A new method for support vector regression using a data-driven insensitive parameter.
problem Determining an optimal insensitive parameter in support vector regression.
method A data-driven approach to approximate the insensitive parameter by minimizing a generalized loss function based on the likelihood principle.
result The proposed method outperforms traditional support vector regression methods and has lower computational costs.
New method identifies physical processes and parameters from data.
problem Current data-driven methods assume known or linear model parameters, limiting realistic process identification.
method Combines data-driven and data-assimilation methods for simultaneous process and parameter identification.
result Successfully identifies physical processes and infers model parameters for nonlinear models.
New method uses FY loss for better inverse optimization.
problem Estimating unknown parameters from noisy and suboptimal solutions.
method Fenchel-Young loss approach for efficient gradient-based optimization.
result Significant improvement in parameter estimation accuracy and computational speed.
Framework improves data-driven ROMs for complex systems using Bayesian operator inference.
problem Improving the quality of data-driven reduced-order models for complex dynamical systems.
method Develops an active learning framework using Bayesian operator inference to identify and select training parameters.
result The proposed adaptive sampling strategy consistently yields more stable and accurate ROMs than random sampling.
The article analyzes machine learning methods for simultaneous parameter estimation in econometrics.
problem Estimating effects of many-valued treatments and treatment effects for many groups.
method Regularized estimation and data-driven choices of regularization parameters.
result Data-driven choices of regularization parameters yield estimators with risk close to optimal.
Study integrates machine learning with SAA for optimizing decisions based on uncertain parameters and covariates.
problem Optimizing decisions under uncertain parameters and covariates.
method Data-driven frameworks integrating machine learning prediction models within SAA for scenario generation.
result Consistent and asymptotically optimal solutions under certain conditions, with finite sample guarantees.
Accelerates materials optimization with data-driven models.
problem Optimizing materials with high-dimensional parameters.
method Data-driven experimental design with uncertainty analysis.
result Optimal candidate found with 3x fewer measurements.
The study provides a theory for deriving generalization guarantees for data-driven algorithm design.
problem Understanding the sufficient amount of data needed for high-performing algorithm design.
method Developed a broadly applicable theory for deriving generalization guarantees that bound the difference between average performance over a training set and expected performance.
result Uncovered a unifying structure to prove extremely general guarantees for various algorithm types.
MAD framework learns operators from physics-embedded data efficiently.
problem Data-driven methods require costly labeled datasets and model-driven techniques face efficiency-accuracy trade-offs.
method Integrates physical laws with data-driven learning to generate physics-embedded analytical solutions and synthetic data.
result Eliminates dependence on experimental or simulated training data, enabling efficient operator learning across multi-parameter systems.
ADML combines debiased learning with data-driven model selection for efficient inference.
problem Debiased machine learning estimators can be unstable and biased in nonparametric models.
method Data-driven model selection techniques combined with debiased machine learning.
result ADML estimators yield superefficient inference for pathwise differentiable parameters.
New framework for data-driven hyperparameter tuning with structured loss.
problem Statistical foundations for multi-dimensional hyperparameter tuning remain limited.
method General framework using real algebraic geometry for semi-algebraic function classes.
result First general guarantees for multi-dimensional hyperparameter tuning.
This paper tackles regularization parameter learning in inverse problems using data-driven bilevel optimization.
problem Finding optimal regularization parameters in inverse problems.
method Data-driven bilevel optimization approach, analyzing performance in large data samples.
result The approach can reduce computational cost through online numerical schemes based on stochastic gradient descent.
This research designs a data-driven partition to test independence between continuous variables.
problem Testing independence between continuous random variables.
method Empirical log-likelihood statistic and data-driven tree-structured partition.
result Strongly consistent test of independence over probability families.
Enhances machine learning generalization with DD-R-DRO method.
problem Improving machine learning generalization and reducing testing error.
method Doubly robust data-driven distributionally robust optimization (DD-R-DRO) method.
result Reduces testing error relative to state-of-the-art classifiers.
Compressed sensing improves MRI scans with data-driven learning.
problem Challenges in applying compressed sensing from research to clinical practice.
method Data-driven learning to address challenges of hand-crafted priors, tuning parameters, and long reconstruction times.
result Compressed sensing can have greater clinical impact with data-driven learning.
End-to-end framework optimizes constrained trajectories using data-driven methods.
problem Optimizing trajectories under constraints with limited dynamics knowledge.
method Data-driven approach decomposes trajectories into function basis, uses maximum a posteriori for optimization, and incorporates linear constraints.
result Commanding results in aeronautics and sailing route optimization.
Agent-based models now use data-driven parameters to explain financial market dynamics.
problem Understanding the complex behavior of financial markets through agent interactions.
method Data-driven approach to model parameters, combining big data with agent-based modeling.
result Agent-based models can now simulate financial market dynamics using real data.
Proposes a Gaussian process for Koopman mode decomposition.
problem Estimating Koopman mode decomposition quantities and latent variables.
method Unsupervised Gaussian process for simultaneous estimation.
result Efficient parameter estimation through low-rank approximations.
KOMET identifies Koopman operators from model parameter trajectories to adapt to evolving data distributions.
problem Adaptation of parametric models to non-stationary environments.
method Data-driven framework using Koopman operator identification and Extended Dynamic Mode Decomposition (EDMD).
result KOMET achieves high autonomous-rollout accuracies of 0.981 to 1.000 over 100 time steps on various drifting datasets.
A new data-driven model forecasts electricity prices efficiently.
problem Forecasting electricity prices using traditional methods.
method Integrates data-driven and fundamental models, learns from historical data.
result Significantly improves forecasting accuracy compared to existing models.
Improves robustness of high-dimensional regression with rank objective and group lasso regularization.
problem Heavy-tailed noise and outliers in high-dimensional regression.
method Non-smooth Wilcoxon score based rank objective, group lasso regularization, data-driven tuning rule, proximal augmented Lagrangian method.
result Robust estimator with finite-sample error bound and efficient computational method.
Paper proposes a hybrid model-based and data-driven approach for one-bit compressive autoencoding.
problem Designing efficient one-bit compressive autoencoding models for complex systems.
method Hybrid model-based and data-driven methodology for one-bit sparse signal recovery.
result Significant improvement in one-bit compressive autoencoding compared to state-of-the-art algorithms.
The paper proposes a method to predict the performance of data-driven algorithms using surrogate models.
problem Improving the performance prediction of data-driven knowledge discovery algorithms.
method Surrogate-assisted performance prediction using evolutionary modeling of clinical pathways.
result The proposed approach provides interpretable prediction of algorithm performance and quality.
New algorithms optimize algorithm parameters in online settings with reduced computational costs.
problem Optimizing algorithm parameters in online settings with volatile and discontinuous losses.
method Developed semi-bandit optimization algorithms that leverage extra information to reduce computational costs.
result Achieved regret bounds as good as full-information feedback with significantly less computational effort.
Proposes SSE, a data-driven method to regularize embedding layers in neural nets.
problem Reduces overfitting in embedding layers of neural nets.
method Stochastically shares embeddings during SGD, integrating with existing algorithms.
result Improves generalization on various tasks, including recommender systems and natural language models.
Physics-informed neural networks solve PDEs using neural networks.
problem Solving nonlinear partial differential equations (PDEs) with neural networks.
method Physics-informed neural networks trained to solve PDEs while respecting physical laws.
result Physics-informed neural networks can infer solutions to PDEs and create differentiable surrogate models.
Flexible multi-task learning framework using summary statistics.
problem Data-sharing constraints in healthcare settings.
method Proposes a flexible multi-task learning framework utilizing summary statistics and adaptive parameter selection.
result Systematic non-asymptotic analysis and simulations demonstrate the method's performance.
New method predicts VIV in 3D currents for marine risers.
problem Uncertainty in predicting VIV due to 3D current effects.
method Data-driven modeling using random forest regression.
result Data-driven method outperforms traditional models in 3D current conditions.
Paper proposes a hybrid model-based and data-driven method for one-bit compressive variational autoencoding.
problem Designing efficient one-bit compressive sensing systems.
method Hybrid model-based and data-driven approach for one-bit compressive variational autoencoding.
result Significant improvement in one-bit compressive sensing compared to state-of-the-art methods.
New shape representation for airfoils improves design and manufacturing.
problem Designing and manufacturing airfoils efficiently and accurately.
method Combining physics-based and data-driven techniques on a Grassmannian manifold.
result Rich set of novel 2D airfoil deformations not previously captured.
Dynamic assortment problem on two-sided platform with unknown parameters
problem Optimizing assortment display in an online platform with incomplete information and heterogeneous customers
method Data-driven algorithm that learns choice parameters while optimizing revenue
result Worst-case regret grows polylogarithmically over time
Cartesian neural network models learn soft tissue mechanical properties without shape assumptions.
problem Model-based methods limit elastography to imaging linear-elastic parameters.
method Data-driven neural network constitutive models (NNCMs) learn stress-strain relationships from force-displacement data.
result NNCMs can characterize mechanical properties and their spatial distribution without prior shape knowledge.
Polynomial chaos expansion improves machine learning regression accuracy.
problem Improving pointwise prediction accuracy in machine learning regression.
method Data-driven polynomial chaos expansion trained on input-output data.
result PCE metamodels achieve comparable accuracy to ML models on benchmark datasets.
Paper uses Gaussian processes to solve AC-OPF with renewable uncertainty.
problem Optimizing power grids with fluctuating renewable sources.
method Data-driven approach using Gaussian processes.
result Efficiently solves chance-constrained AC-OPF with uncertainty.
A new method estimates parameters of complex models using ordinary least squares.
problem Estimating parameters of nonlinear dynamic models from time series data.
method Physics-Informed Regression (PIR) using regularized ordinary least squares.
result PIR outperforms physics-informed neural networks (PINN) in parameter estimation.
CoLoRA models predict PDE solutions quickly and accurately with minimal data.
problem Efficiently modeling PDE solutions with limited data.
method Continuous low-rank adaptation of neural networks trained on offline data.
result Predictions are orders of magnitude faster and more accurate than classical methods.
Paper uses Bayesian optimization to find best Supertrend indicator settings.
problem Finding optimal trading parameters for the Supertrend indicator.
method Bayesian optimization to automate parameter selection.
result BO-optimized Supertrend strategy yields higher profits in backtesting.
Paper proposes dGCV for tuning in d-KRR, scalable and asymptotically optimal.
problem Lack of data-driven tuning method for divide-and-conquer kernel ridge regression.
method Modified Generalized Cross-validation (dGCV) for tuning parameters in d-KRR.
result dGCV is asymptotically optimal and equivalent to minimizing global loss.
A new UCB algorithm for heavy-tailed bandits with near-optimal regret.
problem Sequential decision making in uncertain environments with heavy-tailed rewards.
method Data-driven, distribution-free UCB algorithm combining resampled median-of-means and UCB.
result Near-optimal regret bound for heavy-tailed distributions.
Discover governing equations from data without specifying terms.
problem Discovering differential equations from data without predefined terms.
method Data-driven approach using genetic programming and automatic differentiation.
result Calibrated differential equations from various solutions of a differential equation.
FaIRGP model improves climate emulation with physical interpretability.
problem Lack of physical interpretability in data-driven emulators.
method Bayesian approach to a data-driven emulator of energy balance equations.
result Demonstrates skillful emulation of global and spatial surface temperatures.
Exact method found for estimating ILP weights from data.
problem Estimating objective-function parameters for integer linear programs.
method Projected subgradient descent applied to suboptimality loss.
result Explicit iteration complexity as a function of problem size.
New method models unknown systems with hidden parameters using neural networks.
problem Modeling unknown dynamical systems with hidden parameters.
method Training a deep neural network (DNN) model using trajectory data of the unknown system.
result DNN model accurately predicts unknown dynamical systems with new initial conditions.
This research proposes a new method to improve model predictions using data-driven correction models.
problem Model misspecification leads to suboptimal decisions in tasks like analysis and optimization.
method Develops a correction model operator with implicit attributes to mitigate model misspecification.
result Improves model predictions and end-goal insights through appropriate choices of correction properties.
Improves parameter selection for denoising with elastic net.
problem Challenges in selecting optimal parameters for denoising.
method Combines statistical learning theory and regularisation theory to approximate optimal elastic net parameters.
result Explicit error bounds on accuracy of approximated parameter and regularisation solution.
Machine learning predicts nuclear physics parameters with high accuracy.
problem Predicting nuclear physics parameters for superheavy elements.
method Gradient boosted trees algorithm trained on nuclear data.
result Predictions have standard deviation from 0.00035 to 0.73.
Efficiently solves heterogeneous QPs by reducing variables using instance-specific projections.
problem Solving high-dimensional quadratic programming problems efficiently.
method Data-driven framework with a graph neural network generating projections tailored to each QP instance.
result Produces high-quality solutions with reduced computation time, outperforming existing methods.
A digital twin for multi-scale systems uses physics-based and machine learning models.
problem Lack of application-specific details in digital twin technology.
method Strategically separates into physics-based and data-driven models; uses mixture of experts with Gaussian Process.
result Robust and accurate predictions at future time-steps for multi-scale systems.