Euclidean
PulseAugur coverage of Euclidean — every cluster mentioning Euclidean across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New Heisenberg Lift Descriptor Enhances Handwriting Recognition Accuracy
Researchers have developed a new descriptor called the Heisenberg Lift Descriptor to improve online handwriting recognition systems. Unlike existing Euclidean descriptors that ignore stroke order, this new method incorp…
-
Hyperbolic embeddings show promise for biomedical differential diagnosis
Researchers have explored the use of hyperbolic graph representation learning for differential diagnosis in biomedical knowledge graphs. This approach aims to leverage the natural tree-like organization captured by hype…
-
New metric family optimizes covariance matrix calculations
A new research paper introduces a novel two-parameter family of Riemannian metrics for optimizing covariance matrices. This family encompasses common choices like Euclidean, Bures-Wasserstein, and affine-invariant metri…
-
New research details tight sampling complexity for log-concave distributions
Researchers have developed a new method to analyze the complexity of sampling smooth, strongly log-concave distributions using stochastic gradient oracles. The study establishes a tight bound for sampling complexity, wh…
-
New Gromov-Wasserstein Duality Enhances Graph Isomorphism Testing
Researchers have developed a new duality result for Gromov-Wasserstein (GW) distances, applicable to all finitely supported metric measure spaces. This advancement leads to improved sample complexity for empirical GW di…
-
Survey maps collaborative learning from Euclidean to graph-structured data
This survey paper explores the evolution of collaborative learning from traditional Euclidean data to more complex graph-structured data. It addresses the limitations of centralized machine learning, such as scalability…
-
New Sierpiński--Knopp Wasserstein distance accelerates persistence diagram analysis
Researchers have developed a new metric called the Sierpiński-Knopp (SK) Wasserstein distance for comparing persistence diagrams. This distance metric maps diagram points to a unit interval using a space-filling curve, …
-
New research explores scaffold supervision for molecular representation learning
Researchers have explored how to improve molecular representation learning by explicitly incorporating structural hierarchy and geometry. Their study focused on whether supervising molecular embeddings with a molecule's…
-
New Equivariant Sheaf Neural Networks Enhance Geometric Transport on Graphs
Researchers have introduced Equivariant Sheaf Neural Networks (ESNN), a novel architecture designed to enhance geometric transport on graphs. ESNN allows for directed, matrix-valued transport between neighboring vector …
-
New algorithms tackle online optimization with evolving feasible sets
Researchers have developed new algorithms for online optimization problems involving nested shrinking feasible regions. These algorithms, designed for settings like convex optimization with nested evolving feasible sets…
-
New research details derivative bounds for random tanh neural networks
Researchers have established high-probability bounds for the mixed input derivatives of wide random neural networks that utilize hyperbolic tangent (tanh) activation functions. The study, which focuses on networks with …
-
Hyperbolic geometry boosts tree-structured prototype networks
Researchers have explored the impact of latent manifold geometry on hierarchical classification models, comparing Euclidean and hyperbolic spaces. Their findings indicate that hyperbolic prototypes significantly preserv…
-
Hyperbolic geometry boosts latent space topology in classification models
Researchers explored the impact of latent manifold choice on hierarchical classification models, comparing Euclidean space with hyperbolic space (Poincaré ball). Their findings indicate that hyperbolic prototypes signif…
-
Computer vision study reveals gap in initialization-free bundle adjustment
A new experimental study revisits initialization-free bundle adjustment (InitFree BA), a technique in computer vision that aims to directly recover camera poses and scene structure without traditional geometric initiali…
-
New methods enhance AI planning with latent world models · 4 sources tracked
Researchers have developed new methods to improve planning in latent world models, which are systems that predict outcomes of action sequences. One approach, Reinforced Planning (RP1), learns to improve multi-step plans…
-
New method validates clustering solutions with <3% optimality gap
Researchers have developed a novel method to evaluate the quality of Minimum Sum-of-Squares Clustering (MSSC) solutions, particularly for large datasets where finding the global optimum is computationally prohibitive. T…
-
New EHGCN method fuses Euclidean and hyperbolic geometry for event perception
Researchers have developed EHGCN, a novel approach for event stream perception that integrates Euclidean and hyperbolic geometry. This method aims to improve the capture of long-range dependencies and hierarchical struc…
-
New framework unifies landmark shape spaces with induced metrics
Researchers have developed a novel framework that unifies existing approaches to landmark shape spaces. This new construction integrates Kendall's landmark shape spaces, which factor out rigid motions and fix scale, wit…
-
New framework uses Equivariant Neural Fields for scalable travel-time prediction
Researchers have introduced Equivariant Neural Eikonal Solvers, a new framework that combines Equivariant Neural Fields with Neural Eikonal Solvers. This approach uses a shared neural network backbone conditioned on sig…
-
New Fisher Widths Analyze Statistical Manifold Complexity
This paper introduces two new functionals, the primal Fisher width and the inverse-Fisher width, to analyze Gaussian-width complexity on statistical manifolds. These widths offer complementary insights into local parame…