SearcharxivSearch

arXiv subjects

Shuqin Zhang

Publications and source records attributed to Shuqin Zhang.

3 recordsLinked to original sources

Atoms of Compacta on Closed Surfaces

For any compact set $K$ lying on a closed surface $\mathcal{S}$ we introduce a closed equivalence relation $\sim$, called the {\em Schönflies equivalence} on $K$. We show that every class $[x]_\sim$ of $\sim$ is a continuum and that the resulting quotient space $K\!/\!\sim$ is a {\em Peano compactum}. By definition, all components of a Peano compactum are locally connected and for any $\varepsilon>0$ only finitely many of them have diameter greater than $\varepsilon$. The decomposition $\mathcal{D}_K=\{[x]_\sim: x\in K\}$ refines every other upper semicontinuous decomposition of $K$ into subcontinua that has a Peano compactum as its quotient space. In other words, $\mathcal{D}_K$ is the {\em core decomposition of $K$} with Peano quotient. The elements of $\mathcal{D}_K$ are called {\em atoms} of $K$. We also show that for any branched covering $f: \mathcal{S}^*\rightarrow \mathcal{S}$ from a closed surface $\mathcal{S}^*$ to $\mathcal{S}$, every atom of $f^{-1}(K)$ is sent into an atom of $K$. If $f$ is even a covering, it sends every atom of $f^{-1}(K)$ onto an atom of $K$. We illustrate our theory with examples and show that it cannot be generalized to $n$-manifolds with $n\ge 3$ by providing a detailed counterexample in~$\mathbb{R}^3$.

math.GN

Frostman and Fourier characterisations of fractal dimensions

We examine Frostman-type characterisations and other extremal measure criteria for a range of fractal dimensions of sets. In particular we derive properties of the less familiar modified lower box dimension and upper correlation dimension. We also express a number of fractal dimensions in terms of Fourier properties of measures.

math.MG

Investigating Neuron Disturbing in Fusing Heterogeneous Neural Networks

Fusing deep learning models trained on separately located clients into a global model in a one-shot communication round is a straightforward implementation of Federated Learning. Although current model fusion methods are shown experimentally valid in fusing neural networks with almost identical architectures, they are rarely theoretically analyzed. In this paper, we reveal the phenomenon of neuron disturbing, where neurons from heterogeneous local models interfere with each other mutually. We give detailed explanations from a Bayesian viewpoint combining the data heterogeneity among clients and properties of neural networks. Furthermore, to validate our findings, we propose an experimental method that excludes neuron disturbing and fuses neural networks via adaptively selecting a local model, called AMS, to execute the prediction according to the input. The experiments demonstrate that AMS is more robust in data heterogeneity than general model fusion and ensemble methods. This implies the necessity of considering neural disturbing in model fusion. Besides, AMS is available for fusing models with varying architectures as an experimental algorithm, and we also list several possible extensions of AMS for future work.

cs.LG