Manifold Micro-Surgery with Linearly Nearly Euclidean Metrics
The Ricci flow is a method of manifold surgery, which can trim manifolds to more regular. However, in most cases, the Rich flow tends to develop singularities and lead to divergence of the solution. In this paper, we propose linearly nearly Euclidean metrics to assist manifold micro-surgery, which means that we prove the dynamical stability and convergence of such metrics under the Ricci-DeTurck flow. From the information geometry and mirror descent points of view, we give the approximation of the steepest descent gradient flow on the linearly nearly Euclidean manifold with dynamical stability. In practice, the regular shrinking or expanding of Ricci solitons with linearly nearly Euclidean metrics will provide a geometric optimization method for the solution on a manifold.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Thoughts on the Consistency between Ricci Flow and Neural Network Behavior
The Ricci flow is a partial differential equation for evolving the metric in a Riemannian manifold to make it more regular. On the other hand, neural networks seem to have similar geometric behavior for specific tasks. I…
ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
Long-context inference is constrained by KV-cache memory, which grows linearly with sequence length; KV-cache compression therefore hinges on reliably selecting which past tokens to retain. Most geometry-based eviction m…
Outlier DetectionRiemannian Federated Learning via Averaging Gradient Stream
In recent years, federated learning has garnered significant attention as an efficient and privacy-preserving distributed learning paradigm. In the Euclidean setting, Federated Averaging (FedAvg) and its variants are a c…
Federated LearningPrivacy PreservingProbing for Representation Manifolds in Superposition
This paper introduces the Manifold Probe, a supervised method for discovering representation manifolds in superposition. The method generalizes linear regression probes by learning the space of features of a concept that…
Large-scale entity resolution via microclustering Ewens--Pitman random partitions
We introduce the microclustering Ewens--Pitman model for random partitions, obtained by scaling the strength parameter of the Ewens--Pitman model linearly with the sample size. The resulting random partition is shown to …
Entity Resolution