Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.
problem Effective learning in linear bandits with corrupted rewards across different corruption models.
method Unified framework for analyzing strong and weak corruption, connection to gap-dependent misspecification, and specialized algorithm.
result Optimal bounds for gap-dependent misspecification in linear bandits.
Algorithm reduces regret in misspecified linear contextual bandits.
problem Misspecified linear contextual bandits with bounded misspecification.
method Data selection scheme for online regression, leveraging uncertainty.
result Regret bound of O ~ ( d 2 / Δ ) \tilde O(d^2/Δ) O ~ ( d 2 /Δ ) when ζ ≤ O ~ ( Δ / d ) ζ \leq \tilde O(Δ/\sqrt{d}) ζ ≤ O ~ ( Δ/ d ) . Improved gap-dependent bounds for reinforcement learning with linear approximations.
problem Achieving nearly minimax-optimal performance with linear function approximation.
method Developed and analyzed the LSVI-UCB++ algorithm and its concurrent variant.
result First gap-dependent regret bound for nearly minimax-optimal algorithm LSVI-UCB++.
This paper improves Q-learning bounds using reference-advantage decomposition.
problem Improving Q-learning bounds in MDPs with positive suboptimality gaps.
method Develops a novel error decomposition framework to prove gap-dependent regret bounds.
result Establishes logarithmic gap-dependent regret bounds for Q-learning.
Study gap-dependent regret bounds for risk-sensitive RL.
problem Risk-sensitive reinforcement learning with entropic risk measure.
method Propose cascaded gaps to adapt to problem structures, derive regret bounds.
result Exponential improvement over existing bounds in appropriate settings.
New method reduces regret and communication costs in federated Q-learning.
problem Worst-case regret and communication cost bounds in federated Q-learning.
method Gap-dependent analysis leveraging MDP structures.
result Achieves log T \log T log T -type regret and communication cost bounds. Fine-grained gap-dependent regret bounds for reinforcement learning.
problem Achieving optimal regret bounds for reinforcement learning with suboptimality gaps.
method Developed novel analytical frameworks and refined algorithms for UCB-based and non-UCB-based reinforcement learning.
result Established the first fine-grained gap-dependent regret bounds for both UCB-based and non-UCB-based algorithms.
This paper establishes that optimistic algorithms attain gap-dependent and non-asymptotic logarithmic regret for episodic MDPs. In contrast to prior work, our bounds do not suffer a dependence on diameter-like quantities or ergodicity, and smoothly interpolate between the gap dependent logarithmic-regret, and the $\wid…
The paper analyzes Q-learning in 2-player Markov games and provides gap-dependent logarithmic regret bounds.
problem Analyzing the cumulative regret of Nash Q-learning in 2-player turn-based stochastic Markov games.
method Proposed gap-dependent logarithmic upper bounds for cumulative regret in episodic tabular setting and discounted game setting.
result The proposed bounds match theoretical lower bounds up to a logarithmic term.
New algorithm reduces MDP regret by accounting for state suboptimality gaps and variance.
problem Reducing regret in episodic MDPs with varying state suboptimality gaps.
method Introduced MVP algorithm with variance-aware gap-dependent regret bound.
result Achieved a variance-aware gap-dependent regret bound for MDPs.
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.
New algorithm reduces regret in private online learning with optimal gap-dependent rate.
problem Optimal gap-dependent regret rate for private stochastic decision-theoretic online learning.
method Horizon-free pure-DP algorithm with exponential block partitioning and softmax selection.
result Explicit regret bound of 1000 ⋅ ( log K Δ min + log K ε ) 1000 \cdot (\frac{\log K}{Δ_{\min}}+\frac{\log K}{\varepsilon}) 1000 ⋅ ( Δ m i n l o g K + ε l o g K ) . Optimized α \alpha 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 \alpha α -posteriors. result Optimized α \alpha α -posteriors minimize KL divergence from true posterior, especially in severe misspecification. 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.
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.
Adaptive smooth non-stationary bandits achieve optimal regret rates without knowing parameters.
problem Smooth non-stationary bandits with Hölder class rewards.
method Established optimal dynamic regret rate and adaptive algorithm.
result Optimal dynamic regret can be attained adaptively without knowing Hölder exponent and coefficient.
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.
A matroid is a notion of independence in combinatorial optimization which is closely related to computational efficiency. In particular, it is well known that the maximum of a constrained modular function can be found greedily if and only if the constraints are associated with a matroid. In this paper, we bring togethe…
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.
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.
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.
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.
The paper tackles misspecification in contextual bandits by incorporating arm-specific variables.
problem Misspecification in contextual bandits due to unexplained inter-arm heterogeneity.
method Develops robust contextual bandit algorithms (RoLinUCB and RoLinTS) that incorporate arm-specific variables to address misspecification.
result The developed algorithms bound the n n n -round Bayes regret and show superior performance in various misspecification scenarios. New insights into bias-variance tradeoff for data-driven optimization under local misspecification.
problem Understanding the relative performance of SAA, IEO, and ETO under local misspecification.
method Developed a local misspecification perspective using contiguity theory in statistics.
result Explicit expressions for decision bias and geometric understanding of variance.
The paper improves SBI for BHMs by diagnosing misspecification and inferring parameters.
problem Model misspecification in Bayesian hierarchical models.
method Two-step framework: latent function diagnosis followed by SBI of target parameters.
result Improved simulation-based inference for complex models without explicit model checking.
RoPE framework calibrates misspecified simulators for reliable inference.
problem Misspecification compromises reliability of simulation-based inference.
method Data-driven calibration using optimal transport and a small calibration set.
result RoPE framework improves inference accuracy and uncertainty calibration.
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.
Algorithm mitigates performance loss in constrained reinforcement learning with model misspecification.
problem Performance loss in reinforcement learning policies due to model misspecification in constrained control systems.
method Proposes an algorithm to handle constrained model misspecification in continuous control systems.
result Algorithm successfully mitigates performance loss in real-world reinforcement learning tasks.
Enhances predictive models against misspecification and outliers.
problem Suboptimal generalization under misspecification and outliers.
method Combines PAC m ^m m ensemble bounds with a generalized logarithm score function. result Produces predictive distributions resistant to both misspecification and outliers.
We consider the noisy power method algorithm, which has wide applications in machine learning and statistics, especially those related to principal component analysis (PCA) under resource (communication, memory or privacy) constraints. Existing analysis of the noisy power method shows an unsatisfactory dependency over …
Model misspecification is a long-standing enigma of the Bayesian inference framework as posteriors tend to get overly concentrated on ill-informed parameter values towards the large sample limit. Tempering of the likelihood has been established as a safer way to do updates from prior to posterior in the presence of mod…
Proposes a method to improve SBI under model misspecification.
problem Unreliable inference from SBI methods under model misspecification.
method Introduces a regularized loss function to penalize statistics that increase model-data mismatch.
result Demonstrates superior performance and robust inference in misspecified scenarios.
SBI provides more accurate pole positions than chi-squared minimization in model misspecification.
problem Accurate pole position estimation in pi-pi scattering models.
method Simulation Based Inference (SBI) method compared to chi-squared minimization.
result SBI leads to more robust predictions of pole positions in models of pi-pi scattering.
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.
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…
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.
New method improves simulation-based inference by avoiding model misspecification.
problem Inefficient parameter estimation for models with intractable likelihoods.
method Proposes a robust SNL method with additional adjustment parameters.
result Demonstrates more accurate point estimates and uncertainty quantification.
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.
Paper proposes efficient method for evaluating Bayesian models in imaging.
problem Evaluation of Bayesian models in imaging when ground truth is unavailable.
method Novel combination of Bayesian cross-validation and data fission for unsupervised model selection and misspecification detection.
result Achieved excellent selection and detection accuracy with low computational cost.
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.
UDA improves ABI robustness but fails under certain prior misspecifications.
problem Robustness of ABI in noisy real-world data.
method Systematic evaluation of UDA across various misspecification scenarios.
result UDA aligns summary spaces but can fail under prior misspecifications.
BayesBag improves reproducibility of Bayesian inference under model misspecification.
problem Bayesian posteriors can be unreliable and inconsistent under model misspecification.
method Apply bagging to the Bayesian posterior to improve reproducibility.
result Bagged posteriors typically satisfy reproducibility criteria under misspecification.
Improves DRO with Bayesian Ambiguity Sets for model misspecification.
problem Overly conservative decisions due to misspecified models in DRO.
method Introduces DRO-RoBAS with robust posterior predictive distribution.
result Outperforms other Bayesian and empirical DRO approaches in out-of-sample performance.
Study EM and GD for clustering with penalties for misspecification and high dimensions.
problem Clustering with misspecification and high-dimensional data.
method Model-based Gaussian Mixture Models, EM algorithm, GD optimization with AD, penalized likelihood.
result GD outperforms EM on high-dimensional data but both have poor cluster interpretation.
Unified approach for non-stationary linear bandits with dynamic regret.
problem Non-stationary linear bandits with round-specific feasible actions and drifting reward models.
method Unified misspecification-reduction viewpoint, restarting algorithms with misspecification-dependent regret guarantees.
result Optimal \(T^{2/3}P_T^{1/3}\) dynamic-regret dependence for both linear bandits and contextual linear bandits.
New RL algorithms reduce costs for single-agent and federated learning.
problem Minimizing costs in RL and federated RL settings.
method Q-EarlySettled-LowCost and FedQ-EarlySettled-LowCost algorithms.
result First algorithms to achieve low burn-in and logarithmic switching costs.