DistPre predicts traffic speeds efficiently for large networks.
problem Fine-grained, accurate speed prediction for large-scale transportation networks.
method Customizes LSTM models on a cluster, sharing trained models between detectors.
result Efficient and accurate fine-grained traffic-speed prediction.
LS-PLM predicts ad clicks from large scale sparse data.
problem Predicting click-through rates (CTR) from large scale nonlinear sparse data.
method Formulated with L1 and L2,1 regularizers, solved with directional derivatives and quasi-Newton method, and distributed on hundreds of machines. result Captures nonlinear patterns from massive sparse data, reducing feature engineering.
New model scales GP regression for large datasets with consistent predictions.
problem Scaling Gaussian process regression to large datasets with inconsistent predictions.
method Generalized Robust Bayesian Committee Machine, combining predictions from distributed experts in a consistent manner.
result The new model provides consistent predictions that converge to the true underlying function as training size increases.
DALC customizes LSTM models for detectors in large-scale traffic networks.
problem Fine-grained traffic prediction for large-scale transportation networks.
method Formulated as a finite Markov decision process, introduced ALC algorithm for automatic customization, and developed DALC for distributed customization.
result DALC provides higher prediction accuracy than Apache Spark MLlib approaches.
Efficiently trains large-scale ordinal regression models using DCD.
problem Efficiently training large-scale ordinal regression models.
method Dual coordinate descent method (DCD) for training and a new prediction function.
result Extensive experiments show the DCD method is suitable for large-scale data.
Many real-world regression problems demand a measure of the uncertainty associated with each prediction. Standard decision forests deliver efficient state-of-the-art predictive performance, but high-quality uncertainty estimates are lacking. Gaussian processes (GPs) deliver uncertainty estimates, but scaling GPs to lar…
Deep neural networks provide meaningful uncertainty estimates for large-scale simulations.
problem Uncertainty estimates for deep neural network predictions from large-scale simulations.
method General variational inference approach to calibrate Bayesian uncertainties.
result Calibrated Bayesian uncertainties preserved physics-correlations in predicted quantities.
A new kernel, Isolation Kernel, simplifies large scale online kernel learning without sacrificing accuracy.
problem Building efficient and scalable kernel-based models from large datasets with high accuracy.
method Introducing Isolation Kernel, which creates an exact, sparse, and finite-dimensional feature map of a kernel, allowing for efficient large scale online kernel learning without accuracy loss.
result Large scale online kernel learning can be achieved efficiently and accurately using Isolation Kernel.
We propose a method to visualize class similarity in large-scale classifiers.
problem Analyzing hierarchical structures and relationships in large-scale classification.
method Compute class similarity based on prediction scores and visualize the class similarity matrix.
result Visualizing class similarity matrices reveals hierarchical structures and relationships.
Study compares N-gram and RNN models for chord prediction on large datasets.
problem Improving chord prediction accuracy and adaptability in music.
method Compared N-gram models to various RNN architectures on multiple datasets.
result RNN models adapt to songs at test time, improving chord prediction.
Study shows curiosity-driven learning can perform well without extrinsic rewards.
problem Lack of scalable methods for intrinsic reward design in reinforcement learning.
method Performed a large-scale study of curiosity-driven learning across 54 environments, using prediction error as reward.
result Curiosity-driven learning can achieve good performance without extrinsic rewards, aligning with hand-designed rewards in many cases.
New algorithm improves ad targeting for personalized online services.
problem Personalizing online services for improved user experience and revenue.
method Label ranking approach for non-linear, large-scale prediction of user interests.
result The proposed algorithm outperforms existing solutions in rank loss and top-K retrieval.
We propose a nonparametric approach to link prediction in large-scale dynamic networks. Our model uses graph-based features of pairs of nodes as well as those of their local neighborhoods to predict whether those nodes will be linked at each time step. The model allows for different types of evolution in different part…
Transformers learn to predict chess moves with surprising accuracy and strength.
problem Training transformers on chess to predict moves accurately.
method Large-scale chess dataset (10M games), supervised learning with up to 270M parameters.
result Transformers can predict action-values for novel boards with high accuracy.
Bayesian Temporal Factorization predicts multidimensional time series with missing data.
problem Predicting large-scale, multidimensional spatiotemporal data with missing values.
method Integrates low-rank matrix/tensor factorization and VAR process into a probabilistic model.
result Superior performance on real-world spatiotemporal data sets compared to existing methods.
Paper improves Native ads CTR prediction using event embeddings and recurrent networks.
problem Hard CTR prediction for Native ads due to lack of direct query intent.
method Proposes a large-scale event embedding scheme and a recurrent neural network model.
result Significantly outperforms baseline and variants in CTR prediction.
New method uses weak labels to create valid confidence sets for predictions.
problem Lack of labeled data in machine learning models.
method Developed a conformal prediction framework to provide valid predictive confidence sets using weakly labeled data.
result New coverage definition allows for tighter and more informative (but valid) confidence sets.
CNN predicts traffic speeds from images of traffic flow.
problem Predicting large-scale traffic speeds in transportation networks.
method Converts spatiotemporal traffic data into images, then uses CNN for feature extraction and speed prediction.
result The method outperforms other algorithms by 42.91% in accuracy.
Researchers parallelize neural kernels for large-scale data, achieving state-of-the-art accuracy.
problem Limited scalability of neural kernels on large datasets.
method Massively parallel computation across many GPUs, combined with a distributed, preconditioned conjugate gradients algorithm.
result Achieved state-of-the-art accuracy of 91.2% on CIFAR-5m dataset using neural kernels.
Proposes DMVST-Net for taxi demand prediction.
problem Improving taxi demand prediction for smart city resource allocation.
method Deep Multi-View Spatial-Temporal Network (DMVST-Net) combining LSTM, CNN, and semantic views.
result Demonstrates effectiveness over state-of-the-art methods on large-scale taxi demand data.
New method adds interactions to interpretable models for large-scale data.
problem Limited model complexity and lack of interactions in interpretable models.
method Factorization method to derive scalable higher-order tensor product spline models.
result Incorporates all higher-order interactions of non-linear feature effects without computational penalties.
PGBM creates probabilistic predictions efficiently.
problem Creating probabilistic predictions for large-scale data.
method Approximates leaf weights as random variables, learns moments via stochastic tree ensemble update equations.
result PGBM offers significant speedup and accuracy improvements over existing methods.
Post-processes deep networks with StoNet to quantify uncertainty.
problem Uncertainty quantification in predictions from large-scale deep neural networks.
method Feeds DNN output into StoNet, trains StoNet with sparse penalty, constructs prediction intervals.
result Proposed approach constructs honest confidence intervals with shorter lengths and better calibration.
Augments graph node features to improve GNN performance.
problem Improving graph neural networks' performance on large-scale datasets.
method Iteratively augments node features with gradient-based adversarial perturbations.
result Boosts model performance in node classification, link prediction, and graph classification tasks.
A new algorithm predicts periodic time series data efficiently in cloud environments.
problem Efficiently identifying and predicting periodic patterns in large-scale time-series data.
method Proposes a Periodicity-based Parallel Time Series Prediction (PPTSP) algorithm using TSDCA, MTSPPR, and PTSP methods.
result Significant improvements in prediction accuracy and performance compared to existing algorithms.
Paper introduces models to discover complex structures in large hypergraphs.
problem Understanding dependency structures in complex systems represented as hypergraphs.
method Probabilistic models treating classes of similar units as nodes in a latent hypergraph, using low-rank representations.
result Improves link prediction and discovers interpretable structures in diverse real-world systems.
Semi-supervised GANs improve travel mode inference from GPS data.
problem Travel mode inference from GPS trajectories.
method Developed semi-supervised GANs and compared them with CNNs on a large-scale smartphone dataset.
result Best semi-supervised GAN model achieved 83.4% prediction accuracy.
SVM predicts regional rainfall with varying accuracy, best in central US.
problem Regional rainfall prediction for social and economic impact planning.
method Support Vector Machine (SVM) applied to sequences of daily rainfall maps.
result SVM predictions for central region outperform untrained classifier.
Efficient multi-label classifier handles missing labels and large datasets.
problem Handling large-scale datasets with many instances and labels, missing label assignments, label correlations, and unlabeled data.
method Non-linear embedding of label vectors using a stochastic approach to predict tail labels, handling missing labels, and exploiting unlabeled data.
result Our method outperforms state-of-the-art multi-label classifiers in prediction performance and training time.
Study predicts individual treatment effects in ride-sharing competitions.
problem Understanding how team competitions affect individual drivers' outcomes.
method Analyzed data from 500 competitions, built machine learning models.
result Reduced out-sample prediction error by over 24%.
The paper analyzes instability in large-scale machine learning models.
problem Unexpected instability and variance in neural predictive algorithms.
method Measuring changes in geometric models with output consistency and topological stability.
result Identifying the influence of data points, approximation methods, and parameter settings on model stability.
We propose a new two stage algorithm LING for large scale regression problems. LING has the same risk as the well known Ridge Regression under the fixed design setting and can be computed much faster. Our experiments have shown that LING performs well in terms of both prediction accuracy and computational efficiency co…
Method analyzes large-scale network data to detect communication pattern shifts.
problem Analyzing large-scale time-series network data is challenging.
method Temporal encoder embedding method using ground-truth or estimated vertex labels.
result Detects communication pattern shifts across all levels of network structure.
A novel approach calibrates Gaussian process for fast large-scale classification.
problem Deriving fast and accurate classification algorithms with uncertainty quantification.
method Applying Gaussian process regression to classification labels and calibrating predictions.
result The proposed approach provides similar accuracy and uncertainty quantification as Gaussian process classification but with significantly reduced computational resources.
Unified model predicts structure of neural network loss landscapes.
problem Understanding the structure of neural network loss landscapes.
method Modeling loss landscape as high-dimensional wedges, analyzing hyperparameters' effects.
result Existence of low-loss subspaces connecting solutions.
Improved MPC with neural networks and active sets for large-scale problems.
problem Large-scale model predictive control with guarantees on feasibility and stability.
method Combines offline-trained neural network and online primal active set solver.
result Achieves 2x reduction in online inference time for large problems.
Efficiently maps indoor magnetic fields with SKI and D-SKI.
problem Computing large-scale magnetic field maps in indoor environments.
method Structured kernel interpolation (SKI) with derivatives (D-SKI) for Gaussian process regression.
result Achieves better accuracy and faster computation than state-of-the-art methods.
This paper surveys large-scale machine learning methods for efficient data analysis.
problem Efficiently processing large-scale data with machine learning models.
method Divided into three categories: model simplification, optimization approximation, and computation parallelism.
result Blueprint for future developments in large-scale machine learning.
Space-efficient feature maps improve string alignment kernel scalability.
problem String alignment kernels scale poorly with quadratic complexity, limiting large-scale applications.
method Presented SFMEDM, a space-efficient feature map for edit distance with moves using metric embedding and random Fourier features.
result Demonstrated superior performance of SFMEDM in prediction accuracy, scalability, and computation efficiency.
Reanalysis of bioactivity prediction models suggests SVM performance is competitive with deep learning.
problem Benchmarking and validation of machine learning models in drug discovery.
method Reanalysis of a large-scale comparison of machine learning models for bioactivity prediction, using numerical experiments to question ROC curve relevance and suggest precision-recall curve.
result Support vector machines show competitive performance with deep learning methods in bioactivity prediction.
A new method for large-scale GP regression using seamless patching of local models.
problem Boundary discontinuity issue in local partitioned GP models.
method Partitioning input domain into local regions, applying different local GP models, and ensuring seamless patching with pseudo-observations.
result Mitigates boundary discontinuity problem, leading to improved accuracy and predictive uncertainty.
FNO model predicts GCS pressure fields with 81% less data, even with limited high-fidelity data.
problem Accurate prediction of complex physical behaviors in large-scale 3D geological carbon storage problems with limited data.
method Multi-fidelity Fourier Neural Operator (FNO) for efficient training with multi-fidelity datasets.
result Multi-fidelity FNO model predicts pressure fields with reasonable accuracy even with limited high-fidelity data.
This research improves HC classification speed and memory usage with feature selection.
problem Large-scale HC datasets with high-dimensional features.
method Filter-based feature selection methods for dimensionality reduction.
result Up to 3x speed-up and 45% less memory usage on massive datasets.
Develops a deep clustering framework for large-scale road traffic prediction.
problem Challenges in modeling diverse traffic patterns and handling high-dimensional time series with low latency.
method Combines deep clustering with CNNs and RNNs to predict road traffic at large-scale networks.
result The DeepCluster framework effectively clusters road segments and improves prediction performance.
GLACE embeds large-scale attributed graphs effectively, preserving structure and attributes.
problem Uncertainty and complexity in large-scale attributed graphs.
method Gaussian embeddings for scalable and efficient graph embedding.
result GLACE outperforms state-of-the-art methods on multiple graph analysis tasks.
New method selects variables for nonlinear regression in large datasets.
problem Nonlinear regression with large-scale datasets.
method Kernel-based variable selection with random features.
result Outstanding performance on large-scale synthetic and real datasets.
Researchers use interpretable classifiers to predict antibiotic resistance.
problem Predicting antibiotic resistance from genome sequences.
method Set Covering Machines for highly interpretable models.
result Highly interpretable models for antibiotic resistance prediction.
Efficiently trains large CNN models for hashtag prediction.
problem Training large CNN models with limited GPU memory.
method Hard mixture of experts model trained in parallel.
result Large scale models trained with minimal fragmentation.