Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

9.4%18.8%28.2%37.5% · May 201919922001200920182026
48 results for unbalanced networks

Unbalanced GANs stabilize GAN training by pre-training the generator with VAE.

problem Stable training of GANs to avoid mode collapses and improve image quality.
method Pre-train GAN generator with VAE, balance generator and discriminator training, prevent discriminator's early convergence.
result Unbalanced GANs reduce mode collapses and outperform ordinary GANs in stability, convergence, and image quality.

A new algorithm improves semi-supervised learning in unbalanced and heterogeneous networks.

problem Improving semi-supervised learning in partially labeled networks with unbalanced and heterogeneous data.
method Proposed a new algorithm called weighted inverse Laplacian (WIL) for partially labeled networks, based on random walk and information propagation.
result WIL ensures misclassification rate of order O(1d)O(\frac{1}{d}) for partially labeled degree-corrected block model (pDCBM) with average degree d=Ω(logn)d=Ω(\log n), and outperforms other methods in unbalanced and heterogeneous networks.

This study compares deep learning with other ML algorithms on credit scoring unbalanced data.

problem Training models on highly unbalanced data is challenging.
method Compared several machine learning algorithms with deep learning on a credit scoring unbalanced dataset.
result Deep learning shows promising performance on imbalanced data with little samples.

Exact solutions reveal how unbalanced initializations promote rapid feature learning in neural networks.

problem Understanding how neural networks efficiently extract features from data.
method Deriving exact solutions to a minimal model of neural networks transitioning between lazy and rich learning regimes.
result Unbalanced layer-specific initialization variances and learning rates determine the degree of feature learning.

SI learning is effective for unbalanced data, showing resilience to object dependencies.

problem Learning from unbalanced data in multi-instance learning.
method Analysis of SI learning objective with rich classifier families, focusing on unbalanced data.
result Unbalanced data improves resilience of SI method to object dependencies, especially in neural networks.

New algorithm solves unbalanced optimal transport on trees in quasi-linear time.

problem Efficiently solving unbalanced optimal transport problems on trees.
method Proposed an algorithm that solves a more general unbalanced optimal transport problem exactly in quasi-linear time on a tree metric.
result Solves unbalanced optimal transport on trees in quasi-linear time (less than one second for a tree with one million nodes).

New method clusters strong and weak views effectively, improving performance by up to 40%.

problem Clustering incomplete multi-view data with unbalanced incompleteness.
method View evolution scheme and weighted multi-view subspace clustering.
result Improves clustering performance by up to 40% on three metrics.

New methods estimate transport-growth pairs in unbalanced optimal transport.

problem Statistical guarantees for Monge-type estimation in unbalanced optimal transport remain limited.
method Developed two estimators for transport-growth pairs under different setups.
result Achieved minimax optimal rate for estimation of transport-growth pairs.

This paper generalizes Sinkhorn algorithm for unbalanced optimal transport.

problem Handling distributions with different total mass and robustness to outliers.
method Alternates between standard Sinkhorn updates and pointwise application of a contractive function.
result Defines Sinkhorn divergences that are differentiable, positive, definite, convex, and robust.

Proposes a GAN-based model for semi-supervised text regression.

problem Predicting social and economic outcomes from unbalanced textual data.
method Conditional Generative Adversarial Network (GAN) for semi-supervised learning.
result End-to-end framework for predictions without high-level representation selection.

This paper introduces a new formulation of the Conic Gromov-Wasserstein distance for comparing complex network structures.

problem Comparing measures of unequal mass and complex network structures.
method Novel semi-coupling formulation and extension to hypernetworks.
result Establishes fundamental properties and robustness of CGW metric.

Unbalanced minibatch Optimal Transport improves domain adaptation performance.

problem Optimal transport distances are computationally expensive for large datasets.
method Use unbalanced minibatch Optimal Transport to estimate distances over subsets of data.
result Unbalanced Optimal Transport leads to better domain adaptation results.

Proposes a method to stabilize treatment effect estimation with unbalanced data.

problem Unbalanced treatment assignment leading to unstable propensity score estimations.
method Undersamples data for propensity score modeling and calibrates scores to match original distribution.
result The estimator retains asymptotic properties of the DML estimator and improves finite sample performance.

Paper connects surface shape analysis and unbalanced optimal transport.

problem Computing the SRNF shape distance on piecewise linear surfaces.
method Characterizes SRNF shape distance as WFR distance pullback, proposes new algorithm for WFR distance computation.
result Direct computation of SRNF shape distance on piecewise linear surfaces.

We extend Sobolev transport to unbalanced measures on graphs.

problem Optimal transport struggles with measures of different total mass and high computational complexity.
method We propose a scalable unbalanced Sobolev transport (UST) for measures on graphs.
result UST admits a closed-form formula for fast computation and is negative definite.

We prove that a geodesic net with three boundary (= unbalanced) vertices on a non-positively curved plane has at most one balanced vertex. We do not assume any a priori bound for the degrees of unbalanced vertices. The result seems to be new even in the Euclidean case. We demonstrate by examples that the result is not …

2018-03-10abs ↗pdf ↗

New explicit constructions of unbalanced Ramanujan bipartite graphs.

problem Constructing bipartite Ramanujan graphs with specified degrees and avoiding certain edges.
method Presented explicit constructions and discussed known methods for Ramanujan graph construction.
result Affirmative answer to constructing unbalanced Ramanujan bipartite graphs under certain conditions.

Paper introduces VSSGD to balance deep learning training with variance suppression.

problem Unbalanced data leads to unbalanced training process in deep learning.
method Adaptively adjusts error variance and mean to balance training.
result VSSGD accelerates training, prevents overfitting, and improves learning from small samples.

A new model corrects inhomogeneity in Optimal Transport with Boundary.

problem Inhomogeneity in UROT models for Optimal Transport with Boundary.
method Proposed a modified entropic regularization term to make UROT models homogeneous.
result Homogeneous UROT model preserves properties of standard UROT while correcting inhomogeneity.

Study of Gaussian distributions using entropic Gromov-Wasserstein and inner product Gromov-Wasserstein.

problem Optimal transportation between Gaussian distributions with different dimensions.
method Entropic Gromov-Wasserstein and inner product Gromov-Wasserstein, with closed-form expressions and von Neumann's trace inequality.
result Closed-form expressions for the entropic IGW and its unbalanced variant between Gaussian distributions.

Improved R-QDA classifier performs well in unbalanced data settings.

problem High sensitivity of R-QDA to covariance matrix estimation noise in unbalanced data.
method Proposes an improved R-QDA with two regularization parameters and a modified bias.
result Significantly better classification performance compared to traditional R-QDA.

This study generates synthetic data to augment sleep apnea detection datasets.

problem Insufficient and unbalanced training datasets for health applications.
method Designing a recurrent Generative Adversarial Network to generate synthetic data and balance the dataset.
result All classifiers exhibit improved performance in sensitivity and kappa statistic.

This paper explains the method used in the segmentation challenge (Task 1) in the International Skin Imaging Collaboration's (ISIC) Skin Lesion Analysis Towards Melanoma Detection challenge held in 2018. We have trained a U-Net network to perform the segmentation. The key elements for the training were first to adjust …

2018-07-23abs ↗pdf ↗

Unbalanced data arises in many learning tasks such as clustering of multi-class data, hierarchical divisive clustering and semisupervised learning. Graph-based approaches are popular tools for these problems. Graph construction is an important aspect of graph-based learning. We show that graph-based algorithms can fail…

2011-12-11abs ↗pdf ↗

Characterizes distribution-free rates in unbalanced classification problems.

problem Minimizing error under two different distributions in unbalanced settings.
method Characterizes minimax rates over all pairs of distributions using a geometric condition.
result Identifies a dichotomy between hard and easy classes based on a three-points-separation condition.

Introduces new metric for Riemannian metrics, extending unbalanced optimal transport.

problem Extending unbalanced optimal transport to Riemannian metrics.
method Dynamic and static formulations of unbalanced optimal transport on Riemannian metrics.
result Wasserstein--Ebin metric provides a new Riemannian structure on the space of Riemannian metrics.

This paper uses UOT metrics for better dimensionality reduction and classification/clustering.

problem Improving dimensionality reduction and classification/clustering methods.
method Uses Hellinger--Kantorovich metric from unbalanced optimal transport (UOT).
result UOT outperforms Euclidean and OT-based methods in classification and clustering tasks.

New scalable methods for unbalanced optimal transport improve efficiency and applicability.

problem Scalable algorithms for unbalanced optimal transport remain underexplored.
method Analysis of semi-dual formulation and adaptive gradient methods.
result SGD methods achieve a convergence rate of O(n/εT) for large-scale applications.

Proposes a fairness criterion for multi-objective optimization in classification.

problem Ensuring fairness in classification models across different groups.
method Formulates a minimax Pareto fairness criterion and provides an optimization algorithm.
result Demonstrates improved fairness compared to existing methods on various real-world datasets.

Optimal transport with path constraints for distributions of different masses.

problem Comparing distributions with different total masses under path constraints.
method Introduces a model for unbalanced optimal transport with path constraints, proving existence of solutions.
result Existence of solutions to path constrained unbalanced optimal transport for various constraints.

New method uses optimal transport for better covariate matching in causal effect estimation.

problem Estimating causal effects in observational studies with high-dimensional covariates.
method Multimarginal unbalanced optimal transport for interpretable matching.
result Method provides interpretable weights and competitive performance with k-nearest neighbors.

DRAGON improves learning for rare classes in unbalanced datasets using class descriptions.

problem Learning rare classes in unbalanced datasets with deep models.
method DRAGON is a late-fusion architecture that corrects bias towards frequent classes and fuses class-descriptions to improve tail-class accuracy.
result DRAGON outperforms state-of-the-art models on new benchmarks for long-tail learning with class descriptors.

CNN accurately reconstructs lattice topology with strong thermal fluctuations.

problem Reconstructing lattice topology with strong thermal fluctuations and unbalanced data.
method Deep convolutional neural network (CNN) mapping local magnetic moments to coupling probabilities.
result CNN accurately reconstructs lattice topology where thermal fluctuations dominate.