Jointly correct bias fields and reconstruct undersampled MRI images.
problem Recovering fully sampled MRI images from undersampled data while accounting for bias field differences.
method An unsupervised learning-based reconstruction algorithm combined with a N4-based bias field estimation method in a joint optimization scheme.
result The proposed method improves reconstruction quality, both visually and in terms of RMSE.
Study shows survivorship bias inflates returns in India's small-cap index.
problem Survivorship bias in emerging market small-cap indices.
method Reconstructing historical index composition through market capitalization ranking and comparing equal-weight portfolios of current constituents versus all historical members.
result Survivor-only backtesting overstates returns by 4.94 percentage points and Sharpe ratios by 0.097.
Study improves confidence measures in medical imaging pipelines by addressing bias.
problem Bias in metric-based imaging pipelines compromises the efficiency of prediction intervals.
method Formalized symmetric and asymmetric CP formulations, analyzed bias effects, and validated empirically.
result Symmetric intervals are inflated by bias, while asymmetric intervals remain unaffected.
New analysis shows reconstruction attacks are unreliable without prior data knowledge.
problem Privacy and security risks from neural network memorization of training data.
method Complementary analysis of reconstruction methods, proving their unreliability without prior data knowledge.
result Reconstruction attacks are fundamentally unreliable without prior data knowledge, and networks trained more extensively are less susceptible.
New method uses generative models to improve phase retrieval stability.
problem Improving stability of solutions in phase retrieval problems.
method Unified reconstruction approach using generative models to mitigate overfitting.
result Mitigates overfitting to generative model for varying noise levels.
Parametric images provide insight into the spatial distribution of physiological parameters, but they are often extremely noisy, due to low SNR of tomographic data. Direct estimation from projections allows accurate noise modeling, improving the results of post-reconstruction fitting. We propose a method, which we name…
New method reconstructs significant parts of training data from neural networks.
problem Understanding and reconstructing training data from neural networks.
method Proposes a novel reconstruction scheme based on recent theoretical results about neural network training.
result Shows that a significant fraction of training data can be reconstructed from neural network parameters.
We found hidden convexity in FPCA and developed a faster algorithm.
problem Bias in PCA leading to unequal subgroup outcomes.
method Convex optimization via eigenvalue optimization.
result Faster and fairer PCA algorithm.
ResUNet-CMB neural network reconstructs CMB effects from noisy data.
problem Reconstructing CMB anisotropies from noisy data.
method Convolutional neural network (ResUNet-CMB) for simultaneous reconstruction of lensing and reionization.
result ResUNet-CMB outperforms quadratic estimators at low noise levels and avoids lensing-induced bias.
Anomaly detection is of great interest in fields where abnormalities need to be identified and corrected (e.g., medicine and finance). Deep learning methods for this task often rely on autoencoder reconstruction error, sometimes in conjunction with other errors. We show that this approach exhibits intrinsic biases that…
Framework reconstructs missing spatio-temporal data for extreme value prediction.
problem Predicting extreme values from incomplete spatio-temporal data.
method Convolutional deep neural networks and autoencoder-like models for conditional sampling.
result Framework produces accurate reconstructions of missing data for extremal values.
Lossy compression of statistical data using quantum annealing.
problem Efficiently compressing statistical floating-point data.
method Representation learning with binary variables, classical optimization of basis vectors, quantum annealing for coefficients, bias correction.
result Quantum annealing shows promising results with 3.5x better compression than neural-network autoencoders.
Text corpora are widely used resources for measuring societal biases and stereotypes. The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the vectors of the representative words of the concepts of interest (such as gender…
SLUG method detects bias and out-of-distribution content in generative models.
problem Generative models can underrepresent certain groups and fail on out-of-distribution data.
method SLUG: A new uncertainty quantification method for VAEs combining Laplace approximations and stochastic trace estimators.
result SLUG's UQ score correlates with bias and out-of-distribution content.
A new BO method tackles high-dimensional optimization without reconstruction.
problem Optimizing high-dimensional black-box functions is challenging, especially when low-dimensional structures are assumed.
method Tackles the problem in the original high-dimensional space using learned low-dimensional structure.
result Our method explores the high-dimensional space more effectively than existing approaches.
DRIO improves time series imputation by minimizing reconstruction error and distributional divergence.
problem Bias in imputation due to mismatch between observed and true data distributions.
method DRIO minimizes reconstruction error and worst-case divergence using Wasserstein ambiguity set.
result DRIO consistently provides robust imputation and improved forecasting.
A primary concern of excessive reuse of test datasets in machine learning is that it can lead to overfitting. Multiclass classification was recently shown to be more resistant to overfitting than binary classification. In an open problem of COLT 2019, Feldman, Frostig, and Hardt ask to characterize the dependence of th…
NestedVAE isolates common factors from paired images without additional supervision.
problem Reduction of data-driven biases in machine learning models.
method Combines deep latent variable models with information bottleneck theory.
result NestedVAE significantly outperforms alternative methods in various tasks.
Generative Adversarial Networks generate PXD background noise efficiently.
problem Efficiently generate statistically independent PXD background noise samples.
method Conditional Generative Adversarial Networks (GANs) with contrastive learning.
result On-demand PXD background generator reduces storage requirements.
A ML-based method reconstructs 3D organ doses from 2D radiographs for pediatric abdominal radiotherapy.
problem Reconstructing detailed 3D dose distributions for childhood cancer survivors using limited 2D radiographs.
method Surrogate-free ML approach using 142 abdominal planning CTs, 300 artificial plans, and evolutionary algorithm.
result Accurate 3D dose reconstructions with MAEs ≤ 1.7 Gy for edge organs, validated on independent dataset.
The PC algorithm is a popular method for learning the structure of Gaussian Bayesian networks. It carries out statistical tests to determine absent edges in the network. It is hence governed by two parameters: (i) The type of test, and (ii) its significance level. These parameters are usually set to values recommended …
A method improves Cryo-EM 3D map refinement by regularizing rotation estimation.
problem Noise-robustness vs. data-consistency in Cryo-EM 3D map reconstruction.
method Ellipsoidal support lifting (ESL) for regularizing and approximating the global minimizer over Riemannian manifolds.
result The induced bias due to regularizing effect of ESL estimates better rotations than global optimisation.
VAEs improve generalization by regulating mutual information, contrary to intuition.
problem Improving generalization in VAEs.
method Rate-distortion analyses controlling rate strength, network capacity, and generalization difficulty.
result Decreasing the strength of the rate paradoxically improves generalization.
Study on estimating volatility of volatility using Fourier methods and provides insights into volatility dynamics.
problem Estimating the volatility of volatility (vol-of-vol) accurately and efficiently.
method Used Fourier methodology to estimate integrated volatility of volatility, bias-corrected and without bias-correction, comparing their asymptotic properties and accuracy.
result The bias-corrected estimator reaches the optimal rate n1/4, while the uncorrected estimator has a slower rate and smaller asymptotic variance. Method reconstructs aneurysm growth history from patient parameters using physics-informed autoencoder.
problem Predicting arterial aneurysm rupture due to inaccessible growth time series.
method Physics-informed autoencoder combined with neural network for mapping patient parameters to aneurysm growth time history.
result Incorporating physical model constraints improves time series reconstruction, especially in noisy data.
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.
Gradient descent with small random init mimics spectral methods for low-rank matrix recovery.
problem Reconstructing a low-rank matrix from few measurements.
method Gradient descent with small random initialization followed by a few iterations.
result Gradient descent from small random init converges to a well-generalizing solution.
Autoencoders misidentify anomalies due to data topology.
problem Autoencoders fail to accurately identify anomalies in data with nontrivial topology.
method Illustrative low-dimensional examples and analysis of autoencoder behavior in latent space.
result Topology of the dataset affects autoencoder performance, leading to misidentification of anomalies.
New method stabilizes machine learning for physics-informed inverse problems.
problem Reconstructing physical quantities from PDE-compliant measurements.
method Physics-informed learning with smooth inductive bias.
result PDE operators stabilize variance and prevent overfitting in fixed dimensions.
The paper highlights how machine learning calibrations can be biased by training data.
problem Machine learning calibrations can be biased by the training data, affecting downstream analyses.
method The paper examines simulation-based and data-based calibrations, highlighting their prior dependence and proposing solutions.
result A recently proposed Gaussian Ansatz approach can avoid some biases in simulation-based calibrations.
New method decomposes Markov chain rewards into persistent and transient components.
problem Ambiguity in classical evaluation methods for Markov chains with reducible and periodic states.
method Minimal exact quotient by the real peripheral invariant subspace, decomposing rewards into persistent and transient components.
result Exact comparison with classical methods shows that the new decomposition reallocates the same information, making persistent modes explicit.
Study compares L1 and VG sparsity priors in inverse problems.
problem Sparse regularization in inverse problems with incomplete or corrupted measurements.
method Compared L1 regularization with Variational Garrote (VG), a probabilistic method approximating L0 sparsity.
result VG often achieves lower minimum generalization error and improved stability in strongly underdetermined regimes.
SOS-VAE improves generative models for scientific applications by correcting decoder bias.
problem Bias in generative parameters due to supervised learning in VAEs.
method Develops SOS-VAE framework to influence decoder for predictive latent representation.
result Ensures reliable generative parameters for scientific applications.
New method better identifies irrelevant variables for more accurate treatment effect estimation.
problem Handling irrelevant variables in treatment effect estimation with deep disentanglement.
method Deep embedding method to disentangle pre-treatment variables, explicitly identify and represent irrelevant variables, and orthogonalize them.
result Better identification and representation of irrelevant variables lead to more precise treatment effect prediction.
Physen-Noise2Noise tackles defocus deblurring in low-light conditions with physics-guided self-supervised learning.
problem Defocus deblurring in low-light conditions with complex biased noise.
method Physics-guided self-supervised deblurring framework that leverages noisy multi-frame observations and a learnable noise bias parameter.
result Physen-Noise2Noise consistently outperforms state-of-the-art methods in defocus deblurring with complex biased noise.
Natural gradient descent avoids the magic of model parametrization, leading to different optimization outcomes.
problem Understanding the impact of model parametrization on optimization and generalization in deep learning.
method Characterization of natural gradient flow in deep linear networks and nonlinear neural networks.
result Natural gradient descent fails to generalize in some cases, while gradient descent with the right architecture performs well.
New method uses observational data to improve trial design efficiency.
problem Scarce randomized controlled trials; inefficiency of using observational data.
method Active Residual Learning, R-Design framework, R-EPIG criterion.
result Efficiently estimating residuals to correct observational bias improves trial design.
Restricted Boltzmann Machines (RBMs) are generative models which can learn useful representations from samples of a dataset in an unsupervised fashion. They have been widely employed as an unsupervised pre-training method in machine learning. RBMs have been modified to model time series in two main ways: The Temporal R…
Quantizes latent space to improve disentanglement in models.
problem Learning disentangled representations from unlabeled data.
method Quantizes latent space into discrete code vectors with a learnable scalar codebook and applies high weight decay regularization.
result Quantized-latent autoencoder (QLAE) outperforms prior work in disentanglement without sacrificing data reconstruction.
Paper develops a framework to identify latent dynamics from high-dimensional data.
problem Identifying latent dynamics from high-dimensional time-series data.
method Combines physics inductive bias and learn-to-identify strategy.
result Meta-HyLaD framework effectively identifies hybrid latent dynamics.
Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Nevertheless, when training data is scarce their performance is significantly degraded due to overfitting. In this paper, we mit- igate overfitting…
FM4PDE learns PDE solutions from sparse data.
problem Reconstructing PDE solutions from limited observations.
method Flow-matching generative framework that learns PDE coefficients and solutions.
result Error guarantees for guided procedures, including deterministic and stochastic samplers.
Enhanced X-ray polarimetry with deep learning for better exposure times.
problem Improving sensitivity of X-ray telescopic observations with imaging polarimeters.
method A weighted maximum likelihood combination of predictions from a deep ensemble of ResNet convolutional neural networks trained on Monte Carlo event simulations.
result Improves effective exposure times by ~45% for power-law source spectra.
A semi-supervised framework using stochastic interpolation and latent representations.
problem Challenges in conditional generative modeling with scarce labeled data.
method Combines conditional stochastic interpolation with low-dimensional latent representations.
result Significantly improves sample complexity and achieves faster convergence rate.
Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representati…
Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive model of human memory, we propose a network representation learning scheme. In this …
Deep learning speeds up whole heart MRI to 30 seconds.
problem Long acquisition times in whole heart MRI.
method Deep learning, specifically a 3D residual U-Net, to reconstruct high-resolution images from low-resolution data.
result Super-resolution images show better edge sharpness and fewer artefacts than low-resolution images.
An axiomatic approach to signal reconstruction is formulated, involving a sample consistent set and a guiding set, describing desired reconstructions. New frame-less reconstruction methods are proposed, based on a novel concept of a reconstruction set, defined as a shortest pathway between the sample consistent set and…