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.

168,695 papers · 148 categories

Trend · papers per month

90179269358 · Jun 202019922001200920172026
48 results for Class Prejudice

New proof links initial class bias to DNN trainability, challenging traditional understanding.

problem Understanding the initial class bias in DNNs and its impact on trainability.
method Theoretical proof linking initial class bias to mean field theories of DNNs.
result Efficient learning is connected to a network's prejudice towards a specific class, contradicting traditional understanding.

New welfare-based fairness notions align with existing error rate balance and predictive parity.

problem Aligning fairness notions with welfare-based criteria.
method Discussing and establishing conditions for envy freeness and prejudice freeness.
result Envy freeness and prejudice freeness are equivalent to error rate balance and predictive parity.

Paper proposes a method to identify and treat latent discriminating features in machine learning models.

problem Fairness issues in machine learning models trained on historical data containing sensitive attributes.
method A novel algorithm that identifies and treats latent discriminating features, agnostic of the learning algorithm.
result Experimental results show near-ideal fairness measurement compared to other methods.

Method trains a debiased model from a biased one by focusing on samples that contradict the bias.

problem Training neural networks can lead to biased predictions due to spurious correlations.
method Train a pair of neural networks, intentionally biasing one and debiasing the other by focusing on contradictory samples.
result Our method significantly improves training against various types of biases, sometimes outperforming explicit supervision methods.

Predictive modeling is increasingly being employed to assist human decision-makers. One purported advantage of replacing human judgment with computer models in high stakes settings-- such as sentencing, hiring, policing, college admissions, and parole decisions-- is the perceived "neutrality" of computers. It is argued…

2016-10-25abs ↗pdf ↗

Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We develop algorithms for contextual …

2018-12-15abs ↗pdf ↗

Algorithmic fairness is a field of study that addresses the systematic disadvantage of marginalized groups in machine learning systems.

problem Modern machine learning systems increasingly determine access to economic and social opportunities, leading to structural inequalities and prejudices.
method Statistical and structural approaches to algorithmic fairness.
result The field of algorithmic fairness emerged to address the systematic disadvantage of marginalized groups in machine learning systems.

Examines predictability and complexity of economic time series using symbolic dynamics and entropy.

problem Understanding the predictability and complexity of economic time series.
method Symbolic dynamics and Information theory (entropy and uncertainty).
result Economic time series are complex and can be expressed in terms of information production.

Improved 3D generative models for drug design reduce bias and enhance data efficiency.

problem Data sparsity and bias in 3D molecular design models.
method Multi-level contrastive learning protocol for bias control and data efficiency.
result Hierarchical generative models that are topologically unbiased and explainable.

Recent work in fairness in machine learning has proposed adjusting for fairness by equalizing accuracy metrics across groups and has also studied how datasets affected by historical prejudices may lead to unfair decision policies. We connect these lines of work and study the residual unfairness that arises when a fairn…

2018-06-07abs ↗pdf ↗

Machine learning models are widely adopted in scenarios that directly affect people. The development of software systems based on these models raises societal and legal concerns, as their decisions may lead to the unfair treatment of individuals based on attributes like race or gender. Data preparation is key in any ma…

2019-10-05abs ↗pdf ↗

Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We study a consideration for the expl…

2017-11-19abs ↗pdf ↗

Classifies manifolds with dense conjugacy classes in their mapping class groups.

problem Classifying manifolds based on conjugacy classes in their mapping class groups.
method Analyzing connected orientable 2-manifolds and their mapping class groups.
result Mapping class groups of certain manifolds have dense conjugacy classes.

This paper tackles worst-class error rate in classification tasks.

problem Minimizing worst-class error rate in classification tasks, especially in medical image classification.
method Designing a boosting approach to bound the worst-class error rate using Deep Neural Networks (DNNs).
result The proposed boosting approach lowers worst-class test error rates while avoiding overfitting.

Paper constructs a cohomology class related to McDuff's secondary class, proving it transgresses to the Euler class of foliated sphere bundles.

problem Finding higher-dimensional analogs of the Calabi invariant and its transgression to the Euler class.
method Constructing a cohomology class of volume-preserving diffeomorphisms and proving transgression to the Euler class of foliated sphere bundles.
result The cohomology class transgresses to the Euler class of foliated sphere bundles.

One of the earliest conjectures in computational learning theory-the Sample Compression conjecture-asserts that concept classes (equivalently set systems) admit compression schemes of size linear in their VC dimension. To-date this statement is known to be true for maximum classes---those that possess maximum cardinali…

2014-01-29abs ↗pdf ↗

The paper proves inequalities for orbifold second Chern classes in Fujiki's class.

problem Inequalities for orbifold second Chern classes of compact normal analytic varieties.
method Generic nefness theorems for tangent and cotangent sheaves, and an orbifold Bogomolov--Gieseker inequality for mixed polarizations.
result Semipositivity of the orbifold second Chern class for varieties with nef anti-canonical divisor.

Study on characteristic classes for foliation deformations.

problem Characterizing and understanding characteristic classes for foliation deformations.
method Introduced a differential graded algebra (DGA) to recover Bott vanishing and formulae, and discussed properties of its cohomology.
result Discovered new classes that cannot be described by existing classes like Godbillon--Vey and Fuks--Lodder--Kotschick.

The hyperelliptic mapping class group has been studied in various contexts within topology and algebraic geometry. What makes this study tractable is that there is a surjective map from the hyperelliptic mapping class group to a mapping class group of a punctured sphere. The more general family of superelliptic mapping…

2016-04-13abs ↗pdf ↗

CILF learns adaptive embeddings for class-incremental learning with novel class detection and model update.

problem Handling unknown classes and model update in streaming data with new classes.
method CILF uses decoupled prototype based loss for intra-class and inter-class structure improvement, and a learnable curriculum clustering operator for adaptive embedding.
result CILF effectively detects multiple novel classes and mitigates embedding confusion, while updating the model without catastrophic forgetting.

In this paper we give explicit formulas of differential characteristic classes of principal GG-bundles with connections and prove their expected properties. In particular, we obtain explicit formulas for differential Chern classes, differential Pontryagin classes and differential Euler class. Furthermore, we show that…

2013-11-15abs ↗pdf ↗

A new method identifies class-specific covariates in multi-class prediction tasks.

problem Identifying covariates specifically associated with one or more outcome classes in multi-class prediction tasks.
method Introducing multi forests (MuFs) with multi-way and binary splits to measure class-associated discriminatory ability.
result The multi-class VIM specifically ranks class-associated covariates highly, unlike conventional VIMs.

Study of conjugacy classes in infinite-type surfaces' mapping class groups.

problem Characterizing conjugacy classes in infinite-type surfaces' mapping class groups.
method Model-theoretic methods developed by Kechris, Rosendal, and Truss.
result Detailed classification of conjugacy classes in mapping class groups of infinite-type surfaces.

The paper classifies dense conjugacy classes in mapping class groups of locally finite graphs.

problem Identifying which mapping class groups have dense conjugacy classes.
method Developed flux homomorphisms and combinatorial criteria for stability.
result A complete classification for self-similar locally finite graphs and a criterion for stability.

We give a complete description of conjugacy classes of finite subgroups of the mapping class group of the sphere with r marked points. As a corollary we obtain a description of conjugacy classes of maximal finite subgroups of the hyperelliptic mapping class group. In particular, we prove that for a fixed genus g there …

2005-10-11abs ↗pdf ↗

We present a simple generative framework for learning to predict previously unseen classes, based on estimating class-attribute-gated class-conditional distributions. We model each class-conditional distribution as an exponential family distribution and the parameters of the distribution of each seen/unseen class are d…

2017-07-25abs ↗pdf ↗

For a local Lie group M we define odd order cohomology classes. The first class is an obstruction to globalizability of the local Lie group. The third class coincides with Godbillon-Vey class in a particular case. These classes are secondary as they emerge when curvature vanishes.

2009-12-04abs ↗pdf ↗

This paper proposes a novel generic one-class feature learning method based on intra-class splitting. In one-class classification, feature learning is challenging, because only samples of one class are available during training. Hence, state-of-the-art methods require reference multi-class datasets to pretrain feature …

2018-12-20abs ↗pdf ↗

This research sets limits on how complex multi-class learning problems can be.

problem Understanding the complexity of multi-class classification problems.
method Established upper bounds on Natarajan dimensions for specific function classes.
result Upper bounds on Natarajan dimensions for multi-class decision trees, random forests, and neural networks.

Characteristic classes of oriented vector bundles can be identified with cohomology classes of the disjoint union of classifying spaces BSO_n of special orthogonal groups SO_n with n=0,1,... A characteristic class is stable if it extends to a cohomology class of a homotopy colimit BSO of classifying spaces BSO_n. Simil…

2009-10-25abs ↗pdf ↗

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.

Gen1S learns novel classes with 1-shot data using residual space and generative models.

problem Learning new classes with limited data in a growing dataset.
method Mapping embeddings to a residual space, using generative models to learn multi-modal distribution, and applying it as a structural prior.
result Consistent improvement over state-of-the-art methods in recognizing novel classes.

We study types of mapping classes which arise as a product of a given mapping class and powers of certain pure mapping classes. We derive an explicit constant depending only on a surface such that almost all above pure mapping classes give rise to pseudo-Anosov type whenever their powers are larger than the constant. F…

2016-11-16abs ↗pdf ↗

New classes defined for manifold pseudogroups, linking to cohomology and bundle structures.

problem Characterizing pseudogroups of diffeomorphisms using characteristic classes.
method Defined Godbillon-Vey-Losik and first Chern-Losik classes via de Rham cohomology and frame bundles.
result Explicit expressions and geometric representations for the new classes.

Paper tackles many-class few-shot learning with class hierarchy, improving accuracy.

problem Many-class few-shot learning problem in practical applications.
method Leverages class hierarchy to train a coarse-to-fine classifier using memory-augmented hierarchical-classification network (MahiNet).
result MahiNet outperforms state-of-the-art models on MCFS problems in both supervised and meta-learning settings.

Continuous epimorphisms between certain mapping class groups are induced by homeomorphisms.

problem Understanding continuous epimorphisms between specific mapping class groups.
method Analyzing subgroups of mapping class groups of infinite-genus 2-manifolds with no planar ends.
result Continuous epimorphisms are induced by homeomorphisms for the specified subgroups.