This paper evaluates targeted data poisoning attacks by focusing on the hardest samples, improving evaluation and defense strategies.
problem The effectiveness of targeted data poisoning attacks is often overestimated due to average evaluation methods.
method The paper introduces metrics to identify the hardest and easiest to poison samples based on clean model information.
result The proposed metrics reliably stratify samples by poisoning vulnerability, enabling rigorous worst-case evaluation and proactive defense.
This work evaluates PDA methods without target labels, revealing significant accuracy drops.
problem Evaluating PDA methods without target labels and inconsistent experimental settings.
method Realistic evaluation of 7 PDA methods with 7 model selection strategies on 2 datasets.
result Accuracy drops up to 30 percentage points without target labels, only one method performs well.
New method stabilizes FQE by reweighting Bellman targets.
problem Stability guarantees for FQE often rely on Bellman completeness, which can fail with function approximation.
method Proposes stationary-weighted FQE, reweighting Bellman targets by stationary target-to-behavior density ratio.
result Proves finite-sample linear convergence to stationary projected Bellman fixed point without Bellman completeness.
Framework optimizes targeting high-need individuals while estimating treatment effects.
problem Balancing resource allocation to high-need individuals with evaluating treatment effects.
method Proposes a framework to design randomized allocation rules that balance targeting high-need recipients with learning treatment effects.
result Optimized policies can significantly mitigate the tradeoff between targeting high-need individuals and estimating treatment effects.
Combines trial and observational data to improve policy evaluation.
problem External validity of randomized trial results in target populations.
method Uses covariate data to model trial sampling and certifies policy evaluations.
result Valid trial-based policy evaluations under model miscalibration.
Paper introduces IC-index to evaluate interaction prediction methods.
problem Evaluate interaction prediction methods using IC-index.
method IC-index measures interaction direction prediction performance.
result IC-index complements existing prediction performance estimators.
New method improves conditional covariance estimation using targeted groups of assets.
problem Improving conditional covariance estimation in financial time series.
method Introduces targeting in BEKK and DCC models for financial time series analysis.
result Encouraging results from empirical case study, especially with fewer assets.
The paper evaluates samplers on multi-modal targets, focusing on mode separation and recovery.
problem Handling multi-modality in sampling.
method Synthetic experimental setting focusing on mode relative importance recovery.
result Illustrates the challenges and potential of samplers in multi-modality.
Study designs logging policies to minimize off-policy evaluation error.
problem Minimizing OPE error with logging policies for target policies.
method Characterizes reward-coverage tradeoff, proposes a unifying framework, derives optimal policies.
result Provides actionable guidance for firms choosing recommendation systems.
Presents SPEED, an algorithm for optimal policy evaluation in linear bandits with heteroscedastic noise.
problem Optimal data collection for policy evaluation in linear bandits with heteroscedastic reward noise.
method Formulated an optimal design for weighted least squares estimates, derived the optimal sample allocation, introduced SPEED algorithm, and derived regret bounds.
result SPEED leads to policy evaluation with MSE comparable to oracle strategy and significantly lower than random policy execution.
EAST aligns neural network classifiers with user-defined evaluation metrics.
problem Mismatch between neural network training and evaluation metrics leads to suboptimal performance.
method EAST uses dynamic thresholding, soft-set confusion matrix, and annealing to align neural network predictions with target evaluation metrics.
result EAST improves alignment between training objectives and evaluation metrics, outperforming existing methods.
Develops methods to estimate and quantify uncertainty in off-policy evaluation.
problem Uncertainty quantification in off-policy evaluation for new policy deployment.
method Designs a pseudo policy to generate subsamples and applies conformal prediction.
result Valid interval estimators for target policy's return with uncertainty quantification.
ISAAC audits deep models for drug-target interactions, revealing structural differences.
problem Deep models for DTI often use irrelevant features, making them hard to evaluate.
method ISAAC uses intervention-based structural auditing to evaluate model sensitivity.
result ISAAC reveals significant structural differences in DTI models' reasoning.
Radio frequency (RF) sensors are used alongside other sensing modalities to provide rich representations of the world. Given the high variability of complex-valued target responses, RF systems are susceptible to attacks masking true target characteristics from accurate identification. In this work, we evaluate differen…
The study addresses biases in evaluating molecular optimization methods and proposes methods to reduce these biases.
problem Biases in in silico evaluation of molecular optimization methods.
method Discussion and empirical investigation of bias reduction methods for predictor misspecification and sample reuse.
result Empirical investigation of bias reduction methods for predictor misspecification and sample reuse.
Evaluating prediction models under covariate shift and selective labels
problem Model performance evaluation under distribution shift and selection bias
method Double machine learning
result Accurate estimation of target risk
This study evaluates different normalizing flow architectures for MCMC.
problem Lack of systematic comparison of normalizing flow architectures in MCMC.
method Extensive evaluation of various normalizing flow architectures on different MCMC methods and target distributions.
result Contractive residual flows are the best general-purpose models for MCMC.
We present a general framework for accelerating a large class of widely used Markov chain Monte Carlo (MCMC) algorithms. Our approach exploits fast, iterative approximations to the target density to speculatively evaluate many potential future steps of the chain in parallel. The approach can accelerate computation of t…
New algorithm MTMC reduces MCMC evaluation costs.
problem High-dimensional sampling with intractable posterior evaluations.
method Iteratively updated approximation of posterior distribution for acceptance rate.
result Approximation converges to true posterior as iterations increase.
Paper proposes a framework for reliable off-policy evaluation in reinforcement learning.
problem Quantifying uncertainty in off-policy estimates for safe deployment of target policies.
method Distributionally robust optimization for creating confidence bounds.
result Non-asymptotic and asymptotic guarantees for robust cumulative reward estimates.
We propose an efficient transfer Bayesian optimization method, which finds the maximum of an expensive-to-evaluate black-box function by using data on related optimization tasks. Our method uses auxiliary information that represents the task characteristics to effectively transfer knowledge for estimating a distributio…
Paper proposes a method to create more reliable confidence intervals for off-policy evaluations.
problem Creating reliable confidence intervals for off-policy evaluations.
method Proposes a deeply-debiasing procedure to construct efficient, robust, and flexible confidence intervals.
result Validated by theoretical results and numerical experiments, the method improves the reliability of off-policy evaluations.
Paper introduces new evaluation criteria for feature-based model explanations.
problem Establishing reliable feature importance explanations for models.
method Robustness analysis using smaller adversarial perturbations.
result New explanations that are necessary and sufficient for predictions.
EWFM trains continuous flows with only energy evaluations, improving sample quality with fewer computations.
problem Efficiently sampling from complex, high-dimensional Boltzmann distributions using only energy evaluations.
method Energy-Weighted Flow Matching (EWFM) using importance sampling and iterative/annealed training.
result Improved sample quality with up to 3 orders of magnitude fewer energy evaluations compared to existing methods.
LSB is a new MCMC method for discrete spaces that reduces target evaluations.
problem Sampling in discrete domains with high efficiency and adaptability.
method Local self-balancing proposals, mutual information objective, self-balancing learning.
result LSB converges with fewer target evaluations compared to existing methods.
We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In particular, we introduce a novel doubly-robust estimator for the OPE problem in RL, b…
Understanding and evaluating the robustness of neural networks under adversarial settings is a subject of growing interest. Attacks proposed in the literature usually work with models trained to minimize cross-entropy loss and output softmax probabilities. In this work, we present interesting experimental results that …
This paper presents novel mixed-type Bayesian optimization (BO) algorithms to accelerate the optimization of a target objective function by exploiting correlated auxiliary information of binary type that can be more cheaply obtained, such as in policy search for reinforcement learning and hyperparameter tuning of machi…
A new method for evaluating and selecting policies in contextual bandits improves confidence intervals and policy quality.
problem Evaluating and selecting policies in contextual bandits with logged data.
method Self-normalized Importance Weighting (SN) estimator with Efron-Stein tail inequality and multiplicative bias control.
result The method provides tighter confidence intervals and better policy selection compared to competitors.
PTSD improves neural samplers by combining diffusion models and PT, enhancing efficiency.
problem Efficiency and correlation issues in neural samplers compared to PT.
method Sequential training of diffusion models across temperatures, combining high-temperature models for approximate lower-temperature samples.
result Significantly improved target evaluation efficiency, outperforming diffusion-based samplers.
BIS uses bandits to efficiently sample from expensive-to-evaluate densities.
problem Sampling from computationally expensive target densities.
method Sequential selection through multi-armed bandits, optimizing sample set directly.
result BIS achieves accurate sampling with fewer evaluations than adaptive methods.
With the increasing variety of services that e-commerce platforms provide, criteria for evaluating their success become also increasingly multi-targeting. This work introduces a multi-target optimization framework with Bayesian modeling of the target events, called Deep Bayesian Multi-Target Learning (DBMTL). In this f…
We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and correctly incorporates techniques from importance weighting, doubly robust evaluation, and nonstationary policy evaluation approaches. In a…
TERA method speeds up derivative Gaussian processes in high dimensions.
problem High-dimensional function evaluations and gradient computations are computationally expensive.
method TERA uses exact gradient reduction to decouple n and d from the computational cost. result TERA achieves state-of-the-art predictive accuracy with orders of magnitude faster computation.
This paper bridges the gap between theoretical and practical OPE for bandit problems.
problem Estimating the value of a target policy from samples generated by different policies.
method Categorizing OPE situations based on evaluation policy properties, proposing a meta-algorithm.
result Meta-algorithm successfully bridges the gap between theoretical and practical OPE for bandit problems.
Concept-driven OPE reduces variance in off-policy decision evaluation.
problem High variance in off-policy decision evaluation due to limited sample sizes.
method Integrating human-explainable concepts into OPE to reduce variance.
result Concept-based OPE estimators remain unbiased and reduce variance when concepts are known and predefined.
This paper analyzes the difficulty of unsupervised domain adaptation using information theory.
problem The challenge of unsupervised domain adaptation under covariate shift.
method Formulates the problem using a distribution π in the ground-truth triples (p, q, f), defines optimal learner performance, and introduces PTLU for quantifying difficulty.
result Characterizes the optimal learner and introduces PTLU as a measure of UDA difficulty.
Active testing for large language models is made more efficient and accurate.
problem Efficient evaluation of large language models with limited labels.
method Cost-saving measures and in-context learning for constructing a surrogate model.
result Significantly more accurate evaluations of LLM performance compared to random data acquisition.
SIREN protocol corrects optimistic winner's scores in LLM evaluation.
problem Optimistic winner's scores in LLM evaluation due to adaptive benchmarking.
method SIREN protocol that freezes post-search shortlist, separates selection and evaluation, and uses bootstrap for uncertainty quantification.
result SIREN provides valid confidence intervals for procedure-performance curves and deployment conclusions.
Develops a new method for learning discrete distributions without embedding them in a continuous space.
problem Challenges in learning discrete distributions using current methodologies.
method Introduces a MAD invertible map and a mixed variational flow (MAD Mix) for discrete distributions.
result MAD Mix produces more reliable approximations than continuous-embedding flows.
The paper analyzes the sample complexities for policy evaluation with linear function approximation.
problem Policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
method Investigates sample complexities for two policy evaluation algorithms: TD and TDC.
result Establishes high-probability sample complexity bounds for policy evaluation algorithms.
This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history generated by unknown behavioral policies. We study a regression-based fitted Q iter…
In many real-world scenarios where data is high dimensional, test time acquisition of features is a non-trivial task due to costs associated with feature acquisition and evaluating feature value. The need for highly confident models with an extremely frugal acquisition of features can be addressed by allowing a feature…
The paper targets optimal interventions for long-term outcomes using imputed data and policy learning.
problem Maximizing long-term outcomes observed only in the future.
method Imputing missing long-term outcomes and using a doubly-robust approach for policy evaluation and optimization.
result The approach outperforms simple short-term proxies and achieves significant revenue impact over three years.
The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal difference (TD) learning algorithms and provide theoretical analysis on their conver…
New algorithms for model selection in off-policy evaluation of reinforcement learning.
problem Hyperparameter tuning for off-policy evaluation methods in reinforcement learning.
method Developed new model-free and model-based selectors with theoretical guarantees and a new experimental protocol.
result New model-free selector, LSTD-Tournament, demonstrates promising empirical performance.
A new MCMC method combines low and high-fidelity models to reduce computation.
problem Inefficient computation of expensive target densities in scientific applications.
method Pseudo-marginal MCMC approach using a telescoping series of low-fidelity models.
result Asymptotically exact multi-fidelity MCMC algorithms for reduced computational cost.
Paper develops IV method for consistent OPE in confounded MDPs.
problem Confounding variables in observational data affect OPE effectiveness.
method Instrumental variable approach for consistent off-policy evaluation.
result IV method enables correct identification of target policy's value.