Search for: All records

The 𝓁₂² min-sum k-clustering problem is to partition an input set into clusters C_1,…,C_k to minimize ∑_{i=1}^k ∑_{p,q ∈ C_i} ‖p-q‖₂². Although 𝓁₂² min-sum k-clustering is NP-hard, it is not known whether it is NP-hard to approximate 𝓁₂² min-sum k-clustering beyond a certain factor. In this paper, we give the first hardness-of-approximation result for the 𝓁₂² min-sum k-clustering problem. We show that it is NP-hard to approximate the objective to a factor better than 1.056 and moreover, assuming a balanced variant of the Johnson Coverage Hypothesis, it is NP-hard to approximate the objective to a factor better than 1.327. We then complement our hardness result by giving a fast PTAS for 𝓁₂² min-sum k-clustering. Specifically, our algorithm runs in time O(n^{1+o(1)}d⋅ 2^{(k/ε)^O(1)}), which is the first nearly linear time algorithm for this problem. We also consider a learning-augmented setting, where the algorithm has access to an oracle that outputs a label i ∈ [k] for input point, thereby implicitly partitioning the input dataset into k clusters that induce an approximately optimal solution, up to some amount of adversarial error α ∈ [0,1/2). We give a polynomial-time algorithm that outputs a (1+γα)/(1-α)²-approximation to 𝓁₂² min-sum k-clustering, for a fixed constant γ > 0. 

We give improved algorithms for maintaining edge-orientations of a fully-dynamic graph, such that the maximum out-degree is bounded. On one hand, we show how to orient the edges such that maximum out-degree is proportional to the arboricity $$\alpha$$ of the graph, in, either, an amortised update time of $$O(\log^2 n \log \alpha)$$, or a worst-case update time of $$O(\log^3 n \log \alpha)$$. On the other hand, motivated by applications including dynamic maximal matching, we obtain a different trade-off. Namely, the improved update time of either $$O(\log n \log \alpha)$$, amortised, or $$O(\log ^2 n \log \alpha)$$, worst-case, for the problem of maintaining an edge-orientation with at most $$O(\alpha + \log n)$$ out-edges per vertex. Finally, all of our algorithms naturally limit the recourse to be polylogarithmic in $$n$$ and $$\alpha$$. Our algorithms adapt to the current arboricity of the graph, and yield improvements over previous work: Firstly, we obtain deterministic algorithms for maintaining a $$(1+\varepsilon)$$ approximation of the maximum subgraph density, $$\rho$$, of the dynamic graph. Our algorithms have update times of $$O(\varepsilon^{-6}\log^3 n \log \rho)$$ worst-case, and $$O(\varepsilon^{-4}\log^2 n \log \rho)$$ amortised, respectively. We may output a subgraph $$H$$ of the input graph where its density is a $$(1+\varepsilon)$$ approximation of the maximum subgraph density in time linear in the size of the subgraph. These algorithms have improved update time compared to the $$O(\varepsilon^{-6}\log ^4 n)$$ algorithm by Sawlani and Wang from STOC 2020. Secondly, we obtain an $$O(\varepsilon^{-6}\log^3 n \log \alpha)$$ worst-case update time algorithm for maintaining a $$(1~+~\varepsilon)\textnormal{OPT} + 2$$ approximation of the optimal out-orientation of a graph with adaptive arboricity $$\alpha$$, improving the $$O(\varepsilon^{-6}\alpha^2 \log^3 n)$$ algorithm by Christiansen and Rotenberg from ICALP 2022. This yields the first worst-case polylogarithmic dynamic algorithm for decomposing into $$O(\alpha)$$ forests. Thirdly, we obtain arboricity-adaptive fully-dynamic deterministic algorithms for a variety of problems including maximal matching, $$\Delta+1$$ colouring, and matrix vector multiplication. All update times are worst-case $$O(\alpha+\log^2n \log \alpha)$$, where $$\alpha$$ is the current arboricity of the graph. For the maximal matching problem, the state-of-the-art deterministic algorithms by Kopelowitz, Krauthgamer, Porat, and Solomon from ICALP 2014 runs in time $$O(\alpha^2 + \log^2 n)$$, and by Neiman and Solomon from STOC 2013 runs in time $$O(\sqrt{m})$$. We give improved running times whenever the arboricity $$\alpha \in \omega( \log n\sqrt{\log\log n})$$.