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.

168,657 papers · 148 categories

Trend · papers per month

135270405540 · Jun 202019922001200920172026
48 results for minority samples

A new oversampling framework generates minority samples by perturbing majority classes.

problem Oversampling in imbalanced classification often neglects majority classes, leading to samples spread across the minority space.
method Introduces a counterfactual objective to generate new minority samples by perturbing majority samples.
result Generated minority samples are near the decision boundary and significantly outperform state-of-the-art methods.

Boost-and-Skip generates minority samples without guidance, faster and more effectively.

problem Generating minority samples in low-density regions of a data manifold.
method Boost-and-Skip approach with variance-boosted initialization and timestep skipping.
result Boost-and-Skip effectively promotes the emergence of underrepresented minority features.

Imbalanced data classification problem has always been a popular topic in the field of machine learning research. In order to balance the samples between majority and minority class. Oversampling algorithm is used to synthesize new minority class samples, but it could bring in noise. Pointing to the noise problems, thi…

2019-08-30abs ↗pdf ↗

Framework learns to transform majority to minority samples for balanced classification.

problem Imbalanced classification leading to biased predictions.
method Minimizes MMD and uses triplet loss for global alignment and boundary awareness.
result Consistent improvements over classical and generative baselines in AUROC, G-mean, F1-score, and MCC.

M2m method improves deep learning performance on class-imbalanced datasets.

problem Class imbalance in labeled training datasets causes deep neural networks to generalize poorly to minority classes.
method Augment less-frequent classes by translating samples from more-frequent classes.
result Significantly improves generalization on minority classes compared to existing methods.

A learning classifier must outperform a trivial solution, in case of imbalanced data, this condition usually does not hold true. To overcome this problem, we propose a novel data level resampling method - Clustering Based Oversampling for improved learning from class imbalanced datasets. The essential idea behind the p…

2018-11-02abs ↗pdf ↗

A new LLM-based method enhances diversity in oversampling for imbalanced classification.

problem Limited diversity in synthetic minority samples generated by current LLM-based approaches reduces robustness and generalizability.
method Condition synthetic sample generation on minority labels and features, use permutation strategy for fine-tuning, fine-tune on minority and interpolated samples.
result Significantly outperforms eight SOTA baselines in diverse synthetic sample generation and downstream classification tasks.

The paper analyzes how minority group imbalance affects neural network performance.

problem The impact of minority group imbalance on neural network performance.
method Formulated group imbalance problem with Gaussian Mixture Model, quantified sample complexity, convergence rate, and testing performance.
result Increasing the minority group fraction does not necessarily improve the generalization performance of the minority group.

We present a new family of zero-field Ising models over NN binary variables/spins obtained by consecutive "gluing" of planar and O(1)O(1)-sized components and subsets of at most three vertices into a tree. The polynomial-time algorithm of the dynamic programming type for solving exact inference (computing partition func…

2019-10-22abs ↗pdf ↗

The paper explores how deep generative models can improve performance on imbalanced datasets.

problem Imbalanced datasets lead to poor classifier performance and misleading evaluation metrics.
method The paper studies deep generative models for oversampling minority classes in imbalanced tabular data.
result Deep generative models can improve performance on imbalanced classification tasks, but require different under- and oversampling ratios.

Data in real-world application often exhibit skewed class distribution which poses an intense challenge for machine learning. Conventional classification algorithms are not effective in the case of imbalanced data distribution, and may fail when the data distribution is highly imbalanced. To address this issue, we prop…

2019-01-05abs ↗pdf ↗

CopulaSMOTE addresses class imbalance in diabetes prediction models.

problem Class imbalance in diabetes prediction models, especially with fewer confirmed cases.
method Copula-based oversampling approach that models joint dependence structure.
result CopulaSMOTE improves minority-class recovery in larger diabetes datasets.

The paper tackles sampling biases by ensuring minority groups are adequately represented in training data.

problem Sampling biases in training data lead to algorithmic biases in machine learning systems.
method The paper presents adaptive sampling methods to determine if it's possible to assemble a representative dataset from given data sources.
result The methods presented can determine with high confidence if a representative dataset can be assembled from given data sources.

A novel minimax classifier tackles imbalanced datasets with few minority samples.

problem Imbalanced datasets with limited minority samples.
method Proposes a novel minimax learning algorithm with two steps: minimization and maximization.
result The algorithm improves model performance compared to existing methods.

In this paper we consider minors of ribbon graphs (or, equivalently, cellularly embedded graphs). The theory of minors of ribbon graphs differs from that of graphs in that contracting loops is necessary and doing this can create additional vertices and components. Thus the ribbon graph minor relation is incompatible wi…

2013-11-09abs ↗pdf ↗

Proposes a method to balance imbalanced image datasets using capsule-GAN.

problem Imbalanced datasets challenge deep learning techniques.
method Capsule-GAN, combining GANs and capsule networks, addresses imbalance by generating minority class samples.
result Improves learning from imbalanced data with fewer parameters.

Synthetic augmentation helps but not always in imbalanced learning.

problem Imbalanced learning causes poor performance on rare classes.
method Developed a statistical framework for synthetic augmentation in imbalanced learning.
result Synthetic augmentation is not always beneficial and depends on the imbalance regime.

Paper tackles group robustness with partially labeled data.

problem Learning invariant representations from datasets with spurious correlations.
method Constructs a constraint set and derives a high probability bound for group assignment. Proposes an optimization algorithm for worst-off group assignments.
result Improvements in minority group's performance while preserving overall accuracy.

Paper analyzes stability and forgetting in score-based generative models.

problem Understanding the stability and long-time behavior of generative models.
method Quantitative bounds on sampling error using stability and forgetting properties of the Markov chain.
result Provides practical consequences of stability and contraction mechanism in sampling.

A new CA-GAN architecture improves minority class data generation in health datasets.

problem Algorithmic bias due to health data poverty and underrepresentation of minority groups.
method Proposes CA-GAN architecture to address shortcomings of resampling and GAN-based approaches.
result CA-GAN outperforms SMOTE and WGAN-GP* in generating authentic minority class data and maintaining original distribution.

The paper analyzes SMOTE for imbalanced classification, providing theoretical bounds and guidelines.

problem The challenge of imbalanced classification problems, especially with minority classes.
method Theoretical analysis of SMOTE and related oversampling techniques for minority classes.
result Derives concentration and excess risk bounds for SMOTE and kernel-based classifiers.

Every infinitely edge-connected graph has a minor of Farey graph or T0tT_{\aleph_0}\ast t.

problem Characterizing edge-connected graphs with specific minor properties.
method Analyzing the minor structure of infinitely edge-connected graphs.
result Infinitely edge-connected graphs contain Farey graph or T0tT_{\aleph_0}\ast t as a minor.

Paper determines Assouad-Nagata dimension for all minor-closed metrics.

problem Understanding the Assouad-Nagata dimension of minor-closed metrics.
method Using edge-weighted graphs and edge-deletion/contraction to model minor-closed metrics, determining their Assouad-Nagata dimension.
result Determined the Assouad-Nagata dimension for every minor-closed metric.

Theoretical and empirical study on SMOTE rebalancing strategy for imbalanced data.

problem Handling imbalanced tabular data sets using SMOTE and its variants.
method Derive non-asymptotic upper bounds on SMOTE density, adapt SMOTE based on theoretical findings.
result SMOTE tends to copy original minority samples asymptotically and vanishes near minority class boundaries.

In this paper we study the continuum time dynamics of a stock in a market where agents behavior is modeled by a Minority Game and a Grand Canonical Minority Game. The dynamics derived is a generalized geometric Brownian motion; from the Black & Scholes formula the calibration of both the Minority Game and the Grand Can…

2012-05-11abs ↗pdf ↗

This paper gives a critical account of the minority game literature. The minority game is a simple congestion game: players need to choose between two options, and those who have selected the option chosen by the minority win. The learning model proposed in this literature seems to differ markedly from the learning mod…

2007-06-29abs ↗pdf ↗

We explore several oversampling techniques for an imbalanced multi-label classification problem, a setting often encountered when developing models for Computer-Aided Diagnosis (CADx) systems. While most CADx systems aim to optimize classifiers for overall accuracy without considering the relative distribution of each …

2018-07-07abs ↗pdf ↗

The complement of a non-separating planar graph contains a K_n minor.

problem Characterizing the structure of complements of planar graphs.
method Analyzing the structure of complements of non-separating planar graphs and using examples to illustrate hypotheses.
result The order 2n-3 is the lowest possible for a non-separating planar graph whose complement contains a K_n minor.

The paper is partially withdrawn: in its current form, Lemma 2.3 is false, so that our proof of Theorem A and Proposition B has an important gap. We were unable to fix it yet. Any help is most welcome. We prove that the restriction of surface minority to fiber surfaces of divides is a well-quasi-order. Here surface min…

2012-11-30abs ↗pdf ↗

The paper develops a statistical theory explaining overfitting in imbalanced classification.

problem Overfitting in high-dimensional imbalanced classification.
method Developed a statistical theory for support vector machines and logistic regression.
result Overfitting is more severe for the minority class due to truncation or skewing effects in high-dimensional data.

Overparameterized models can worsen minority group errors even when overall test error improves.

problem Overparameterization exacerbates spurious correlations, harming minority groups.
method Simulations and experiments on image datasets, theoretical analysis of linear models.
result Subsampling the majority group can achieve low minority error in overparameterized models.

Paper tackles imbalanced time series classification with a novel oversampling method.

problem Imbalanced time series classification challenges due to high dimensionality and correlation.
method Density-ratio based clustering followed by shrinkage technique for covariance estimation, then generating synthetic samples.
result OHIT outperforms state-of-the-art methods in F1, G-mean, and AUC metrics.