In this study, we propose Momentum Tracking, which is a method with momentum acceleration whose convergence rate is proven to be independent of data heterogeneity.
To this end, we introduce an effective temporal stereo method to dynamically select the scale of matching candidates, enable to significantly reduce computation overhead.
In this paper, we aim to approximate the 1-Wasserstein distance by the tree-Wasserstein distance (TWD), where TWD is a 1-Wasserstein distance with tree-based embedding and can be computed in linear time with respect to the number of nodes on a tree.
This paper proposes a Platform for Risk Assessment of DIC (PRADIC) that is developed by Idaho National Laboratory (INL).
Recent theoretical studies have attempted to explain the benefit of the large negative sample size by upper-bounding the downstream classification loss with the contrastive loss.
In quantum mechanics, the Heisenberg uncertainty relation presents an ultimate limit to the precision by which one can predict the outcome of position and momentum measurements on a particle.
A classifier built upon the representations is expected to perform well in downstream classification; however, little theory has been given in literature so far and thereby the relationship between similarity and classification has remained elusive.
Adversarially robust classification seeks a classifier that is insensitive to adversarial perturbations of test patterns.
Development of those closures traditionally rely on the experimental data and analytical derivation with simplified assumptions that usually cannot deliver a universal solution across a wide range of flow conditions.
Current system thermal-hydraulic codes have limited credibility in simulating real plant conditions, especially when the geometry and boundary conditions are extrapolated beyond the range of test facilities.
Segmentation of objects with various sizes is relatively less explored in medical imaging, and has been very challenging in computer vision tasks in general.
To realize efficient computational fluid dynamics (CFD) prediction of two-phase flow, a multi-scale framework was proposed in this paper by applying a physics-guided data-driven approach.
The proposed EM approach is based on the collaborative filtering among the annotated and unannotated datasets.
A clue to tackle their direct optimization is a calibrated surrogate utility, which is a tractable lower bound of the true utility function representing a given metric.
In this paper, we derive an unbiased risk estimator which can handle all of similarities/dissimilarities and unlabeled data.
A previously proposed discrepancy that does not use the source domain labels requires high computational cost to estimate and may lead to a loose generalization error bound in the target domain.
Supervised learning needs a huge amount of labeled data, which can be a big bottleneck under the situation where there is a privacy concern or labeling cost is high.
Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels are available.