Study improves calibration of NMT models, especially EOS and attention uncertainty.
problem Improper functioning of beam-search inference due to miscalibrated NMT models.
method Design and apply recalibration methods based on EOS and attention uncertainty signals.
result Improved accuracy and better sequence-level calibration of NMT models.
Scoping review of EO-ML methods for causal inference in poverty geography.
problem Lack of thorough documentation and best practices for EO-ML methods in causal analysis.
method Comprehensive scoping review cataloging five principal approaches.
result Detailed protocol for integrating EO data into causal analysis.
This work develops a machine learning approach to EOS models that accounts for thermodynamic constraints and model uncertainty.
problem Developing accurate equation of state models for high energy-density experiments with inherent uncertainties.
method Physics-informed Gaussian process regression (GPR) framework to capture model uncertainty and thermodynamic constraints.
result The proposed framework reduces prediction uncertainty by incorporating thermodynamic constraints, as demonstrated for diamond carbon EOS.
New findings show GD converges to a linear interpolator even with quadratic loss function under certain conditions.
problem Understanding convergence of Gradient Descent with quadratic loss functions.
method Parameterized linear regression with quadratic loss function, empirical and theoretical analysis.
result Gradient Descent converges to a linear interpolator even with quadratic loss function under the Edge of Stability regime.
Paper introduces EO_k for quantifying accuracy-fairness trade-offs in FRL.
problem Tackles the trade-off between accuracy and fairness in FRL.
method Kernel-based formulation of EO criterion for FRL.
result Offers a unified analytical characterization of fairness tradeoffs.
Supervised learning with a deep convolutional neural network is used to identify the QCD equation of state (EoS) employed in relativistic hydrodynamic simulations of heavy-ion collisions from the simulated final-state particle spectra ρ(pT,Φ). High-level correlations of ρ(pT,Φ) learned by the neural network act a…
Deep linear networks oscillate beyond the edge of stability in a predictable manner.
problem Understanding oscillations in deep linear networks beyond the edge of stability.
method Theoretical analysis of loss oscillations in deep matrix factorization loss.
result Loss oscillations in deep linear networks follow a period-doubling route to chaos and occur within a small subspace.
EoS selectively shapes learning, affecting some groups more than others.
problem EoS affects learning differently across the data distribution.
method Branching intervention to enter or exit EoS regime, controlled perturbation to isolate mechanisms.
result EoS redistributes learning, amplifying progress on some groups and suppressing others.
This paper presents quantum and classical algorithms for approximate submodular function minimization.
problem Approximate minimization of submodular functions.
method Classical and quantum algorithms for submodular minimization, with a new quantum sampling method.
result Quantum algorithm for approximate submodular minimization with improved time complexity.
Gradient descent near stability threshold shows sharpness oscillations.
problem Understanding sharpness and stability in non-Euclidean norms during gradient descent.
method Interpreted EoS through Directional Smoothness, defined generalized sharpness for arbitrary norms.
result Non-Euclidean GD exhibits sharpness oscillations around the stability threshold.
Gradient descent near stability threshold exhibits sharpness oscillations.
problem Understanding sharpness behavior near stability threshold in non-Euclidean norms.
method Interpreted EoS through Directional Smoothness and generalized sharpness under arbitrary norms.
result Non-Euclidean GD with generalized sharpness shows sharpness oscillations near 2/η. VL finds flatter solutions at edge of stability, matching theory with practice.
problem Understanding implicit regularization in deep learning.
method Edge of Stability framework, controlling variational posterior shape and sample number.
result VL finds even flatter solutions than gradient descent.
Paper introduces multi-scale methods to improve CATE estimation from EO data.
problem Challenges in balancing fine-grained and contextual information in EO-based causal inference.
method Multi-Scale Representation Concatenation, combining Vision Transformer and Causal Forests.
result Multi-scale approach captures effect heterogeneity better than single-scale models.
GD at EoS edge minimizes logistic loss without monotonic convergence.
problem Understanding GD's implicit bias at the edge of stability.
method Theoretical analysis of logistic regression with constant stepsize GD.
result GD with any constant stepsize minimizes logistic loss over long time scales.
Cohen et al. (2021) show GD trajectories align on a bifurcation diagram.
problem Understanding the Edge of Stability (EoS) phenomenon in gradient descent.
method Empirical studies and rigorous mathematical proofs for two-layer networks and single-neuron networks.
result GD trajectories align on a specific bifurcation diagram independent of initialization.
GD monotonically decreases GFS sharpness in neural networks and scalar models.
problem Oscillatory behavior of loss in GD training.
method Analysis of GFS sharpness and empirical validation.
result GFS sharpness decreases monotonically during GD training.
Deep learning predicts nuclear equation of state from rotating core collapse GW signals.
problem Classifying the nuclear equation of state from rotating core collapse gravitational wave signals.
method Employed deep convolutional neural networks to classify visual and temporal patterns in GW signals.
result Up to 97% correct classifications of nuclear equation of state in the test set.
Optimizes trading portfolios considering risk and profit.
problem Balancing risk and profit in trading portfolios.
method Risk-Aware Trading Swarm (RATS) algorithm.
result RATS improves portfolio performance and risk management.
The use of EEG biometrics, for the purpose of automatic people recognition, has received increasing attention in the recent years. Most of current analysis rely on the extraction of features characterizing the activity of single brain regions, like power-spectrum estimates, thus neglecting possible temporal dependencie…
SVM and N-best algorithm classify microbial marker clades from genome sequences.
problem Classifying microbial clades from genome sequences, especially new species.
method Support vector machine (SVM) with N-best algorithm, time series feature extraction, random fragment generation, k-mer size selection.
result Recognition accuracy rates above 28% in top-1 candidate, above 91% in top-10 candidate.
FIFA improves fairness in imbalanced datasets by encouraging both classification and fairness generalization.
problem Imbalanced datasets lead to poor fairness generalization in classifiers.
method FIFA: Imbalance-Fairness-Aware approach that encourages both classification and fairness generalization.
result FIFA improves fairness generalization on real-world datasets.
Improves disease progression prediction using auxiliary surrogate labels and health markers.
problem Challenges in predicting disease progression due to unknown true disease states.
method Integrates hidden Markov model with time-varying discriminative classification model.
result Significant improvement in distinguishing LBD from AD using objective markers.
Novel method identifies proteomic risk markers for Alzheimer disease.
problem Lack of comprehensive proteomic risk markers for Alzheimer disease diagnosis.
method Deep belief network-based feature selection method using proteomic and clinical data.
result Identified an optimal subset of proteins achieving 90% accuracy in Alzheimer disease diagnosis.
Fairness in algorithmic decision-making processes is attracting increasing concern. When an algorithm is applied to human-related decision-making an estimator solely optimizing its predictive power can learn biases on the existing data, which motivates us the notion of fairness in machine learning. while several differ…
AR app visualizes Quranic Surah al-Fil for Islamic education.
problem Lack of interactive and context-rich learning materials for Quranic studies.
method Research and development approach, including data collection, user requirement analysis, interface design, 3D asset creation, and integration of AR technology.
result AR application achieved high accuracy and user satisfaction, enhancing learner engagement and understanding.
MarkerMap selects key genes for cell type analysis in single-cell RNA-seq.
problem Selecting informative genes from large single-cell RNA-seq datasets is challenging and computationally intensive.
method MarkerMap is a generative model that identifies minimal gene sets explaining cell type variability.
result MarkerMap outperforms existing methods in both supervised and unsupervised marker selection.
Predicts clinical events using a landmark approach with machine learning for large biomarker histories.
problem Dynamic prediction of clinical events from large biomarker histories.
method Landmark approach extended to endogenous markers history combined with machine learning methods for survival data.
result Superlearner combining regularized regressions and random survival forests outperforms standard survival models.
This paper introduces the factorial marked temporal point process model and presents efficient learning methods. In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i.e. a marker. In this paper, we describe the factorial marked point processes w…
CNMs detect tipping points in complex systems using causal network markers.
problem Identifying tipping points ahead of critical transitions in complex systems.
method Introducing CNMs that incorporate causality indicators to detect tipping points.
result CNMs show higher predictive power and accuracy than traditional DNB indicators.
Paper proposes fair ML predictors to avoid discrimination.
problem Discrimination in ML predictors from historical data.
method Proposes two algorithms to adjust ML predictors for fairness.
result Proves fair EO and AA predictors are optimal in performance.
The diagnosis of Alzheimer's disease (AD) in routine clinical practice is most commonly based on subjective clinical interpretations. Quantitative electroencephalography (QEEG) measures have been shown to reflect neurodegenerative processes in AD and might qualify as affordable and thereby widely available markers to f…
Modeling latent dynamics in high-dimensional event sequences without prior knowledge.
problem Modeling latent dynamics in high-dimensional event sequences with unknown marker relations.
method Adversarial imitation learning framework decomposed into latent structural intensity model, efficient random walk model, and seq2seq discriminator.
result Effective detection of hidden network among markers and decent prediction for future events.
Deep learning predicts preterm birth risk with improved accuracy.
problem Improving accuracy in predicting spontaneous preterm deliveries.
method U-Net segmentation network for automatic extraction of cervical length and anterior cervical angle.
result Combined markers reduce false-negative ratio from 30% to 18%
New classifiers ensure fairness by adjusting a base classifier's operating characteristics.
problem Ensuring fairness in binary classification with multiple group constraints.
method Intervening directly on a base classifier's operating characteristics using group-wise ROC convex hulls and post-processing.
result Methods satisfy multiple fairness constraints (DP, EO, PP) with minimal interventions and near-oracle accuracy.
fiBAG integrates multiplatform genomic data to identify disease markers.
problem Understanding complex mechanisms underlying human diseases from multiplatform genomic data.
method fiBAG uses Gaussian process models and Bayes factors to identify functional evidence and guide variable selection.
result fiBAG improves detection of disease-related markers compared to non-integrative methods.
A new bias score method optimizes fairness in classification.
problem Ensuring fairness in binary classification under group constraints.
method Introducing bias scores and developing a post-hoc approach to adapt to fairness constraints.
result The method maintains high accuracy while ensuring fairness constraints.
Gaussian processes enhance EO with accurate and uncertain predictions.
problem Challenges in GP models for EO, including data-driven physics and causal inference.
method Data-driven physics-aware models respecting signal characteristics and physical laws.
result GP models need to evolve for better EO applications.
A simple function shows how neural nets can converge despite high sharpness.
problem Understanding why neural nets converge with high sharpness.
method Constructed a minimal example function and analyzed its training dynamics rigorously.
result Final converging point has sharpness close to 2/η. One of the most prevalent symptoms among the elderly population, dementia, can be detected by classifiers trained on linguistic features extracted from narrative transcripts. However, these linguistic features are impacted in a similar but different fashion by the normal aging process. Aging is therefore a confounding …
Quantifying behavior is crucial for many applications in neuroscience. Videography provides easy methods for the observation and recording of animal behavior in diverse settings, yet extracting particular aspects of a behavior for further analysis can be highly time consuming. In motor control studies, humans or other …
For precision medicine and personalized treatment, we need to identify predictive markers of disease. We focus on Alzheimer's disease (AD), where magnetic resonance imaging scans provide information about the disease status. By combining imaging with genome sequencing, we aim at identifying rare genetic markers associa…
We describe a method that infers whether statistical dependences between two observed variables X and Y are due to a "direct" causal link or only due to a connecting causal path that contains an unobserved variable of low complexity, e.g., a binary variable. This problem is motivated by statistical genetics. Given a ge…
Study uses DNM theory to detect early warning signals of market instability.
problem Detecting early warning signals of financial market instability.
method Applying Dynamical Network Marker (DNM) theory to trading data from the Tokyo Stock Exchange.
result Early warning signals of large price movements can be detected on a daily time scale.
The paper proposes a method to integrate prior information into penalized regression.
problem Improving predictive performance in high-dimensional tasks with prior information.
method Integrating multiple sources of prior information into penalized regression.
result The method improves predictive performance, as shown by simulations and applications.
Weight decay stabilizes training dynamics by slowing progressive sharpening.
problem Understanding how weight decay affects training stability in deep learning models.
method Analyzing weight decay effects at the Edge of Stability, developing a mathematical framework.
result Weight decay dampens oscillations and stabilizes sharpness in CNNs, causing a phase transition in MLPs.
Optimizes biomarker selection for cost-effective treatment rules.
problem Incorporating multiple biomarkers in treatment selection rules can be costly and reduce model performance.
method Developed procedures for estimating linear and nonlinear combinations of biomarkers using 0-norm penalized weighted classification.
result Demonstrated the importance of feature selection and marker cost in treatment selection rules.
Proposes a two-stage method for estimating heterogeneous treatment effects using gradient boosting trees.
problem Estimating heterogeneous treatment effects in randomized clinical trials with high-dimensional predictive markers.
method Two-stage statistical learning procedure using gradient boosting trees (XGBoost) to estimate main effects and HTE.
result Improves efficiency in estimating heterogeneous treatment effects through nonparametric function estimation.
The paper proposes a method to assess surrogate heterogeneity in non-randomized data.
problem Lack of methods to evaluate surrogate heterogeneity in non-randomized data.
method Proposes a framework using meta-learners to assess surrogate heterogeneity in real-world data.
result Identifies individuals for whom the surrogate is a valid replacement of the primary outcome.