Optimizes crowdsourced preference-based subjective evaluation with online learning.
problem Large-scale evaluation of generative media using crowdsourcing due to combinatorial explosion.
method Automatic optimization of pair combination selections and evaluation volumes with online learning.
result Optimizes evaluation by reducing pair combinations and allocating optimal evaluation volumes.
Cramming method evaluates learned policies from contextual bandits efficiently.
problem Evaluating final learned policies from contextual bandit algorithms.
method On-policy evaluation using a single pass of data, ensuring consistency and asymptotic normality.
result Cramming method reduces evaluation standard error by approximately 40% compared to off-policy methods.
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.
New method extends fitted Q-evaluation for distributional off-policy reinforcement learning.
problem Estimating return distribution in reinforcement learning using offline data.
method Developed a set of guiding principles and new FDE methods with theoretical justification.
result FDE methods outperform existing approaches in simulations and real-world games.
Study evaluates saliency maps on artificial data with different backgrounds.
problem Objective evaluation of saliency methods on artificial data with varying backgrounds.
method Developed a framework to generate artificial data with synthetic lesions and a known ground truth map, evaluated two data sets with different backgrounds (Perlin noise and 2D brain MRI slices).
result Heatmaps vary strongly between saliency methods and backgrounds.
This paper evaluates and validates cluster results using external and internal evaluation methods.
problem Evaluating and validating the quality of clustering results.
method External evaluation using Homogeneity, Correctness, and V-measure scores; internal evaluation using Silhouette Index and Sum of Square Errors.
result Validation of the number of clusters using dendrogram and statistical frequency distribution.
We extend an offline evaluation method for continuous-armed bandits.
problem Evaluating policies in continuous-armed bandits with limited data.
method Extend existing offline evaluation method for continuous-armed bandits.
result Our method provides a consistent ranking of policies.
The paper critiques current time series classification evaluation methods.
problem Current performance evaluation methods in time series classification are criticized.
method No specific new method proposed, but a critical analysis of existing methods.
result Suggests a need for discussion and reflection on TSC performance evaluation.
Enhances BLEU for better SMT evaluation.
problem Improving BLEU for more human-like evaluation of machine translations.
method Adapts BLEU to consider synonyms, word order, and style variations in human translations.
result Improves SMT evaluation metrics and correlates with human translation quality.
Paper proposes metrics to evaluate AI explanations without ground truth.
problem Challenges in evaluating neural network explanations without ground truth.
method Designs four metrics to evaluate explanation results.
result New insights into neural network interpretation methods.
Paper discusses methods to evaluate defenses against adversarial examples.
problem Difficulty in evaluating adversarial robustness.
method Methodological foundations and best practices for evaluating defenses.
result Suggests new methods to avoid common pitfalls in evaluations.
Unified evaluation framework for sampling methods.
problem Lack of a standardized evaluation framework for sampling methods.
method Introduces a benchmark suite and performance criteria for sampling methods.
result Insights into strengths and weaknesses of existing sampling methods.
Paper develops a method to highlight influential transitions for off-policy evaluation.
problem Validating off-policy evaluation in high-stakes settings.
method Highlight influential transitions, develop influence functions for Q-evaluation.
result Method can identify limitations and make evaluation more robust.
This paper considers the challenge of evaluating a set of classifiers, as done in shared task evaluations like the KDD Cup or NIST TREC, without expert labels. While expert labels provide the traditional cornerstone for evaluating statistical learners, limited or expensive access to experts represents a practical bottl…
The paper presents methods to improve policy evaluation in reinforcement learning.
problem Policy evaluation in reinforcement learning with linear function approximation.
method Transformed into a convex-concave saddle point problem, primal-dual batch gradient method, and two stochastic variance reduction methods.
result Achieved linear convergence even with only strong concavity in dual variables.
Method selects best estimator for off-policy evaluation.
problem Choosing the best estimator for off-policy evaluation.
method Generic data-driven method for estimator selection.
result Method is competitive with oracle estimator, up to a constant factor.
New saliency evaluations focus on completeness and soundness, improving explanations.
problem Current saliency evaluations focus on completeness but ignore soundness.
method Introduces new intrinsic evaluation metrics based on completeness and soundness.
result Simple saliency method matches or outperforms prior methods in new evaluations.
New method improves consistency of reinforcement learning performance evaluations.
problem Inconsistent performance results in reinforcement learning due to flawed evaluation metrics.
method Proposes a new comprehensive evaluation methodology for reinforcement learning algorithms.
result Demonstrates improved reliability of performance measurements for reinforcement learning algorithms.
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
We consider evaluation methods for payoffs with an inherent financial risk as encountered for instance for portfolios held by pension funds and insurance companies. Pricing such payoffs in a way consistent to market prices typically involves combining actuarial techniques with methods from mathematical finance. We prop…
New method for evaluating LLMs reduces bias in open-ended evaluations.
problem Bias in Elo-based ratings of LLMs due to data redundancies.
method Proposes evaluation as a 3-player game and introduces novel solution concepts.
result Novel method leads to more robust and intuitive ratings.
Paper proposes a method to efficiently test rare vehicle failures using kernel methods.
problem Efficiently test rarely occurring but critical vehicle failures.
method Uses kernel methods to approximate and construct sampling distributions for rare event sets.
result Proposed method robustly identifies rare vehicle failures and significantly reduces evaluation time.
HOIST uses multiple surrogates to optimize DNN hyperparameters efficiently.
problem Insufficient evaluation data for Bayesian optimization of DNN hyperparameters.
method HOIST combines complete and intermediate evaluation data using weighted bagging of multiple surrogates.
result HOIST outperforms state-of-the-art approaches on various DNN types.
Study evaluates human vs. machine review generation, finds human assessments correlate better with lexical overlaps.
problem Evaluating natural language generation models for online reviews is challenging and inconsistent.
method Compared human evaluators with various automated evaluation methods, including discriminative and word overlap metrics.
result Human evaluators do not correlate well with discriminative evaluators, but correlate better with lexical overlaps.
Paper improves bootstrapping for off-policy reinforcement learning inference.
problem Improving bootstrapping for off-policy reinforcement learning inference.
method Proposes a bootstrapping FQE method for off-policy statistical inference and a subsampling procedure to improve runtime.
result Asymptotically efficient and distributionally consistent bootstrapping FQE method for off-policy inference.
New models can't beat existing ones, so debiasing methods only slightly reduce needed labels.
problem Limiting scalability in model evaluation due to self-preferencing biases.
method Study of debiasing methods using a few high-quality labels to reduce model judgments.
result Debiasing methods can't decrease required ground truth labels by more than half when the judge is no more accurate than the model.
Develops framework to evaluate feature attribution methods.
problem Lack of ground truth for evaluating feature attribution methods.
method Proposes a framework including a dataset and metrics.
result Certain methods produce false positive explanations.
This paper compares and evaluates methods for evaluating statistical models using benchmarking data and simulations.
problem Choosing between benchmarking data sets and simulation studies for method comparison studies.
method Borrowing ideas from mixed methods research and Clinical Scenario Evaluation, the paper investigates and develops new approaches to evaluate methods.
result Develops new approaches to evaluate methods by combining the strengths of benchmarking data sets and simulation studies.
AVATAR uses a surrogate model to quickly evaluate ML pipelines, saving time and resources.
problem Time-consuming evaluation of ML pipelines limits exploration of complex models.
method AVATAR employs a surrogate model to assess pipeline validity without execution.
result AVATAR accelerates ML pipeline evaluation, improving efficiency in complex scenarios.
The article reviews scoring rules for estimating and evaluating forecasts.
problem Evaluating probabilistic forecasts and estimating probability distributions.
method Mathematical foundations and characterization of scoring rules.
result Important families of scoring rules and their applications in statistics and machine learning.
New method evaluates policies with latent confounders using optimal balance.
problem Evaluating policies with unobserved confounders in costly exploration scenarios.
method Importance weighting method to avoid latent outcome regression, minimizing adversarial balance objective.
result Provable consistency in policy evaluation with latent confounders, demonstrated empirically.
New framework assesses graph-learning datasets for better evaluation.
problem Insufficient evaluation of graph-learning datasets and methods.
method Introduces Rings framework for dataset ablations and proposes performance separability and mode complementarity measures.
result Demonstrates utility of Rings framework for graph-learning dataset evaluation.
SVRG reduces gradient evaluations for policy evaluation in reinforcement learning.
problem Policy evaluation in reinforcement learning with high computational costs.
method Two variants of SVRG for policy evaluation that reduce gradient calculations.
result Significant reduction in the number of gradient evaluations while preserving linear convergence speed.
Proposes standards for evaluating online machine learning methods in evolving data streams.
problem Difficulty in evaluating online machine learning methods under realistic conditions.
method Proposes comprehensive evaluation standards, performance measures, and evaluation strategies.
result Provides a new Python framework (float) for modular integration of libraries and custom code.
Adversarial method finds rare catastrophic failures in safety-critical agents.
problem Evaluating safety-critical learning systems for catastrophic failures.
method Adversarial evaluation approach focusing on rare adversarial situations.
result Adversarial evaluation finds catastrophic failures and estimates failure rates faster.
First differentially private off-policy evaluation method.
problem Privacy leakage in reinforcement learning using sensitive data.
method Differential privacy approach for off-policy evaluation.
result Empirically outperforms previous methods in speed of convergence.
Study shows refugee matching gains are robust to different evaluation methods.
problem Stability of refugee matching gains under various evaluation methods.
method Used multiple off-policy evaluation methods including IPW and AIPW.
result Impact estimates remain consistent in magnitude and statistically significant.
New method evaluates feature interactions using orthogonal variance decomposition.
problem Feature selection fails to account for interactions between features.
method Orthogonal variance decomposition to evaluate feature subsets considering interactions.
result Our method accurately identifies relevant features and improves model accuracy.
Adaptive loss function improves performance by aligning training and evaluation metrics.
problem Loss-metric mismatch in machine learning training.
method Adaptive loss alignment through meta-learning of a dynamic loss function.
result Significant performance improvements across various tasks and data.
Generative AI reduces IR evaluation costs but introduces errors; this work provides reliable CIs.
problem Generating relevance annotations using AI introduces errors that affect IR evaluation metrics.
method Proposes two methods: prediction-powered inference and conformal risk control to place reliable CIs around IR metrics.
result Proposed methods accurately capture both variance and bias in evaluation based on AI-generated annotations.
Paper proposes benchmarks and metrics for evaluating handwriting generation.
problem Evaluating the style of handwriting generation is challenging.
method Deep learning techniques for generating temporal sequences.
result Proposes evaluation metrics for handwriting generation.
New approach for pricing evaluation improves on existing methods.
problem Improving off-policy evaluation for personalized pricing.
method Balanced policy evaluation framework with worst-case optimization.
result Empirical advantage over existing methods in pricing applications.
Paper benchmarks adversarial robustness methods on image classification.
problem Vulnerability of deep neural networks to adversarial examples.
method Established a comprehensive benchmark with robustness curves.
result Found important findings on adversarial attack and defense methods.
Language model benchmarks often misrepresent true understanding, revealing vulnerabilities in evaluation methods.
problem Language model benchmarks fail to accurately reflect true language understanding and adaptability.
method Systematic analysis of NLP evaluation frameworks, identifying vulnerabilities in static benchmarks, human evaluation protocols, and LLM-as-judge frameworks.
result Current evaluation methods are unreliable and need improvement to accurately assess LLM performance.
Develops a theoretical framework for fair feature selection method evaluation.
problem Unfair comparisons between feature selection methods due to varying evaluation methods.
method Theoretical framework based on mutual information for feature ordering.
result Undoubtful comparison of feature selection methods independent of estimation methods, classifiers, and datasets.
AHS framework selects hyperparameters for FQE with error guarantees.
problem Hyperparameter selection for FQE is challenging and affects its utility.
method AHS framework defines optimality criteria without hyperparameters.
result Error bounds match empirical observations.
Paper assesses uncertainty in safety evaluation of self-driving tech.
problem Estimating uncertainty in safety-critical event probabilities.
method Combines bootstrap method and likelihood ratio scheme for input uncertainty assessment.
result Demonstrates the impact of data variability on safety evaluation estimates.
New method learns to encode predictions within interpretations, improving evaluation.
problem Need for interpretable machine learning, but existing methods are slow or lack fidelity.
method Amortized explanation methods that learn a global selector model optimizing fidelity of interpretations.
result Predictions can be encoded within interpretations, detected by EVAL-X.