the best linear predictor (approximation) of a structural function, such as conditional average structural and treatment effects, and structural derivatives, based on modern machine learning (ML) tools. We represent this structural function as a conditional expec…
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…
Paper introduces new importance metrics for machine learning models, linking them to CATE.
problem Interpreting black-box models' importance metrics due to data dependence and non-parametric nature.
method Introduces MVIM and CVIM, proposing permutation-based estimation and bias-variance decomposition.
result MVIM and CVIM have a quadratic relationship with CATE, addressing bias in correlated predictors.
Optimal regression with reject option using conditional variance thresholding.
problem Regression with reject option to handle uncertain predictions.
method Derive optimal rule based on thresholding conditional variance, semi-supervised estimation using labeled and unlabeled data.
result The predictor with reject option is almost as good as the optimal predictor in terms of risk and rejection rate.
New method uses machine learning to improve statistical inference.
problem Performing inference on conditional functionals with scarce labeled data.
method Combines localization with prediction-based variance reduction.
result Valid and sharp confidence intervals for conditional functionals.
Optimizing proper loss yields calibrated models under specific conditions.
problem Understanding when optimizing proper loss functions leads to calibrated predictions.
method Local optimality condition and Lipschitz functions.
result Predictors with local optimality are nearly calibrated and nearly locally optimal.
Bayes predictor remains robust to ignorable missingness shifts.
problem Challenges in prediction with missing covariates and shifts in missingness reasons.
method Bayesian approach and different prediction methods.
result Bayes predictor remains unchanged by ignorable shifts, but robust prediction requires disregarding missingness for non-ignorable shifts.
This work tackles long-term visual planning by goal-conditioned hierarchical predictors.
problem Current learning approaches fail on long-horizon tasks due to lack of goal information and coarse-to-fine planning.
method Formulate goal-conditioned predictors (GCPs) and hierarchical models to predict trajectories between observations.
result GCPs enable effective long-term planning with much longer horizons than before.
We consider rules for discarding predictors in lasso regression and related problems, for computational efficiency. El Ghaoui et al (2010) propose "SAFE" rules that guarantee that a coefficient will be zero in the solution, based on the inner products of each predictor with the outcome. In this paper we propose strong …
Efficiently selects predictors in sparse regression without approximations.
problem High computational cost in subset selection for sparse regression.
method Conditional uncorrelation formula and efficient non-approximate method.
result Significant reduction in computational complexity for subset selection.
Defines a new metric to measure importance of predictors in complex machine learning models.
problem Measuring importance of predictors in black box machine learning models.
method Introduces a new metric, GVIM, based on true conditional expectation functions and causal interpretation.
result The GVIM can be represented as a function of Conditional Average Treatment Effect (CATE), providing a causal interpretation.
We consider a problem of data integration. Consider determining which genes affect a disease. The genes, which we call predictor objects, can be measured in different experiments on the same individual. We address the question of finding which genes are predictors of disease by any of the experiments. Our formulation i…
It has been argued that in supervised classification tasks, in practice it may be more sensible to perform model selection with respect to some more focused model selection score, like the supervised (conditional) marginal likelihood, than with respect to the standard marginal likelihood criterion. However, for most Ba…
We resolve the open problem of optimal sample complexity for multicalibration and deterministic predictors.
problem Optimal sample complexity for multicalibration and deterministic predictors
method Minimax-optimal multicalibration algorithm and generalization to OI predictors
result Minimax-optimal multicalibration algorithm and deterministic predictors with optimal sample complexity
A new knockoff statistic using conditional prediction function improves variable selection in complex models.
problem Controlling false discovery rate in complex models with nonlinear relationships.
method Introducing a knockoff statistic based on the conditional prediction function for use with machine learning models.
result The CPF statistics provide superior power in detecting prognostic variables over existing knockoff statistics.
Bayesian framework evaluates predictors of subjective visual tasks.
problem Evaluating uncertainty in machine learning predictors for tasks with subjective annotations.
method Bayesian framework to estimate epistemic uncertainty from human labels.
result Framework successfully applied to four image classification tasks.
AM-PPI uses multiple predictors to reduce label cost in healthcare AI.
problem Reduces label cost in post-deployment monitoring of healthcare AI.
method Combines model predictions with a small labeled sample, routing each instance to a cost-appropriate subset of predictors.
result Produces narrower confidence intervals than single-predictor methods.
Proposes new method for calibrating treatment effect predictors.
problem Calibrating predictors of heterogeneous treatment effects.
method Causal isotonic calibration and cross-calibration.
result Achieves fast calibration rates under weak conditions.
DFNNs predict non-Euclidean responses from Euclidean predictors.
problem Regression with non-Euclidean responses.
method Deep Fréchet neural networks (DFNNs) approximating conditional Fréchet means.
result DFNNs consistently outperform existing methods in empirical studies.
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.
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.
New method uses neural networks for estimating survival functions from censored data.
problem Estimating conditional survival functions from censored time-to-event data with complex predictors.
method Generative adversarial networks leveraging self-consistent equations, without parametric assumptions.
result Established the convergence rate of the proposed estimator.
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 …
The knockoff filter introduced by Barber and Candès 2016 is an elegant framework for controlling the false discovery rate in variable selection. While empirical results indicate that this methodology is not too conservative, there is no conclusive theoretical result on its power. When the predictors are i.i.d. Gaussian…
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.
A new method combines predictors and their lags using supervised PCA for dynamic forecasting.
problem Dynamic forecasting with many predictors.
method Supervised PCA with re-scaling and penalized methods.
result The method outperforms traditional PCA and diffusion-index approaches in prediction.
Linear properties are either universal or absent across language models.
problem Explaining the prevalence of linear properties in language models.
method Proved identifiability of distribution-equivalent next-token predictors and analyzed various notions of linearity.
result Linear properties either hold in all or none distribution-equivalent next-token predictors.
This work shows how disentangled and sparse representations improve multi-task learning.
problem Improving generalization in multi-task learning with disentangled and sparse representations.
method Proved a new identifiability result and proposed a practical approach using sparsity-promoting bi-level optimization.
result Maximally sparse base-predictors yield disentangled representations under certain conditions.
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.
Technology and collaboration enable dramatic increases in the size of psychological and psychiatric data collections, but finding structure in these large data sets with many collected variables is challenging. Decision tree ensembles like random forests (Strobl, Malley, and Tutz, 2009) are a useful tool for finding st…
The study simplifies assessing overlap in logistic regression models using empirical likelihood.
problem Assessing overlap in multidimensional logistic regression models.
method Translation of Silvapulle's condition to empirical likelihood maximization, mechanized with R code.
result Minimal overlapping structures are cataloged in dimensions less than four, providing rules for higher dimensions.
Study on approximability and generalization in machine learning.
problem Understanding how approximation affects learning and generalization in machine learning.
method Introducing a notion of sensitivity to analyze the impact of approximation operators on predictors and proving upper bounds on generalization.
result Proven that approximable target concepts are learnable with fewer labelled samples and sufficient unlabelled data.
The paper studies calibration in ML models for wireless networks, showing key theoretical and practical insights.
problem Ensuring ML models in wireless networks deliver well-calibrated confidence scores for reliable decision-making.
method Theoretical analysis and simulation-based experiments using Platt scaling and isotonic regression.
result Well-calibrated models improve the system's minimum achievable OP and are part of a broader class of predictors.
This paper extends stable blanket theory to models with hidden variables and causal cycles.
problem Identifying stable predictors in models with hidden variables and causal cycles.
method Use acyclic directed mixed graphs (ADMGs) and directed graphs (DGs) with m-separation and σ-separation to characterize and construct intervention-stable predictor sets. result Graphical characterizations of Markov blankets, stable frontiers, and stable blankets in models with hidden variables and cycles.
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
In order to identify important variables that are involved in making optimal treatment decision, Lu et al. (2013) proposed a penalized least squared regression framework for a fixed number of predictors, which is robust against the misspecification of the conditional mean model. Two problems arise: (i) in a world of ex…