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

63125188250 · Jun 202019922001200920172026
48 results for divergence metrics

Develops a new divergence framework that combines ff-divergences and IPMs.

problem Comparing distributions that are not absolutely continuous.
method Introduces (f,Γ)(f,Γ)-divergences as a two-stage mass-redistribution/mass-transport process.
result Improves estimation, learning, and uncertainty quantification in GANs for heavy-tailed distributions.

Unified view of KL-divergence and IPMs via DRE, with new DRM metrics.

problem Unified understanding of KL-divergence and IPMs.
method Unified representation via maximum likelihood density-ratio estimation (DRE).
result Unified form of IPMs and novel DRM metrics.

The paper explores statistical and topological properties of sliced probability divergences.

problem Understanding the topological, statistical, and computational consequences of slicing divergences.
method Deriving theoretical properties of sliced probability divergences, including metric axioms preservation and weak continuity.
result Sliced divergences share similar topological properties and have stable sample complexity.

Bregman divergences generalize measures such as the squared Euclidean distance and the KL divergence, and arise throughout many areas of machine learning. In this paper, we focus on the problem of approximating an arbitrary Bregman divergence from supervision, and we provide a well-principled approach to analyzing such…

2019-05-28abs ↗pdf ↗

Study on 3D Lie groups finds all generalized Einstein metrics.

problem Classifying generalized Einstein metrics on 3D Lie groups.
method Developed theory of left-invariant generalized pseudo-Riemannian metrics, computed Ricci tensor, determined all metrics.
result Determined all generalized Einstein metrics on three-dimensional Lie groups.

Paper explores how text generation quality and diversity metrics relate to distribution fitting.

problem Unclear relation between text generation quality and diversity metrics and distribution fitting.
method Theoretical approach to prove a linear combination of quality and diversity metrics can be a divergence metric.
result CR/NRR proposed as a better substitute for BLEU/Self-BLEU metrics.

Paper introduces SDM for detecting LLM hallucinations, improving on entropy tests.

problem Challenges of Large Language Models (LLMs) with non-factual, nonsensical responses.
method Joint clustering on sentence embeddings to measure semantic divergence between prompts and responses.
result SDM framework detects deeper form of arbitrariness in LLM responses.

New method makes quality metrics scale-invariant for high-dimensional data.

problem Scale sensitivity in quality metrics affects the accuracy of data projections.
method Analytical and empirical investigation of stress and KL divergence; introduction of a scale-invariant technique.
result The proposed technique accurately captures expected behavior and makes metrics scale-invariant.

New rigidity results for quasi-Einstein metrics with non-zero divergence-free vector fields.

problem Classifying quasi-Einstein metrics with specific vector field properties.
method Analyzing quasi-Einstein metrics on closed manifolds and near-horizon geometries of extreme black holes.
result These metrics always admit a one-parameter group of isometries generated by the divergence-free vector field.

On a compact nn-dimensional manifold MM, it is well known that a critical metric of the total scalar curvature, restricted to the space of metrics with unit volume, is Einstein. It has been conjectured that a critical metric of the total scalar curvature, restricted to the space of metrics with constant scalar curvat…

2017-10-20abs ↗pdf ↗

The Wasserstein probability metric has received much attention from the machine learning community. Unlike the Kullback-Leibler divergence, which strictly measures change in probability, the Wasserstein metric reflects the underlying geometry between outcomes. The value of being sensitive to this geometry has been demo…

2017-05-30abs ↗pdf ↗

New metrics quantify implementation risk in portfolio backtesting, revealing systematic differences in engine implementations.

problem Systematic divergence in backtested portfolio metrics due to differences in engine implementations.
method Formalized implementation risk, proposed four metrics, executed 15 strategies through five engines, analyzed source-code defects.
result Implementation risk introduces measurable ambiguity in performance attribution, but does not alter investment decisions.

The paper explores geometry of probability measures and barycenter maps.

problem Understanding the space of probability measures and their barycenter.
method Information geometry, Fisher metric, dualistic structures, divergences, geodesics.
result Recent developments in the geometry of probability measures and barycenter.

New formulations for comparing metric measure spaces with arbitrary positive measures.

problem Comparing metric measure spaces with arbitrary positive measures.
method Two novel formulations: a divergence and a conic lifting approach.
result Efficiently solvable formulations for comparing metric spaces with arbitrary positive measures.

The divergence theorem in its usual form applies only to suitably smooth vector fields. For vector fields which are merely piecewise smooth, as is natural at a boundary between regions with different physical properties, one must patch together the divergence theorem applied separately in each region. We give an elegan…

1994-04-02abs ↗pdf ↗

New proof finds three divergence-free vector fields for any 3D manifold.

problem Proving the existence of divergence-free vector fields on 3D manifolds.
method Using geometric properties of eigenspinors in three dimensions.
result Found three divergence-free vector fields that are orthogonal and have the same length at every point.

We study 1-parameter families in the space M1G\mathscr{M}^G_1 of GG-invariant, unit volume metrics on a given compact, connected, almost-effective homogeneous space M=G/HM=G/H. In particular, we focus on diverging sequences, i.e. which are not contained in any compact subset of M1G\mathscr{M}^G_1, and we prove some structu…

2018-12-19abs ↗pdf ↗

Introduces Cauchy-Schwarz divergence for domain adaptation.

problem Evaluating discrepancy between source and target domains in unsupervised domain adaptation.
method Introduces Cauchy-Schwarz divergence as a measure for evaluating discrepancy between marginal and conditional distributions.
result CS divergence offers a tighter generalization error bound than Kullback-Leibler divergence.

Study optimizes tree-based models for better alignment of predicted scores and actual probabilities.

problem Traditional calibration metrics fail to align predicted scores with actual probabilities when score distributions deviate from the underlying data.
method Optimizes tree-based models (Random Forest, XGBoost) using Kullback-Leibler (KL) divergence to minimize the difference between predicted and true probability distributions.
result Optimized tree-based models yield superior alignment between predicted scores and actual probabilities without significant performance loss.

LMC algorithm converges to target in Chi-squared and Renyi divergence.

problem Sampling from target distribution using LMC with strong dissipativity and smoothness conditions.
method LMC algorithm with strong dissipativity and first-order smoothness, initialized with Gaussian.
result LMC reaches ε-neighborhood of target in Chi-squared and Renyi divergence in O(λ²dε⁻¹) steps.

We study the geometry of probability distributions with respect to a generalized family of Csiszár ff-divergences. A member of this family is the relative αα-entropy which is also a Rényi analog of relative entropy in information theory and known as logarithmic or projective power divergence in statistics. We apply E…

2020-01-14abs ↗pdf ↗

This paper introduces a new method to train normalizing flows using precision-recall divergences.

problem Training generative models with mode dropping and low-quality samples.
method Introduces PR-divergences and proposes a novel generative model to minimize precision-recall trade-offs.
result Normalizing flows can be trained to achieve specific precision-recall trade-offs using PR-divergences.