Model reconstructs and simulates international trade networks under policy changes.
problem Reconstructing and simulating international trade networks under policy changes.
method Maximizing entropy based on local trade information to reconstruct networks; simulating structural changes using trade tariffs.
result Trade networks can be successfully reconstructed and simulated under policy changes.
ROAD-EnKFs use learned low-dimensional models to improve state reconstruction and forecasting.
problem Reconstructing and forecasting states of unknown or expensive systems.
method Learned low-dimensional surrogate models and ensemble Kalman filter integration.
result ROAD-EnKFs achieve higher accuracy at lower computational cost than existing methods.
DynAE improves deep clustering by dynamically shifting from reconstruction to centroid construction.
problem Lack of clear cost functions in unsupervised learning for capturing variations and similarities.
method Dynamic Autoencoder (DynAE) that gradually eliminates reconstruction in favor of centroid construction.
result DynAE achieves state-of-the-art results in deep clustering compared to other methods.
Graph filtering improves data reconstruction performance.
problem Data reconstruction and dimensionality reduction.
method Formulate data tasks as graph filtering operations, optimize mean-square error cost involving adjacency matrix, update filters via gradient descent.
result Better reconstruction performance of novel method compared to PCA.
fastMRI dataset helps machine learning for MRI faster, cheaper.
problem Accelerating MRI to reduce costs and patient stress.
method Open dataset and benchmarks for machine learning.
result Machine learning can reconstruct MRI images from fewer data.
Study benchmarks methods for learning non-Cartesian k-space trajectories and reconstruction.
problem Benchmarking methods for learning non-Cartesian k-space trajectories and reconstruction.
method Comparing PILOT, BJORK, and HybLearn schemes to learn non-Cartesian k-space trajectories and reconstruction.
result HybLearn scheme outperforms other methods in learning and comparing non-Cartesian k-space trajectories and reconstruction.
Unified theory explains and mitigates double descent in data reconstruction.
problem Understanding and mitigating double descent in reduced order modeling.
method Data-Noise Averaging theory, sufficient criteria, detailed risk curve prediction, regularization mechanisms.
result Detailed risk curves predicted at reduced computational cost, instability traced to individual sensors.
Quantization-aware phase retrieval algorithm improves signal reconstruction accuracy.
problem Reconstructing signals from quantized phase measurements.
method Developed a rank-1 projection algorithm with consistency criterion using one-sided quadratic cost.
result The algorithm achieves higher reconstruction accuracy and is closer to the Cramér-Rao lower bound.
New CT image reconstruction method reduces X-ray dose while improving image quality.
problem Reducing X-ray dose in CT while maintaining image quality.
method Combines PWLS with learned sparsifying transform using alternating optimization and relaxed OS-LALM.
result Proposed method improves image quality for low dose levels compared to existing methods.
Proposes TCWAE to learn disentangled representations using the Wasserstein Autoencoder.
problem Balancing reconstruction fidelity and disentanglement in learning representations.
method TCWAE (Total Correlation Wasserstein Autoencoder) using different KL estimators.
result Competitive results on data sets with known generative factors, and improved reconstructions on unknown factors.
PALMS reconstructs large-scale networks efficiently with parallel computing.
problem Reconstructing large-scale latent networks from observed dynamics is computationally challenging.
method PALMS (Parallel Adaptive Lasso with Multi-directional Signals) framework for distributed network reconstruction.
result PALMS substantially reduces computational complexity and storage requirements.
Enhances graph function reconstruction for dynamic graphs and time-varying functions.
problem Reconstructing attributes of vertices at different time instants on evolving graphs.
method Kernel-based approach for spatiotemporal dynamics, accommodating time-evolving topologies.
result Improved flexibility and computational efficiency compared to existing methods.
Develops efficient algorithms for spatial field reconstruction and sensor selection in heterogeneous weather sensor networks.
problem Efficient spatial field reconstruction and query-based sensor set selection in heterogeneous sensor networks.
method Spatial Best Linear Unbiased Estimator (S-BLUE) and Cross Entropy method.
result Efficient algorithms with performance guarantees for spatial field reconstruction and sensor selection.
A hybrid network improves MRI reconstruction from undersampled data.
problem Reducing MRI acquisition time while maintaining image quality.
method Hybrid architecture combining k-space and image domains using complex-valued and real-valued U-nets.
result Hybrid approach outperformed image-only deep learning methods in hard-to-reconstruct regions.
New method for sparse autoencoder learning using rank-ordered hidden units.
problem Sparse representation learning without extra hyperparameters.
method Order hidden units by activation, progressively reconstruct input, minimize reconstruction error.
result High sparsity achieved with minimal reconstruction error and robustness.
RODEO speeds up MRI and CT image reconstruction from sparse data.
problem Real-time reconstruction of dynamic medical images from limited data.
method Autoencoder with robust l1-norm cost function and Split Bregman method.
result Real-time image reconstruction with minimal quality loss.
Faster convergence in inverse problems with minimal additional error.
problem Balancing convergence speed and reconstruction accuracy in iterative algorithms.
method Using a coarse estimate of the set to modify iterative algorithms for faster convergence.
result It is possible to achieve faster convergence without significantly increasing computational cost.
A new hybrid VAE-GAN framework improves mode coverage and quality.
problem Mode collapse and poor sample quality in GANs and VAEs.
method Integrates a 'Best-of-Many-Samples' reconstruction cost and a stable synthetic likelihood estimate.
result Significant improvement in mode coverage and quality compared to hybrid VAE-GANs and plain GANs.
We consider the problem of reconstructing a low rank matrix from noisy observations of a subset of its entries. This task has applications in statistical learning, computer vision, and signal processing. In these contexts, "noise" generically refers to any contribution to the data that is not captured by the low-rank m…
Study proposes CNN for reconstructing high-res urban DEMs.
problem Lack of high-res urban DEM datasets for flood modeling.
method Multi-scale CNN model trained on urban DEMs of varying resolutions.
result CNN-based method produces superior high-res urban DEMs.
Incorporating sparsity priors in learning tasks can give rise to simple, and interpretable models for complex high dimensional data. Sparse models have found widespread use in structure discovery, recovering data from corruptions, and a variety of large scale unsupervised and supervised learning problems. Assuming the …
A new method reduces CT scan radiation exposure while improving image quality.
problem Reducing patient radiation exposure in CT scans while maintaining image quality.
method PWLS-ULTRA method that combines clustering and learning-based techniques.
result The method significantly improves image quality compared to existing methods.
Un-trained neural networks outperform trained methods in MRI reconstruction.
problem Accelerated MRI reconstruction with minimal training data.
method Variation of Deep Decoder without training data.
result Un-trained approach significantly outperforms other methods in reconstruction accuracy.
Concrete autoencoder selects key features for efficient data reconstruction.
problem Efficiently identifying and selecting important features for data reconstruction.
method Concrete selector layer with temperature-controlled selection during training, followed by reconstruction using a standard neural network.
result Concrete autoencoder selects a small subset of genes that can reconstruct the remaining gene expression levels, improving on existing methods.
Study on tensor signal estimation from incomplete data.
problem Estimating a rank-one tensor signal from noisy, incomplete data.
method Reduction to random matrix model for spectral analysis.
result Loss of performance due to incomplete data.
Energy dissipating networks control neural network behavior during inference.
problem Lack of provable guarantees for neural networks during inference.
method Iteratively compute descent directions with respect to a given energy function, ensuring convergence to the global minimum.
result Proven convergence of descent directions to the global minimum of the energy function.
Paper analyzes PSGLD for adaptive IRL with finite-sample bounds.
problem Estimating cost function of a forward learner using noisy gradients.
method Passive stochastic gradient Langevin dynamics (PSGLD) algorithm.
result Explicit bounds on 2-Wasserstein distance between PSGLD sample measure and stationary measure.
New method accurately reconstructs Russell 3000 index, revealing crowded portfolios.
problem Crowding in index portfolios during reconstitution events.
method Developed a Python package for accurate index reconstruction using CRSP US Stock data.
result Annual Russell 3000 portfolios are more crowded than quarterly ones, suggesting lower transaction costs.
Proposes a Monte-Carlo method for sparse signal reconstruction.
problem Reconstructing sparse signals in high-dimensional settings.
method Greedy Monte-Carlo (GMC) search algorithm.
result GMC can achieve perfect reconstruction in undersampling situations.
3d-SMRnet speeds up MPI system matrix recovery to 1 minute with high quality.
problem Slow system matrix recovery in MPI due to recalibration.
method 3d-System Matrix Recovery Network using deep learning.
result 3d-SMRnet recovers 3d system matrix with 64x subsampling in 1 minute.
The augmented Lagrangian (AL) method that solves convex optimization problems with linear constraints has drawn more attention recently in imaging applications due to its decomposable structure for composite cost functions and empirical fast convergence rate under weak conditions. However, for problems such as X-ray co…
New method simplifies tomographic reconstruction using RKHS.
problem Tomographic reconstruction challenges.
method RKHS framework for X-ray transform.
result Sharp stability results without Fourier transform.
New variational model preserves image contrasts and features using Weingarten map minimization.
problem Image reconstruction with preservation of contrasts and features.
method Variational model with L1 norm of Weingarten map, ADMM algorithm, gradient descent. result The proposed models preserve image contrasts and features efficiently.
Paper proposes DEMER to reconstruct hidden confounders for better reinforcement learning in recommendation.
problem Reinforcement learning in real-world applications is costly due to exploration in the environment.
method DEMER uses a multi-agent generative adversarial imitation learning framework to learn the environment and hidden confounder.
result DEMER effectively reconstructs hidden confounders and improves recommendation policy performance.
We propose an inference method to estimate sparse interactions and biases according to Boltzmann machine learning. The basis of this method is L1 regularization, which is often used in compressed sensing, a technique for reconstructing sparse input signals from undersampled outputs. L1 regularization impedes the …
Faster and accurate JPEG2000 image classification without reconstruction.
problem Efficiently classify j2k-compressed images without reconstructing them.
method Train a deep CNN using DWT coefficients directly from j2k-compressed images, using different augmentation techniques.
result Achieved faster and more accurate classification of j2k images without additional computation.
A new method improves molecule generation accuracy and efficiency.
problem Posterior collapse in VAEs for molecule sequence generation.
method Re-balancing reconstruction loss to avoid posterior collapse.
result Our method achieves state-of-the-art reconstruction accuracy and competitive validity.
A method extracts binary features directly from CS measurements for compressive image classification.
problem Efficiently classify images using compressive sensing without reconstruction.
method DCT-based approach for binary feature extraction from CS measurements, feature fusion with CNN features.
result Fused features outperform state-of-the-art methods in image classification.
Deep learning removes aliasing in MRI scans with fast computation.
problem High computational costs in MR scan reconstruction.
method Deep residual learning networks for magnitude and phase networks.
result Deep learning successfully removes aliasing artifacts from MRI scans.
Auto-encoders can recover true signals under certain conditions.
problem Signal recovery from auto-encoders.
method Highly incoherent weight matrices and unit ℓ2 row length, negative bias vectors equal to data mean. result True hidden representation can be approximately recovered with increasing sparsity.
Unified approach to training stochastic RNNs with latent variables.
problem Training generative latent variable models with autoregressive decoders.
method Amortized variational inference with backward RNN conditioning and auxiliary reconstruction cost.
result Improved performance on speech and sequential MNIST benchmarks.
Paper speeds up visualization of uncertain data.
problem High computational cost in reconstructing data uncertainties.
method Subdivide data spatially, adaptively reconstructing only necessary values, using GPR kernel and saved data observations to estimate upper bounds for level-crossing probabilities.
result Accurate estimation of value occurrence probabilities with low computation cost.
Novel tensor perturbation bounds for orthogonal iteration methods.
problem Developing robust bounds for tensor reconstruction and subspace estimation.
method Blockwise tensor perturbation bounds for high-order orthogonal iteration (HOOI).
result Upper bounds for singular subspace estimation converge linearly and tensor reconstruction error bound is characterized by a simple quantity.
The paper reconstructs graphs from eigenspace perturbations.
problem Recovering an undirected graph from perturbed eigenspaces.
method Minimizing the Frobenius norm of the commutator between symmetric matrices.
result Identifiability follows a sharp phase transition in the Erdős-Rényi model.
Bayesian algorithm improves sparse recovery in noisy one-bit CS with perturbation.
problem Noisy sparse recovery in one-bit compressed sensing with perturbation.
method BHT-MLE algorithm using Bayesian hypothesis test and ML estimator.
result BHT-MLE offers more accurate reconstruction than MLE at lower computational cost.
A novel likelihood function for MRFs approximates marginal likelihoods and uses copulas to reconstruct the joint likelihood.
problem Intractable partition function for MRF likelihoods.
method Approximate marginal likelihoods through a modified coin-tossing scenario, then reconstruct the joint likelihood using copulas.
result Our approach outperforms Laplace approximation and pseudolikelihood, especially as MRF size increases.
A new method avoids overfitting in network reconstruction by using the minimum description length principle.
problem Determining the optimal model complexity in network reconstruction to prevent overfitting.
method Hierarchical Bayesian inference and weight quantization based on the minimum description length principle.
result The method yields increased accuracy in reconstructing both artificial and empirical networks.
LSS learns molecular trajectories from MD data.
problem Limited integration time steps in MD simulations.
method Three deep learning networks for slow collective variables, dynamics, and configuration reconstruction.
result Generates ultra-long synthetic folding trajectories.