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

99198296395 · Jun 202019922001200920172026
48 results for contrastive examples

Contrastive examples improve fairness in face recognition by balancing minority and majority groups.

problem Face recognition algorithms favor majority groups in training data.
method Create contrastive examples by swapping group memberships in the training dataset.
result Contrastive examples improve fairness metrics like equalized odds.

The study investigates the impact of negative examples in contrastive learning.

problem Understanding how the number of negative examples affects downstream performance in contrastive learning.
method Theoretical analysis and empirical evaluation of NLP and vision tasks.
result The optimal number of negative examples should scale with the number of underlying concepts in the data.

New statistical theory explains contrastive learning effectiveness.

problem Understanding why contrastive learning works well for representation extraction.
method Developed a new theoretical framework based on approximate sufficient statistics.
result Near-sufficient encoders derived from contrastive learning can be adapted for downstream tasks.

Paper proposes contrastive training to improve OOD detection without needing explicit OOD examples.

problem Improving reliable detection of out-of-distribution inputs for machine learning systems.
method Contrastive training approach that doesn't require explicit OOD examples, using CLP score.
result Contrastive training significantly improves OOD detection performance on benchmarks, especially in near OOD classes.

SuNCEt accelerates contrastive learning with minimal labeled data.

problem Efficiently learning visual representations with limited labeled data.
method Noise-contrastive estimation and neighbourhood component analysis-based semi-supervised loss.
result SuNCEt achieves semi-supervised learning accuracy with less than half the labeled data.

New attacks prevent both supervised and contrastive learning from private data.

problem Preventing unauthorized use of private data and commercial datasets.
method Contrastive-like data augmentations in supervised error minimization or maximization frameworks.
result Achieve state-of-the-art worst-case unlearnability across SL and CL algorithms.

New unsupervised method selects hard negative samples for contrastive learning.

problem How to select good negative examples for contrastive learning without using true similarity information.
method Developed a new family of unsupervised sampling methods for hard negative selection.
result Improves downstream performance across multiple modalities.

WEINCE improves contrastive learning by correcting softmax biases.

problem Softmax in InfoNCE can lead to misaligned statistical assumptions in contrastive learning.
method WEINCE uses anchor-wise online batch statistics to blend softmax logits with an endpoint shortfall correction.
result WEINCE yields consistent improvements in frozen-feature evaluation across five vision benchmarks.

We study the motion of discrete interfaces driven by ferromagnetic interactions in a two-dimensional low-contrast periodic environment, by coupling the minimizing movements approach by Almgren, Taylor and Wang and a discrete-to-continuum analysis. As in a recent paper by Braides and Scilla dealing with high-contrast pe…

2014-07-25abs ↗pdf ↗

Debiased contrastive learning improves representation learning by correcting for same-label sampling.

problem Sampling negative examples from truly different labels improves performance in self-supervised representation learning.
method Developed a debiased contrastive objective that corrects for the sampling of same-label datapoints without true labels.
result The proposed debiased contrastive objective consistently outperforms state-of-the-art methods across vision, language, and reinforcement learning benchmarks.

New approach learns graph representations by contrasting first-order neighbors and graph diffusion views.

problem Learning node and graph level representations from graph data.
method Self-supervised approach using contrastive learning of multi-scale encodings.
result Achieves state-of-the-art performance on 8 out of 8 benchmarks.

New method uses contrastively trained GNNs for more reliable graph model evaluation.

problem Need effective methods to evaluate Graph Generative Models.
method Use representations from contrastively trained Graph Neural Networks (GNNs) for evaluation.
result Contrastively trained GNNs provide more reliable evaluation metrics than traditional or GNN-based approaches.

DACL tackles domain-specific contrastive learning by using Mixup noise.

problem Domain-specific contrastive learning methods rely on data augmentation techniques that require domain knowledge.
method DACL uses Mixup noise to create similar and dissimilar examples without domain-specific data augmentation.
result DACL outperforms other domain-agnostic noising methods and combines well with domain-specific methods.

Feature normalization prevents collapse in non-contrastive learning dynamics.

problem Non-contrastive learning can collapse into a single point due to lack of repulsive force.
method Extended previous theory based on L2 loss to cosine loss, considering feature normalization.
result Cosine loss induces stable equilibrium, preventing collapse even with insufficient repulsive force.

Riemann zero mean curvature examples in the Lorentz-Minkowski space are surfaces with zero mean curvature foliated by circles contained in parallel planes. In contrast to the Euclidean case, this family of surfaces presents new and rich features because of the variety of types of circles. In this paper, we give a geome…

2018-12-03abs ↗pdf ↗

The paper explores tail diversification in financial markets using entropy and mutual information.

problem Tail diversification in financial time series.
method Statistical independence through differential entropy and mutual information, using moments as contrast functions.
result Tail covariance matrix is a key driver of tail diversification.

Paper proposes a new regularization method to prevent model degradation under distribution shifts.

problem Model performance degrades under distribution shifts.
method Supervised contrastive learning with heterogeneous similarity.
result The proposed method outperforms existing regularization methods on benchmark datasets.

Was it fair that Harry was hired but not Barry? Was it fair that Pam was fired instead of Sam? How can one ensure fairness when an intelligent algorithm takes these decisions instead of a human? How can one ensure that the decisions were taken based on merit and not on protected attributes like race or sex? These are t…

2019-05-17abs ↗pdf ↗

In this paper we give two examples of sequences of embedded minimal planar domains in R3\mathbb{R}^3 which converge to singular laminations of R3\mathbb{R}^3. In contrast with the situation for embedded minimal disks, these examples do not arise from complete embedded minimal planar domains and highlight some of the su…

2011-07-19abs ↗pdf ↗

Enhances early risk assessments for pediatric outcomes using contrastive learning.

problem Improving risk assessments in early stages of pediatric development.
method Contrastive multi-modal framework that treats each time window as a distinct modality, training on all available data.
result Consistent improvements in early-stage risk assessments validated on real-world tasks.

Proves accuracy guarantees for self-supervised learning with correlated positive pairs.

problem Lack of theoretical guarantees for self-supervised learning with correlated positive pairs.
method Novel augmentation graph concept and spectral decomposition loss.
result Provably accurate features under linear probe evaluation.

Pairs of genus 2 mutant knots can have different Homfly polynomials, for example some 3-string satellites of Conway mutant pairs. We give examples which have different Kauffman 3-variable polynomials, answering a question raised by Dunfield et al in their study of genus 2 mutants. While pairs of genus 2 mutant knots ha…

2007-08-03abs ↗pdf ↗

We propose a method to generate audio adversarial examples that can attack a state-of-the-art speech recognition model in the physical world. Previous work assumes that generated adversarial examples are directly fed to the recognition model, and is not able to perform such a physical attack because of reverberation an…

2018-10-28abs ↗pdf ↗

The new notion of maturity-independent risk measures is introduced and contrasted with the existing risk measurement concepts. It is shown, by means of two examples, one set on a finite probability space and the other in a diffusion framework, that, surprisingly, some of the widely utilized risk measures cannot be used…

2007-10-20abs ↗pdf ↗

Improved visual representation learning with conditional negative sampling.

problem Learning strong unsupervised visual representations using contrastive learning.
method Introduce a family of mutual information estimators that sample negatives conditionally.
result Improves accuracy by 2-5% points on four standard image datasets.

In this article we study properly discontinuous actions on Hilbert manifolds giving new examples of complete Hilbert manifolds with nonnegative, respectively nonpositive, sectional curvature with infinite fundamental group. We also get examples of complete infinite dimensional Kähler manifolds with positive holomorphic…

2013-09-16abs ↗pdf ↗

This work tackles continual learning with semi-supervised data, showing that even with minimal labeled data, performance can match full-supervised methods.

problem Training deep networks on a stream of tasks without forgetting, especially when labeled data is scarce.
method Designing a novel CSSL method that leverages metric learning and consistency regularization to learn from both labeled and unlabeled data.
result Our method outperforms state-of-the-art methods trained with full supervision, achieving comparable performance with only 25% labeled data.

We introduce Contrastive Multivariate Singular Spectrum Analysis, a novel unsupervised method for dimensionality reduction and signal decomposition of time series data. By utilizing an appropriate background dataset, the method transforms a target time series dataset in a way that evinces the sub-signals that are enhan…

2018-10-31abs ↗pdf ↗

Diffuse optical tomography (DOT) has been investigated as an alternative imaging modality for breast cancer detection thanks to its excellent contrast to hemoglobin oxidization level. However, due to the complicated non-linear photon scattering physics and ill-posedness, the conventional reconstruction algorithms are s…

2017-12-04abs ↗pdf ↗

Unified framework for SSL methods linking contrastive and non-contrastive approaches.

problem Lack of theoretical foundations and design guidelines for SSL methods.
method Spectral manifold learning framework to unify SSL methods.
result Theoretical bridge between contrastive and non-contrastive methods.

For d=4,5,6d=4, 5, 6, we exhibit the first examples of complete finite volume hyperbolic dd-manifolds MM with cusps such that infinitely many dd-orbifolds MmM_{m} obtained from MM by generalized Dehn filling admit properly convex real projective structures. The orbifold fundamental groups of MmM_m are Gromov-hyperbolic …

2016-11-08abs ↗pdf ↗

Improved 3D MRI classification using contrastive learning with continuous proxy metadata.

problem Insufficient labelled data for 3D medical image classification.
method Proposed a new loss function (y-Aware InfoNCE) to leverage continuous proxy metadata in contrastive learning.
result 3D CNN model pre-trained on 10^4 multi-site healthy brain MRI scans outperforms fully-supervised methods.