AirRL uses RL to infer urban air quality from selected stations.
problem Inferring fine-grained urban air quality from limited monitoring stations.
method Reinforcement learning model with a dynamic station selector and air quality regressor.
result AirRL achieves highest performance in air quality inference experiments.
Do-AIQ framework evaluates AI algorithms' quality using DOE.
problem Quality evaluation of AI mislabel detection algorithms.
method Design-of-experiment approach with high-dimensional constraint space design and surrogate modeling.
result Established framework for evaluating AI algorithm quality robustly.
New methods improve insurance data quality for catastrophic events.
problem Improving precision and size of insurance data for catastrophic events.
method Bootstrap, bootknife, and GAN algorithms.
result Compared MSE and MAE of simulated outputs, direct algorithm for fuzzy expert opinion.
Study compares uncertainty estimation methods for Bayesian Neural Networks.
problem Quality of uncertainty quantification in Bayesian Neural Networks.
method Empirical comparison of 10 inference methods on regression and classification tasks.
result Common inference metrics can be misleading, and methods designed to capture posterior structure do not always produce high-quality approximations.
DQV Learning uses neural networks to improve reinforcement learning performance.
problem Improving reinforcement learning algorithms for better performance.
method Temporal-difference learning with Value and Quality-value networks, using Deep Convolutional Neural Networks, Experience Replay, and Target Neural Networks.
result DQV learns faster and better than Deep Q-Learning and Double Deep Q-Learning.
Federated learning leaks participant dataset quality even with secure aggregation.
problem Leakage of participant dataset quality in federated learning with secure aggregation.
method Image recognition experiments to infer and attribute dataset quality.
result Relative quality ordering of participants can be inferred and used for various purposes.
CrossLID evaluates GAN quality by comparing intrinsic dimensions.
problem Measuring GAN quality and detecting mode collapse.
method CrossLID measures local intrinsic dimensionality of real-world data vs. GAN-generated samples.
result CrossLID correlates with GAN training progress and is robust to noise.
DKGM improves image quality by debiasing kernel-based models.
problem Improving image quality in generative models without losing detail.
method Two-stage framework: KDE for density estimation, debiasing algorithm inspired by stochastic approximation.
result DKGM achieves comparable image quality to state-of-the-art models on CIFAR10.
Generative AI boosts productivity and improves customer service quality.
problem Productivity and quality of customer support agents.
method Staggered introduction of a generative AI-based conversational assistant in customer support.
result AI increases productivity by 15% on average, with significant heterogeneity across workers.
Framework improves ML performance by identifying high-quality data.
problem Poor data quality hampers ML performance.
method Intelligent data-centric evaluation framework combining quality measurements and unsupervised learning.
result Framework improves ML system performance in real-world use case.
The paper defines and assesses the quality of datasets using a novel expected diameter metric.
problem Lack of rigorous methods to assess data quality.
method Formal definition of data quality, expected diameter metric, Fourier analysis, algebraic methods, probabilistic analysis.
result The expected diameter metric provides theoretical guarantees and practical solutions for data quality assessment.
Model infers street-level air quality using mobile station data.
problem Inferring air quality from limited mobile station data.
method Variational Graph Autoencoder for matrix completion on graph-based data.
result Model outperforms state-of-the-art approaches in air quality inference.
We use smaller proxy datasets to speed up hyperparameter search.
problem Time-consuming and costly training of neural networks on large datasets.
method Generate smaller 'proxy datasets' by sampling, training on easy/hard examples, or generating synthetic data. Compare proxy quality using variance measures.
result Proxy datasets can explain up to 95% of the variance in full dataset results, significantly faster.
Paper proposes a method to enhance low-quality retinal images using optimal transport.
problem Artifacts and imperfections in retinal images lead to diagnostic inaccuracies.
method Leveraging optimal transport theory, an unpaired image-to-image translation scheme is proposed.
result The method improves perceptually and quantitatively the quality of low-quality retinal images.
Study improves data quality assessment for structural monitoring data.
problem Ensuring reliability of structural health monitoring data.
method Probabilistic data quality assessment using a conditional diffusion model.
result Significantly improves accuracy of data quality assessment.
Paper proposes a faster, higher-quality RL method for text-to-image models.
problem Improving image quality and prompt alignment in RL post-training of text-to-image models.
method Online RL variant that reduces variance by sampling paired trajectories and optimizing flow velocity.
result Method converges faster and yields higher output quality and prompt alignment.
New SSIM measure improves adversarial attacks' perceptual quality.
problem Lack of perceptual quality in traditional adversarial attacks.
method Replaced Lp norms with SSIM measure for better quality. result SSIM-constrained attacks achieve better quality and similar success rate.
Paper proposes data quality measures for large-scale high-dimensional data.
problem Lack of practical data quality measures for large-scale high-dimensional data.
method Proposes two data quality measures: class separability and in-class variability. Efficient algorithms based on random projections and bootstrapping are provided.
result Efficient algorithms for computing data quality measures on large-scale high-dimensional data.
Reliable data quality monitoring is a key asset in delivering collision data suitable for physics analysis in any modern large-scale High Energy Physics experiment. This paper focuses on the use of artificial neural networks for supervised and semi-supervised problems related to the identification of anomalies in the d…
Cluster analysis is widely used in the areas of machine learning and data mining. Fuzzy clustering is a particular method that considers that a data point can belong to more than one cluster. Fuzzy clustering helps obtain flexible clusters, as needed in such applications as text categorization. The performance of a clu…
Automated dialogue quality evaluation using user satisfaction estimates across multiple domains.
problem Lack of automated and domain-independent dialogue quality evaluation metrics.
method Created a new Response Quality annotation scheme, introduced five domain-independent feature sets, and experimented with six machine learning models.
result Gradient Boosting Regression model achieved best prediction performance, with a 16% relative improvement in binary satisfaction class prediction accuracy.
Federated learning improves keyboard suggestions without user data.
problem Improving search suggestion quality without direct user data access.
method Applied federated learning for global-scale model training and deployment.
result Significant quality increases in search suggestions.
Algorithm improves reinforcement learning policies using offline data.
problem Improving reinforcement learning policies with limited online data.
method Designs a single non-reactive policy using offline data with provable guarantees.
result Algorithm achieves better policy quality with less online data.
New metric estimates user satisfaction for dialogue quality evaluation.
problem Sparse and intrusive explicit user feedback for dialogue quality evaluation.
method Created a new Response Quality annotation scheme and developed a turn-level User Satisfaction metric using five domain-independent feature sets and six machine learning models.
result Gradient boosting regression achieved best correlation of ~0.79 between predicted and annotated user satisfaction labels.
HDI-Forest improves regression prediction intervals using Random Forest.
problem Improving the quality of prediction intervals in regression tasks.
method HDI-Forest is a novel quality-based PI estimation method based on Random Forest, optimizing PI quality metrics directly from standard tree-based models.
result HDI-Forest significantly reduces PI width by over 20% compared to previous methods, while maintaining or improving coverage probability.
In subgroup discovery, also known as supervised pattern mining, discovering high quality one-dimensional subgroups and refinements of these is a crucial task. For nominal attributes, this is relatively straightforward, as we can consider individual attribute values as binary features. For numerical attributes, the task…
DreamPropeller accelerates text-to-3D generation by 4.7x with minimal loss in quality.
problem Long generation times in text-to-3D generation algorithms degrade user experience.
method DreamPropeller uses Picard iterations generalized for non-ODE paths to accelerate parallel sampling.
result Empirically achieves up to 4.7x speedup with negligible quality loss.
Study examines how classifier performance is affected by training data quality.
problem How classifier performance is affected by training data quality.
method Extensive numerical experiments with four classifiers (Bayes, neural nets, partition models, random forests) on metagenomic assembly data.
result Classifier performance degrades as training data quality degrades, leading to breakdown-like behavior.
VILD learns policies from mixed-quality demonstrations by modeling expert levels.
problem Challenges in learning from diverse-quality demonstrations.
method Explicitly models expert levels with a probabilistic graphical model and variational approach.
result VILD outperforms state-of-the-art methods in continuous-control benchmarks.
This paper optimizes survey questions to reduce bias and select key tokens for QoE analysis.
problem Reducing bias in user surveys and selecting informative tokens for Quality of Experience analysis.
method Randomized question order and greedy submodular maximization for selecting tokens.
result Randomizing token order can significantly reduce bias, and a subset of 30% tokens captures 94% of the information.
New method improves GAN training stability and quality.
problem Improving training stability and sample quality in GANs.
method Proposes a new method for Lipschitz continuity in GANs that is efficient and unbiased.
result Demonstrates the effectiveness of the new method in various GAN training scenarios.
A simple whitening method improves disentanglement in VAEs without sacrificing reconstruction quality.
problem Learning disentangled latent variables in VAEs.
method Proposes a whitening-based approach to disentangle latent variables in VAEs.
result The method finds interpretable latent factors without compromising reconstruction quality.
Theoretical analysis of data quality and synergies in LLMs.
problem Understanding why different training methods require different amounts of data.
method Theoretical analysis of transformers trained on a weight prediction task for linear regression.
result SFT excels on smaller datasets challenging for the pretrained model, while RL benefits from large, not overly difficult data.
REP-GAN improves GANs by reparameterizing proposals for better sample quality and efficiency.
problem Poor sample efficiency in GANs due to independent proposal sampling.
method REParameterizing Markov chains into the latent space of the generator to create dependent proposals.
result Empirically shows significant improvement in sample efficiency and quality.
Study compares crowdsourcing with lab experiments using comparison-based psychophysics.
problem Improving data quality in crowdsourcing psychophysics experiments.
method Comparison-based psychophysics, machine learning for triplet prediction.
result Accuracy of crowdsourcing psychophysics close to lab experiments.
Bayesian neural networks quantify uncertainties in molecular property predictions.
problem Poor predictions in molecular property predictions due to unreliable training data.
method Bayesian neural networks to estimate model-driven and data-driven uncertainties.
result Uncertainty quantification is necessary for reliable molecular applications.
Deep learning improves handwriting style transfer and extraction.
problem Improving handwriting style transfer and extraction using deep neural networks.
method Used a deep conditioned autoencoder on IRON-OFF handwriting data-set to explore style transfer and extraction.
result Improved metrics of state-of-the-art methods by a large margin in style transfer and extraction experiments.
Online audio advertising is a particular form of advertising used abundantly in online music streaming services. In these platforms, which tend to host tens of thousands of unique audio advertisements (ads), providing high quality ads ensures a better user experience and results in longer user engagement. Therefore, th…
Improves labeling quality in machine learning with pairwise feedback.
problem Scalability and quality of labeled datasets in machine learning.
method Incorporates pairwise feedback into the programmatic creation of labeled datasets.
result Even a small number of pairwise feedback sources can substantially improve label quality.
Paper tackles noisy annotations by considering workers' attention levels.
problem Noisy annotations from workers with varying expertise.
method Proposes a probabilistic model that incorporates workers' attention for accurate label quality estimation.
result Improves aggregated labels by quantifying the relationship between workers' attention and label quality.
The pairwise influence matrix of Dobrushin has long been used as an analytical tool to bound the rate of convergence of Gibbs sampling. In this work, we use Dobrushin influence as the basis of a practical tool to certify and efficiently improve the quality of a discrete Gibbs sampler. Our Dobrushin-optimized Gibbs samp…
Stabilizes training of DNN for speech enhancement using PESQ scores.
problem Stability issues in training DNNs using non-differentiable OSQA scores.
method Approximate OSQA scores with a differentiable auxiliary DNN and stabilize training with reinforcement learning techniques.
result Stable training of DNN to achieve state-of-the-art PESQ scores and better sound quality.
Study subjective perception of low light restored images and develop an unsupervised QA model.
problem Lack of subjective QA for low light restored images and challenges in collecting human opinion scores.
method Create a dataset, conduct subjective QA study, develop self-supervised contrastive learning technique to extract features.
result Unsupervised NR QA model achieves state-of-the-art performance for low light restored images.
Engine forecasts NO2, O3, PM2.5, PM10 with high accuracy.
problem Accurate long-term air quality forecasting.
method Convolutional LSTM network trained on grid data.
result 4-day forecasts significantly outperform simple benchmarks.
New framework selects high-quality pretraining data without training LLMs.
problem Slow progress in understanding pretraining data due to costly experiments.
method Statistical framework based on perplexity-benchmark correlations.
result Approach outperforms existing methods on multiple benchmarks.
The multilingual nature of the world makes translation a crucial requirement today. Parallel dictionaries constructed by humans are a widely-available resource, but they are limited and do not provide enough coverage for good quality translation purposes, due to out-of-vocabulary words and neologisms. This motivates th…
New measure assesses time series pre-training data quality without labels.
problem Challenges in collecting diverse pre-training datasets for time series classification.
method Contrastive-learning-based foundation model and contrastive accuracy measure.
result Contrastive accuracy correlates with model performance on downstream tasks.
Early stopping improves sample quality in latent diffusion models.
problem Latent diffusion models degrade sample quality with conventional early stopping.
method Analyzed the interaction between latent dimension and stopping time under Gaussian framework.
result Lower-dimensional representations benefit from earlier termination, higher-dimensional spaces require later stopping.