Riemannian manifold
PulseAugur coverage of Riemannian manifold — every cluster mentioning Riemannian manifold across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
New research explores advanced AI for EEG-based emotion recognition · 2 papers
Two new research papers explore advanced techniques for recognizing emotions from electroencephalography (EEG) data. The first paper introduces a multi-scale temporal framework that processes EEG signals across differen…
-
New framework unifies geometry from robot navigation to black holes
A new research paper titled "The Field Knows: Cross-Dimensional Geometry from Navigation to Black Holes" introduces a continuous metric field framework. This framework uses a single causal contrastive loss to encode sce…
-
New Hopfield Networks Achieve 10x Capacity Boost Using SU(d) Groups
Researchers have introduced generalized Hopfield networks that utilize continuous variables on Riemannian manifolds, specifically focusing on symmetric spaces associated with special unitary groups SU(d). This new appro…
-
Sphere Retraction Normalizations generalize deep neural network training
Researchers have introduced Sphere Retraction Normalizations, a new framework for training deep neural networks that generalizes existing residual connection methods. This approach recasts residual connections on a Riem…
-
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 method approximates diffusion processes on differential forms
Researchers have developed a novel data-driven method to approximate the projected ambient connection Laplacian, which operates on differential forms over Riemannian manifolds sampled by point clouds. This approach exte…
-
New algorithm achieves optimal regret for decentralized Riemannian optimization
Researchers have developed a new method for decentralized online optimization on Riemannian manifolds, specifically addressing strongly geodesically convex functions. This work establishes the first static regret bound …
-
Matrix optimization landscape analyzed using Riemannian geometry
This paper analyzes the global landscape of a fixed-rank matrix optimization problem using the Burer-Monteiro factorization and Riemannian geometry. The research characterizes the search space into three regions based o…
-
New theory extends statistical efficiency to Riemannian manifolds
A new paper by Lin Liu proposes an asymptotic efficiency theory applicable to statistical models with non-Euclidean structures, such as Riemannian manifolds. This work extends existing theories, which are largely confin…
-
New RIPO method overcomes exploration collapse in LLM reinforcement learning
A new research paper introduces Riemannian Isometric Policy Optimization (RIPO), a novel approach to address exploration collapse in reinforcement learning for Large Language Models (LLMs). The paper identifies a fundam…
-
New spectral embedding method incorporates group symmetries for improved data analysis
Researchers have developed a new spectral embedding method that incorporates group symmetries, such as rotations, into affinity kernels. This approach improves dimensionality reduction and clustering for datasets with i…
-
New sampling methods improve efficiency for complex distributions · 2 sources tracked
Researchers have developed a new method called Gradient-free Riemannian Langevin Sampler (GRiLS) to improve the efficiency of sampling multimodal probability distributions. This approach aims to overcome limitations in …
-
New Manifold GCN Layers Outperform State-of-the-Art on Graph Data
Researchers have developed new graph neural network layers designed for data residing on Riemannian manifolds. These layers, named Manifold GCN, are based on a diffusion equation and a tangent multilayer perceptron, off…
-
New Mirror Descent Framework Extends Optimization to Riemannian Manifolds
Researchers have developed a generalized framework for Mirror Descent (MD) on Riemannian manifolds, extending its applicability to complex optimization problems. This new Riemannian Mirror Descent (RMD) framework includ…
-
New Method Approximates Whittle-Matern Fields on Discretized Manifolds
Researchers have developed a new method for approximating Whittle-Matern fields using discrete Gauss Markov Random Fields (GMRFs) on discretized Riemannian manifolds. This approach offers a universal approximation schem…
-
New Riemannian Cross-Covariance Method Enhances ML on Complex Data
Researchers have developed a new method for estimating covariance for random objects on nonlinear Riemannian manifolds, which are increasingly used in machine learning for data like shapes and matrices. This intrinsic R…
-
New Riemannian Framework Enhances Low-Rank Optimal Transport Solvers
Researchers have developed a new Riemannian geometric framework to improve low-rank optimal transport (OT) solvers. This approach models factored couplings as submanifolds and uses the Fisher-Rao product metric to deriv…
-
Geodesic Flow Matching enhances AI for SLAM and image restoration
Researchers have developed Geodesic Flow Matching (GFM) to improve denoising and restoration tasks by accounting for the geometric constraints of data representations. The first paper applies GFM to neuro-symbolic reaso…
-
New method fixes radius distortion in generative models on manifolds
Researchers have developed a new method called Radial Compensation (RC) to address distortions in generative models operating on Riemannian manifolds. Standard approaches map samples from Euclidean tangent space to the …