New method improves experimental design under model misspecification.
problem Improving experimental design under time and budget constraints with model misspecification.
method Developed a new acquisition function (R-IDeA) that targets representativeness, informativeness, and de-amplification.
result The new method outperforms methods focusing on representativeness or informativeness alone.
Paper tackles SBI under model misspecification, presenting robust strategies.
problem Challenges in SBI under model misspecification.
method Three key strategies: robust summary statistics, generalised Bayesian inference, and error modelling.
result Empirical results show vulnerabilities of SBI and effectiveness of misspecification-robust alternatives.
Bayesian framework improves robustness in nonlinear regression models.
problem Measurement error, model misspecification, and distributional misspecification in regression analyses.
method Joint Dirichlet process prior on latent covariate-response distribution, updating with posterior pseudo-samples.
result Improved stability and consistency in estimators under increasing measurement error.
Improves estimation under model misspecification with fake features.
problem Model misspecification with fake features.
method Proposes a framework to decompose output error into underlying, fake, and missing features.
result Fake features can significantly improve estimation performance, even when not correlated with underlying features.
Unified framework for robust A/B testing under model misspecification.
problem Improving sample efficiency in A/B testing with model misspecification.
method Unified framework for contextual bandit and dynamic settings, proving worst-case mean squared error bounds.
result Empirically validated approach using synthetic and real-world datasets.
Variational Bayes (VB) is a scalable alternative to Markov chain Monte Carlo (MCMC) for Bayesian posterior inference. Though popular, VB comes with few theoretical guarantees, most of which focus on well-specified models. However, models are rarely well-specified in practice. In this work, we study VB under model missp…
DP models misspecify LF dependencies, leading to significant performance errors.
problem Misspecification of LF dependencies in DP models.
method Theoretical bounds and empirical analysis of modeling errors.
result Modeling errors can be substantial, even with sensible LF structures.
New method improves robustness of double robust estimators under complete misspecification.
problem Improper performance of double robust estimators when all nuisance functions are misspecified.
method DR+ACC, an adaptive correction clipping method.
result DR+ACC ensures bounded error and maintains semiparametric efficiency.
Optimized α-posteriors reduce KL divergence from true posterior in parametric misspecification.
problem Reduction of KL divergence from true posterior in parametric model misspecification.
method Derivation of Bernstein-von Mises theorem and optimization of α-posteriors. result Optimized α-posteriors minimize KL divergence from true posterior, especially in severe misspecification. The paper analyzes sparse high-dimensional linear regression with random design and unknown error variance, providing adaptiveness and concentration rates.
problem Sparse high-dimensional linear regression with random design and unknown error variance.
method Analysis of posterior concentration rates, employing techniques to address model misspecification.
result Adaptiveness and concentration rates of the posterior for sparse high-dimensional linear regression.
Adapts to misspecification in contextual bandits using offline regression.
problem Unexpected regret due to misspecified reward models.
method Adapts to misspecification by reverting to a safe policy when necessary.
result Regret guarantees degrade gracefully with misspecification level.
New algorithm mitigates misspecification amplification in regression models with covariate shift.
problem Distribution shift and model misspecification in regression models.
method Developed a new algorithm inspired by robust optimization to avoid misspecification amplification.
result No misspecification amplification while still achieving optimal statistical rates.
The paper examines how kernel approximations affect Gaussian process regression in large data applications.
problem Effect of kernel approximations on Gaussian process regression in large data applications.
method Unified framework to analyze Gaussian process regression under computational and epistemic misspecification.
result Theoretical analysis of Gaussian process regression under various misspecifications.
Enhances predictive models against misspecification and outliers.
problem Suboptimal generalization under misspecification and outliers.
method Combines PACm ensemble bounds with a generalized logarithm score function. result Produces predictive distributions resistant to both misspecification and outliers.
The paper tackles model misspecification in reinforcement learning through a bootstrapped neural network and error correction.
problem Model misspecification in reinforcement learning environments.
method Proposes a bootstrapped multi-headed neural network to learn model distributions and a global error correction filter.
result Demonstrates increased performance and stability in model accuracy and planning algorithm use.
The paper investigates model misspecification in Bayesian inference using neural networks.
problem Detecting model misspecification in Bayesian inference with neural networks.
method Conceptualized types of model misspecification and proposed an augmented optimization objective with MMD.
result MMD can detect potentially catastrophic misspecifications in Bayesian inference.
Improved guarantees for misspecified kernelized bandit optimization.
problem Misspecification in kernelized bandit optimization.
method Localization and domain splitting techniques.
result Logarithmic or polylogarithmic growth of misspecification amplification.
Paper introduces RVNP to improve SBI in misspecified models.
problem Misspecification in simulation-based inference leads to unreliable posterior estimation.
method RVNP uses variational inference and error modeling to bridge the simulation-to-reality gap.
result RVNP can recover robust posterior inference without hyperparameters or priors.
New method improves stock return prediction in non-stationary markets.
problem Tackles the challenge of predicting stock returns in non-stationary environments.
method Jointly optimizes model class and training window size using a tournament procedure.
result Consistently outperforms standard benchmarks by 14-23% in out-of-sample R2. Gradient filters track moving parameters under noisy data and misspecification.
problem Tracking multidimensional time-varying parameters under noisy observations and model misspecification.
method Gradient-based filters update parameters using the gradient of a postulated objective function, evaluated at either the predicted or updated parameters.
result Novel sufficient conditions for exponential stability of the filtered parameter path, and finite-sample and asymptotic mean squared error bounds.
Bayesian framework tackles measurement error in covariates.
problem Misleading inference due to corrupted covariates.
method Bayesian Nonparametric Learning framework robust to misspecification.
result General framework for Classical and Berkson error models.
Bayesian regression underestimates parameter uncertainties in noisy models.
problem Parameter uncertainties are underestimated in Bayesian regression for imperfect models.
method Analyzed and designed an ansatz to correct for misspecification in near-deterministic surrogate models.
result Posterior distributions must cover all training points to avoid divergent generalization error.
FMCPE improves SBI accuracy by correcting posterior estimators with flow matching.
problem Model misspecification in SBI leads to biased or overconfident posteriors.
method Flow Matching Corrected Posterior Estimation (FMCPE) trains a posterior approximator and corrects it using calibration samples.
result FMCPE consistently mitigates misspecification effects, improving inference accuracy and uncertainty quantification.
Paper analyzes error bounds for learning with vector-valued RF, improving existing analyses.
problem Learning with vector-valued random features in infinite-dimensional settings.
method Direct analysis of risk functional, avoiding random matrix theory.
result Strong consistency and minimax optimal convergence rates established.
Paper studies offline RL with linear approx, focusing on inherent Bellman error.
problem Offline RL with linear approx, focusing on inherent Bellman error.
method Algorithm that succeeds under single-policy coverage condition, leveraging inherent Bellman error.
result Algorithm yields first known guarantee under single-policy coverage, even for linear Bellman completeness.
New framework investigates how fake features affect model generalization.
problem Model misspecification with fake features and their impact on generalization.
method Non-asymptotic high-probability bound on ridge regression generalization error.
result Trade-off between fake features and optimal ridge parameter.
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.
The paper addresses the gap between theoretical and practical confidence set widths in universal inference.
problem Inference procedures can be overly conservative, leading to wider confidence sets than expected.
method The authors identify the source of asymptotic conservativeness and propose a remedy based on studentization and bias correction.
result The proposed method achieves exact asymptotic coverage at the nominal 1−α level, even under model misspecification. PC-PG balances exploration and exploitation in reinforcement learning.
problem Local policy gradient methods struggle with exploration.
method PC-PG uses an ensemble of learned policies (policy cover) to balance exploration and exploitation.
result PC-PG provides strong theoretical guarantees and empirical validation.
New algorithms for optimizing functions with noisy feedback, even when the model is misspecified.
problem Optimizing a black-box function with noisy bandit feedback, especially when the model is misspecified.
method Developed two algorithms based on Gaussian process methods: EC-GP-UCB and Phased GP Uncertainty Sampling.
result Achieved optimal dependence on misspecification error without prior knowledge, and effective in stochastic contextual settings.
The paper highlights the importance of model misspecification in uncertainty estimation.
problem The reliability of uncertainty estimates in machine learning models under model misspecification.
method Thought experiments and literature review.
result Model misspecification should be given more attention in uncertainty estimation.
Synthetic data augmentation can improve imbalanced classification metrics.
problem Improving imbalanced classification metrics
method Developing a framework for analyzing the effects of synthetic data augmentation on score-based classification
result Augmentation can improve AUROC, AUPRC, balanced accuracy, and F1 score
New framework assesses value of labeled vs unlabeled data in latent variable models.
problem Determining the optimal use of labeled and unlabeled data in latent variable models.
method Developed a bias-variance decomposition of the generalization error for method-of-moments latent variable estimation, and introduced a correction for misspecification.
result Labeled data is more valuable than unlabeled data when models are misspecified, but this value can be reduced with correction.
SRO optimizes decisions against worst-case sampler induced by generative models.
problem Operational uncertainty shifts from explicit probability law to sampler induced by learned generators.
method SRO optimizes decisions against the worst-case sampler induced by perturbing the learned generator.
result Empirical worst-case objective provides high-probability upper certificate for true population objective.
New bandit algorithm works without realizability assumption.
problem Contextual bandit problems without realizability assumption.
method Computes a constrained regression problem in every epoch, ensuring similar regret guarantees as realizability-based algorithms.
result Ensures similar regret guarantees as realizability-based algorithms, up to a misspecification term.
Unified framework for robust linear predictions without distributional assumptions.
problem Robust linear predictions in the presence of outliers and model misspecification.
method Unified robust framework for linear prediction problems on Hilbert spaces, using Median of Means (MoM) approach.
result Achieves an error rate of \(O(\max\left\{|\mathcal{O}|^{1/2}n^{-1/2}, |\mathcal{I}|^{1/2}n^{-1}
ight\}+ε)\) for misspecification level \(ε\), matching best-known rates.
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.
This paper studies optimal approximation factors in misspecified off-policy RL, identifying key factors under various settings.
problem Understanding optimal approximation factors in misspecified off-policy value function estimation.
method Examined various settings including weighted L2-norm, L∞ norm, state aliasing, and state coverage. result Established optimal asymptotic approximation factors for different norms and identified two instance-dependent factors for L2(μ) norm. Study highlights how model choice affects uncertainty estimation in neural network regression.
problem Uncertainty estimation under model misspecification in neural network regression.
method Analyzed the impact of model choice on uncertainty estimation in neural network regression, focusing on aleatoric and epistemic uncertainties.
result Model misspecification leads to unreliable uncertainty estimates, highlighting the importance of choosing appropriate models.
The paper tackles joint learning of linear systems, improving accuracy with pooled data.
problem Estimating transition matrices of multiple related linear systems more accurately.
method Developed novel techniques to bound estimation errors and establish high probability bounds for singular values.
result Significant gains in accuracy achieved by pooling data across systems.
Maximizes robustness in Bayesian experimental design under model uncertainty.
problem Brittleness of Bayesian experimental design under model misspecification.
method Formulates as a max--min game, uses Sibson's α-MI, and adopts PAC-Bayes framework.
result Establishes robust belief update and conditional information gain measure.
Study reveals model misspecification significantly impacts neural SBI algorithms.
problem Impact of model misspecification on neural SBI algorithms.
method Comprehensive study of neural SBI algorithms under various forms of model misspecification.
result Misspecification profoundly deleterious to performance of neural SBI algorithms.
The paper provides PAC bounds for estimating causal effects using covariate adjustment with a valid set.
problem Estimating causal effects in high-dimensional settings without randomized experiments.
method PAC learning perspective, valid adjustment set, $\eps$-Markov blanket, constraint-based algorithms.
result PAC-bounds the estimation error of covariate adjustment by a term exponential in the size of the adjustment set.
FedGVI improves FL robustness to model misspecification.
problem Limited robustness in FL approaches to model misspecification.
method Probabilistic Federated Learning framework that generalizes previous methods.
result FedGVI provides robust and calibrated predictions under model misspecification.
New algorithms adapt to model misspecification in contextual bandits.
problem Design efficient algorithms for contextual bandits that handle model misspecification gracefully.
method Oracle-efficient algorithms for ε-misspecified contextual bandits using square loss regression.
result First algorithm achieving optimal regret bound for unknown misspecification level in linear contextual bandits.
Alpha-based performance evaluation may fail to capture correlated residuals due to model errors. This paper proposes using the Generalized Information Ratio (GIR) to measure performance under misspecified benchmarks. Motivated by the theoretical link between abnormal returns and residual covariance matrix, GIR is deriv…
Detects model misspecifications in causal models using observational data.
problem Identifying predictor variables with causal effects in misspecified models.
method Develops a general framework based on observational data distribution and proposes an algorithm for finite sample data.
result Identifies predictor variables for causal effects even in misspecified models.
Study improves convergence rates for GVI under prior misspecification.
problem Improving convergence rates for GVI under prior misspecification.
method Proves rates of convergence and robustness to prior misspecification in GVI framework.
result Establishes sufficient conditions for existence and uniqueness of GVI posteriors.