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.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

29 results for “Earth-Mover”

Distances for WiFi Based Topological Indoor Mappingcs.LG

Study compares distances for indoor WiFi mapping, finding Earth Mover's Distance effective.

problem Indoor localization and mapping using WiFi signals.

method Comparison of distance measures and kernel density estimation.

result Earth Mover's Distance is most beneficial for indoor localization.

WiFi indoor mapping distance measures Earth Mover's Distance kernel density estimation

2018-09-19abs ↗pdf ↗

On the Definiteness of Earth Mover's Distance and Its Relation to Set Intersectioncs.LG

Positive definite kernels are an important tool in machine learning that enable efficient solutions to otherwise difficult or intractable problems by implicitly linearizing the problem geometry. In this paper we develop a set-theoretic interpretation of the Earth Mover's Distance (EMD) and propose Earth Mover's Interse…

2015-10-09abs ↗pdf ↗

Learning quantum data with the quantum Earth Mover's distancequant-ph

Quantum Earth Mover's distance improves stability and efficiency in quantum learning.

problem Quantum learning's loss landscapes often lead to poor local minima and gradients.

method Introduced the quantum Earth Mover's (EM) distance and proposed a quantum Wasserstein generative adversarial network (qWGAN).

result The quantum EM distance makes quantum learning more stable and efficient.

quantum machine learning quantum Wasserstein Wasserstein-1 distance quantum generative adversarial networks quantum data

2021-01-08abs ↗pdf ↗

Low-Complexity Data-Parallel Earth Mover's Distance Approximationscs.LG

New algorithms speed up EMD computation by four orders of magnitude.

problem High computational complexity of EMD for discrete probability distributions.

method Data-parallel approximation algorithms for linear time complexity.

result Four orders of magnitude faster than existing methods.

Earth Mover's Distance Approximation Algorithms Graphics Processing Units Text Classification Image Recognition

2018-12-05abs ↗pdf ↗

Should Adversarial Attacks Use Pixel p-Norm?cs.LG

Study shows various pixel p-norm measures do not match human perception of adversarial attacks.

problem Understanding human perception of adversarial attacks on image classification systems.

method Performed a behavioral study comparing different p-norm measures and alternative metrics.

result Human perception of adversarial attacks does not align with pixel p-norm measures and other metrics.

adversarial attacks image classification human perception p-norm earth mover's distance

2019-06-06abs ↗pdf ↗

Constructing Graph Node Embeddings via Discrimination of Similarity Distributionsstat.ML

A new method for graph node embeddings by discriminating similarity distributions.

problem Unsupervised learning of node embeddings in graphs.

method Maximizing the earth mover distance between distributions of similarities of similar and dissimilar nodes.

result Generates embeddings with state-of-the-art performance in link prediction.

graph node embeddings unsupervised learning discrimination of similarity distributions link prediction earth mover distance

2018-10-06abs ↗pdf ↗

The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regressioncs.LG

New method for neural networks to predict histogram data.

problem Lack of principled approach for histogram regression.

method Pinball loss applied to cumulative histogram.

result Accuracy similar to EMD with less computational cost.

histogram regression Deep Learning quantiles Earth Mover's Distance neural networks

2021-06-03abs ↗pdf ↗

People Mover's Distance: Class level geometry using fast pairwise data adaptive transportation costsstat.ML

Algorithm calculates distances between US counties based on people living there.

problem Defining a network graph for large, non-i.i.d. data sets.

method Co-clustering diffusion metric and data adaptive transportation cost.

result Approximate Earth Mover's Distance for US county comparisons.

Earth Mover's Distance Co-clustering Data Adaptive Cost US Counties Non-i.i.d. Data

2017-07-03abs ↗pdf ↗

Relaxed Wasserstein with Applications to GANsstat.ML

New RW distances improve GANs performance.

problem Wasserstein-1 distance limitations and slow training in GANs.

method Introducing Relaxed Wasserstein distances and applying them to GANs.

result RWGANs outperform other GANs on real images.

GANs Wasserstein Relaxed Wasserstein Kullback-Leibler Earth-Mover

2017-05-19abs ↗pdf ↗

Quantifying error in estimates of human brain fiber directions using Earth Mover's Distancestat.ML

Diffusion-weighted MR imaging (DWI) is the only method we currently have to measure connections between different parts of the human brain in vivo. To elucidate the structure of these connections, algorithms for tracking bundles of axonal fibers through the subcortical white matter rely on local estimates of the fiber …

2014-11-19abs ↗pdf ↗

PMD: An Optimal Transportation-based User Distance for Recommender Systemscs.IR

PMD measures user distances using optimal transportation, improving recommendation accuracy.

problem Sparse data and lack of co-rated items in collaborative filtering.

method PMD is an Earth Mover's Distance-based user distance measure that utilizes all ratings.

result PMD achieves superior recommendation accuracy, especially in sparse data scenarios.

recommender systems collaborative filtering user distance optimal transportation Earth Mover's Distance

2019-09-10abs ↗pdf ↗

Finding NEEMo: Geometric Fitting using Neural Estimation of the Energy Mover's Distancestat.ML

New neural method calculates EMD for particle physics data.

problem Metric for particle collider events based on Wasserstein metric.

method Neural network architecture estimating EMD using Kantorovich-Rubinstein duality.

result Differentiable way to calculate EMD for geometric fitting.

neural networks optimal transport geometric fitting particle physics Earth Mover's Distance

2022-09-30abs ↗pdf ↗

Federated Learning with Non-IID Datacs.LG

Federated learning struggles with non-IID data, but a strategy improves model accuracy.

problem Federated learning accuracy drops significantly with non-IID data.

method Identified weight divergence as the cause, quantified by EMD, and proposed a solution of sharing a subset of globally shared data.

result Accuracy can be increased by 30% for CIFAR-10 with only 5% globally shared data.

federated learning non-IID data accuracy weight divergence earth mover's distance

2018-06-02abs ↗pdf ↗

Sparse Coding with Earth Mover's Distance for Multi-Instance Histogram Representationcs.LG

Sparse coding (Sc) has been studied very well as a powerful data representation method. It attempts to represent the feature vector of a data sample by reconstructing it as the sparse linear combination of some basic elements, and a $L_2$ norm distance function is usually used as the loss function for the reconstructio…

2015-02-09abs ↗pdf ↗

A Direct

\tilde{O}(1/ε)

Iteration Parallel Algorithm for Optimal Transportcs.DS

Direct parallel algorithm for optimal transport with optimal runtime.

problem Computing the Wasserstein distance between two distributions efficiently.

method Primal-dual extragradient method for first-order iterations.

result Solves optimal transport to additive ε with O(1/ε) parallel depth.

Optimal transport Wasserstein distance Parallel algorithms First-order methods Extragradient method

2019-06-03abs ↗pdf ↗

Maximum Likelihood Estimation for Learning Populations of Parametersmath.ST

Estimates population parameters from limited trials per individual.

problem Estimating parameters from Bernoulli trials with limited data per individual.

method Maximum Likelihood Estimation (MLE) for optimally estimating the underlying distribution.

result MLE achieves optimal error bounds of

\mathcal{O}(\frac{1}{t})

for

t < c\log{N}

and

\mathcal{O}(\frac{1}{\sqrt{t\log N}})

for larger

t

Maximum Likelihood Estimation Bernoulli Trials Optimal Error Bounds Earth Mover's Distance Statistical Minimax

2019-02-12abs ↗pdf ↗

Distance Based Source Domain Selection for Sentiment Classificationcs.IR

Method selects optimal source domain for better cross-domain sentiment classification.

problem Improving sentiment classification on unseen domains with limited labeled data.

method Predictive measure based on distance functions between source and target domains.

result Significant improvement in cross-domain classification error compared to random selection.

sentiment classification source domain selection distance functions cross-domain learning Earth Mover's distance

2018-08-28abs ↗pdf ↗

An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers' Outputscs.LG

This paper analyzes and improves the effectiveness of BN techniques in controlling Internal Covariate Shift.

problem The effectiveness of BN techniques in reducing Internal Covariate Shift (ICS) is limited, especially for high-dimensional outputs and noise.

method The paper introduces a measure for ICS using the Earth Mover (EM) distance, derives bounds for this measure, and proposes a unitization algorithm to further bound ICS.

result The unitization algorithm effectively bounds ICS, especially for low-dimensional outputs and small noise, and can be tuned to control ICS.

Internal Covariate Shift Batch Normalization Earth Mover Distance Deep Neural Networks Unitization Algorithm

2020-01-09abs ↗pdf ↗

Near-linear time approximation algorithms for optimal transport via Sinkhorn iterationcs.DS

Paper shows near-linear time approximation for optimal transport.

problem Computing optimal transport distances efficiently.

method New analysis of Sinkhorn iteration and greedy coordinate descent algorithm, Greenkhorn.

result Achieves near-linear time approximation for optimal transport distances.

optimal transport Sinkhorn iteration Greenkhorn algorithm near-linear time

2017-05-26abs ↗pdf ↗

Image Data Compression for Covariance and Histogram Descriptorsstat.ML

Covariance and histogram image descriptors provide an effective way to capture information about images. Both excel when used in combination with special purpose distance metrics. For covariance descriptors these metrics measure the distance along the non-Euclidean Riemannian manifold of symmetric positive definite mat…

2014-12-04abs ↗pdf ↗

A Tutorial Review of Bayesian Optimization with Gaussian Processes to Accelerate Stationary Point Searchesstat.ML

Bayesian optimization with Gaussian processes speeds up searches for stationary points.

problem Accelerating searches for stationary points on potential energy surfaces.

method Unified Bayesian optimization view using Gaussian process regression with derivative observations, inverse-distance kernels, and active learning.

result Surrogates can reduce the number of expensive electronic structure evaluations by an order of magnitude.

Bayesian optimization Gaussian processes stationary points potential energy surfaces active learning

2026-03-11abs ↗pdf ↗

Grade Inflation in Generative Modelscs.AI

Generative models' evaluation scores can be misleading, leading to inflated grades.

problem Misleading evaluation scores for generative models.

method Analyzed and compared various scores for evaluating synthetic vs. ground-truth data.

result The Eden score avoids grade inflation and better aligns with human perception.

grade inflation generative models evaluation scores equidensity scores Rényi entropy

2024-12-31abs ↗pdf ↗

Sinkhorn Divergences for Unbalanced Optimal Transportmath.OC

This paper generalizes Sinkhorn algorithm for unbalanced optimal transport.

problem Handling distributions with different total mass and robustness to outliers.

method Alternates between standard Sinkhorn updates and pointwise application of a contractive function.

result Defines Sinkhorn divergences that are differentiable, positive, definite, convex, and robust.

optimal transport unbalanced transport Sinkhorn algorithm divergences geometric axioms

2019-10-28abs ↗pdf ↗

Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attackscs.LG

Defense against Wasserstein adversarial attacks using randomized smoothing.

problem Certified robustness against Wasserstein adversarial attacks.

method Randomized smoothing applied to the space of flows between images, bounding Wasserstein distance by L_1 distance.

result Significantly improved accuracy under Wasserstein adversarial attacks compared to unprotected models.

adversarial attacks Wasserstein metric randomized smoothing robustness image classification

2019-10-23abs ↗pdf ↗

Clust-PSI-PFL: A Population Stability Index Approach for Clustered Non-IID Personalized Federated Learningcs.LG

Clust-PSI-PFL uses PSI to improve accuracy and fairness in federated learning.

problem Non-IID data biases federated learning performance.

method Clust-PSI-PFL uses clustering and PSI to form homogeneous groups of clients.

result Clust-PSI-PFL delivers up to 18% higher global accuracy and improves client fairness.

federated learning non-IID data population stability index personalized federated learning cluster-based approach

2025-12-23abs ↗pdf ↗

Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embeddingcs.LG

New graph kernel scales well with graph size and number, achieving state-of-the-art performance.

problem Graph kernels lose structure information when representing graphs.

method Proposes a positive-definite global alignment graph kernel using random features and random graph embeddings.

result Achieves quasi-linear scalability with respect to graph size and number.

graph kernels global alignment random features random graph embeddings quasi-linear scalability

2019-11-25abs ↗pdf ↗

Regularized Optimal Transport and the Rot Mover's Distancestat.ML

Unified framework for smooth convex regularization of optimal transport problems.

problem Optimizing transport plans with regularization.

method Unified framework based on matrix nearness problems with Bregman divergences.

result Regularized optimal transport equivalent to matrix nearness problem.

Optimal Transport Regularization Bregman Divergences Dykstra's Algorithm Newton-Raphson Method

2016-10-20abs ↗pdf ↗

Complex-valued embeddings of generic proximity datacs.LG

Complex embeddings handle non-metric proximity data better than traditional methods.

problem Proximities not always metric or inner product-based, causing convergence issues.

method Proposes complex-valued embeddings for non-vectorial data.

result Complex embeddings outperform traditional techniques on benchmarks.

proximity data complex embeddings non-metric non-psd machine learning

2020-08-31abs ↗pdf ↗

An Efficient Shared-memory Parallel Sinkhorn-Knopp Algorithm to Compute the Word Mover's Distancecs.LG

This paper speeds up WMD computation for multiple queries efficiently.

problem Efficiently computing the semantic dissimilarity between text documents.

method Adapting the Sinkhorn-Knopp algorithm to compute WMD of one document against many targets in parallel.

result 67x speedup on 96 cores compared to sequential and naive parallel methods.

Word Mover's Distance Optimal Transportation Parallel Computing Sinkhorn-Knopp Semantic Similarity

2020-05-14abs ↗pdf ↗