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.

169,181 papers · 148 categories

Trend · papers per month

3876114152 · Jun 202019922001200920182026
48 results for negative pairs

A new method improves graph node embeddings by considering both nearby and distant node similarities.

problem Improving graph node embeddings by considering both nearby and distant node similarities.
method Distance-aware Negative Sampling (DNS) which maximizes cohesion at nearby node-pairs and separation at distant node-pairs.
result DNS outperforms baseline methods in downstream node classification tasks on various datasets and GRL algorithms.

GP-ND avoids obstacles in trajectory planning using Gaussian Process regression.

problem Avoiding obstacles in trajectory planning for real-world systems.
method GP-ND models negative data pairs using Gaussian distributions and maximizes their KL divergence from the GP to avoid them.
result GP-ND outperforms traditional GP learning in obstacle-aware trajectory planning.

Paper explains contrastive learning using cosine similarity and proposes mitigations for batch size effects.

problem Understanding and improving contrastive learning through batch size effects.
method Unified framework of cosine similarity, theoretical insights, and auxiliary loss.
result Performance improvement in small-batch settings through proposed auxiliary loss.

New surgeries on knots preserve contact structures.

problem Understanding how surgeries on Legendrian knots affect their contact structures.
method Analyzing surgeries on specific types of knots (twist and two-bridge knots) and proving distinct contact structures for certain surgeries.
result Negative rational surgeries on certain Legendrian knots yield distinct contact 3-manifolds.

Let MM be a closed orientable Riemannian surface. Consider an SO(3)-connection AA and a Higgs field Φ:Mso(3)Φ:M\to so(3). The pair (A,Φ)(A,Φ) naturally induces a cocycle over the geodesic flow of MM. We classify (up to gauge transformations) cohomologically trivial pairs (A,Φ)(A,Φ) with finite Fourier series in terms of a suita…

2010-12-02abs ↗pdf ↗

In this paper, we study the boundary behavior of the negatively curved Kähler-Einstein metric attached to a log canonical pair (X,D)(X,D) such that KX+DK_X+D is ample. In the case where XX is smooth and DD has simple normal crossings support (but possibly negative coefficients), we provide a very precise estimate on the p…

2014-10-20abs ↗pdf ↗

Improved KG completion on large datasets using entity-relation pair occurrences.

problem Performance bottleneck in training large-scale KGs due to memory constraints.
method Construct a joint learning model using pairwise occurrence information and increase negative sampling quality.
result Significant improvement in performance, especially with low batch size and negative examples.

The paper studies Kähler-Einstein metrics with singularities and their limits.

problem Analyzing Kähler-Einstein metrics with crossing edge singularities and their limits.
method Extending Guenancia's techniques, the paper shows convergence of metrics under specific angle conditions.
result Negatively curved Kähler-Einstein crossing edge metrics converge to mixed cusp and edge metrics smoothly away from the divisor.

Let (X,D) be a klt pair. Assuming either K_X+D big or -(K_X+D) ample, and that the coefficients of D are greater than 1/2, we show that the Kähler-Einstein metric attached to (X,D) -whenever it exists- has cone singularities along D on the log-smooth locus of the pair intersected with the ample locus of K_X+D (in the n…

2012-12-06abs ↗pdf ↗

The paper examines flatness conditions on normal metric contact pairs and proves properties of Einstein manifolds.

problem The study of flatness conditions on normal metric contact pairs.
method Analysis of conformal, concircular, and quasi-conformal curvature tensors.
result Normal metric contact pair manifolds with flat conformal, concircular, and quasi-conformal curvature tensors are Einstein manifolds with specific scalar and sectional curvatures.

In this paper, complement-equivalent arithmetic Zariski pairs will be exhibited answering in the negative a question by Eyral-Oka on these curves and their groups. A complement-equivalent arithmetic Zariski pair is a pair of complex projective plane curves having Galois-conjugate equations in some number field whose co…

2015-06-17abs ↗pdf ↗

A parameter-free statistical model is used to study multiplicity signatures for coherent production of charged-pairs of parabosons of order p=2 in comparison with those arising in the case of ordinary bosons, p=1. Two non-negative real parameters arise because "ab" and "ba" are fundamentally distinct pair operators of …

2003-08-07abs ↗pdf ↗

Model learns image-word associations from captions using contrastive learning.

problem Phrase grounding, associating image regions to caption words.
method Optimizing word-region attention to maximize mutual information, using language model guided word substitutions for negatives.
result Model achieves 76.7% accuracy on Flickr30K Entities benchmark, a 5.7% gain from weak supervision.

We discuss a correspondence between certain contact pairs on the one hand, and certain locally conformally symplectic forms on the other. In particular, we characterize these structures through suspensions of contactomorphisms. If the contact pair is endowed with a normal metric, then the corresponding lcs form is loca…

2010-06-02abs ↗pdf ↗

Given a compact orientable surface of negative Euler characteristic, there exists a natural pairing between the Teichmueuller space of the surface and the set of homotopy classes of simple loops and arcs. The length pairing sends a hyperbolic metric and a homotopy class of a simple loop or arc to the length of geodesic…

2002-11-27abs ↗pdf ↗

A new SSL method using whitening of latent-space features.

problem Efficiency and effectiveness of self-supervised representation learning.
method Proposes a new loss function based on whitening of latent-space features, avoiding the need for negatives and asymmetric networks.
result Improves efficiency and effectiveness of SSL by avoiding the need for negatives and asymmetric networks.

Our earlier twisted-face-pairing construction showed how to modify an arbitrary orientation-reversing face-pairing on a faceted 3-ball in a mechanical way so that the quotient is automatically a closed, orientable 3-manifold. The modifications were, in fact, parametrized by a finite set of positive integers, arbitraril…

2008-06-11abs ↗pdf ↗

Enhances contrastive learning for better representation learning on wild images.

problem Binary partition of views from same and different instances limits CL's performance.
method Doubly Contrastive Learning (CACR) with contrastive attraction and repulsion.
result CACR improves performance and robustness on wild image datasets.

Examining orbits ending in binary collisions for three equal masses under an inverse cube force.

problem Analyzing orbits ending in binary collisions for three equal masses under an inverse cube force.
method Reparametrizing orbits as geodesics on a negatively curved metric on a pair of pants.
result Visibility properties of negatively curved surfaces describe orbits beginning or ending in binary collisions.

A novel GNN architecture improves link prediction by combining positive and negative samples.

problem Link prediction accuracy limited by node-wise methods and increased model complexity of edge-wise methods.
method Proposes a novel GNN architecture that uses both positive and negative samples to inform node embeddings.
result The method retains the inference speed of node-wise models while achieving competitive accuracy with edge-wise alternatives.

Abstract result on correlations of pairs in exponentially growing discrete subsets.

problem Pair correlations in exponentially growing discrete subsets with weight functions.
method Proved abstract result on correlations of pairs of elements in an exponentially growing discrete subset with a weight function.
result Distribution function of unscaled differences is tδ2ett\mapsto\fracδ2\,e^{-|t|}, and pair correlation exhibits Poissonian behavior under certain conditions.

In this paper we develop a complete theory of factorization for isometries of hyperbolic 4-space. Of special interest is the case where a pair of isometries is linked, that is, when a pair of isometries can be expressed each as compositions of two involutions, one of which is common to both isometries. Here we develop …

2013-11-25abs ↗pdf ↗

This paper uses cointegration to identify profitable pair-trading strategies for Indian stocks.

problem Finding profitable pair-trading opportunities in Indian stock market.
method Cointegration analysis to identify co-movement stocks, forming pairs, evaluating portfolios.
result Pairs from auto and realty sectors generally yielded the highest returns, while IT sector pairs had negative returns.

Tests assess if predictions are prudent by comparing observations and predictions.

problem Assessing the prudence of predictions in samples of observations and predictions.
method Bootstrap and normal approximation algorithms for testing unweighted and weighted means, accounting for randomness.
result Tests reveal whether predictions are prudent by showing significantly negative mean differences.

Contrastive learning performance doesn't degrade with more negative samples.

problem Theoretical and empirical evidence of negative samples hurting performance in contrastive learning.
method Simple theoretical setting and empirical support on CIFAR-10 and CIFAR-100 datasets.
result Contrastive learning performance does not degrade with the number of negative samples.

New proof shows surfaces can have identical length spectra but not simple ones.

problem Identifying when two covers of a surface have identical length spectra but not simple ones.
method Characterized isomorphism of covers and constructed surfaces with identical spectra but different simple length spectra.
result Found surfaces with identical length spectra but not simple length isospectral covers.

In this paper, we prove that (1) For any integers n1n\geq 1 and g2g\geq 2, there is a closed 3-manifold MgnM_{g}^{n} which admits a distance nn Heegaard splitting of genus gg except that the pair of (g,n)(g, n) is (2,1)(2, 1). Furthermore, MgnM_{g}^{n} can be chosen to be hyperbolic except that the pair of (g,n)(g, n) is $(3, 1…

2013-02-21abs ↗pdf ↗

Proposes a new loss function to avoid treating missing information as positive or negative feedback.

problem Handling missing information in implicit feedback datasets for recommender systems.
method Introduces the Missing Information Loss (MIL) function and applies it to Matrix Factorization and Denoising Autoencoder.
result MIL achieves competitive performance in ranking-aware metrics and reduces the recommendation of popular items.

New method learns from either positive or negative feedback alone.

problem Limited applicability of existing preference optimization methods in scenarios with only unpaired feedback.
method Decouples learning from positive and negative feedback, using expectation-maximization (EM) to optimize probability of positive outcomes and explicitly incorporate negative examples.
result Stable learning from negative feedback alone demonstrated.

A pair of distinct free homotopy classes of closed curves in an orientable surface FF with negative Euler characteristic is said to be length equivalent if for any hyperbolic structure on FF, the length of the geodesic representative of one class is equal to the length of the geodesic representative of the other clas…

2015-11-20abs ↗pdf ↗

We answer Mark Kacs famous question - can one hear the shape of a drum - in the negative for orbifolds that are spherical space forms. This is done by extending the techniques developed by A. Ikeda on Lens Spaces to the orbifold setting. Several results are proved to show that with certain restrictions on the dimension…

2009-02-14abs ↗pdf ↗

New insights into negative sampling for graph representation learning.

problem Challenges in generating high-quality graph representations for large node sets.
method Theoretical analysis and derivation of negative sampling distribution correlation, proposing MCNS method.
result The negative sampling distribution should be positively but sub-linearly correlated to the positive sampling distribution.