Václav Rozhoň

Bernhard Haeupler, Richard Hladík, John Iacono et al.

We consider the problem of sorting $n$ items, given the outcomes of $m$ pre-existing comparisons. We present a simple and natural deterministic algorithm that runs in $O(m + \log T)$ time and does $O(\log T)$ comparisons, where $T$ is the number of total orders consistent with the pre-existing comparisons. Our running time and comparison bounds are best possible up to constant factors, thus resolving a problem that has been studied intensely since 1976 (Fredman, Theoretical Computer Science). The best previous algorithm with a bound of $O(\log T)$ on the number of comparisons has a time bound of $O(n^{2.5})$ and is more complicated. Our algorithm combines three classic algorithms: topological sort, heapsort with the right kind of heap, and efficient search in a sorted list. It outputs the items in sorted order one by one. It can be modified to stop early, thereby solving the important and more general top-$k$ sorting problem: Given $k$ and the outcomes of some pre-existing comparisons, output the smallest $k$ items in sorted order. The modified algorithm solves the top-$k$ sorting problem in minimum time and comparisons, to within constant factors.

Christoph Grunau, Ahmet Alper Özüdoğru, Václav Rozhoň et al.

The famous $k$-means++ algorithm of Arthur and Vassilvitskii [SODA 2007] is the most popular way of solving the $k$-means problem in practice. The algorithm is very simple: it samples the first center uniformly at random and each of the following $k-1$ centers is then always sampled proportional to its squared distance to the closest center so far. Afterward, Lloyd's iterative algorithm is run. The $k$-means++ algorithm is known to return a $Θ(\log k)$ approximate solution in expectation. In their seminal work, Arthur and Vassilvitskii [SODA 2007] asked about the guarantees for its following \emph{greedy} variant: in every step, we sample $\ell$ candidate centers instead of one and then pick the one that minimizes the new cost. This is also how $k$-means++ is implemented in e.g. the popular Scikit-learn library [Pedregosa et al.; JMLR 2011]. We present nearly matching lower and upper bounds for the greedy $k$-means++: We prove that it is an $O(\ell^3 \log^3 k)$-approximation algorithm. On the other hand, we prove a lower bound of $Ω(\ell^3 \log^3 k / \log^2(\ell\log k))$. Previously, only an $Ω(\ell \log k)$ lower bound was known [Bhattacharya, Eube, Röglin, Schmidt; ESA 2020] and there was no known upper bound.

Jan Grebík, Pavel Hubáček, Martin Koutecký et al.

We report new results on six problems in mathematics and theoretical computer science, produced with the assistance of Bolzano, an open-source multi-agent LLM system. Bolzano orchestrates rounds of interaction between parallel prover agents and a verifier agent while maintaining a persistent knowledge base that is carried across rounds. Classified using the significance-autonomy taxonomy of Feng et al., four of the six results reach the level of publishable research, and three of the six were produced essentially autonomously by Bolzano. Our results provide evidence that LLMs can contribute meaningfully to mathematical research, complementing recent reports by Bubeck et al., Woodruff et al., and others.

Christoph Grunau, Václav Rozhoň

This paper shows how to adapt several simple and classical sampling-based algorithms for the $k$-means problem to the setting with outliers. Recently, Bhaskara et al. (NeurIPS 2019) showed how to adapt the classical $k$-means++ algorithm to the setting with outliers. However, their algorithm needs to output $O(\log (k) \cdot z)$ outliers, where $z$ is the number of true outliers, to match the $O(\log k)$-approximation guarantee of $k$-means++. In this paper, we build on their ideas and show how to adapt several sequential and distributed $k$-means algorithms to the setting with outliers, but with substantially stronger theoretical guarantees: our algorithms output $(1+\varepsilon)z$ outliers while achieving an $O(1 / \varepsilon)$-approximation to the objective function. In the sequential world, we achieve this by adapting a recent algorithm of Lattanzi and Sohler (ICML 2019). In the distributed setting, we adapt a simple algorithm of Guha et al. (IEEE Trans. Know. and Data Engineering 2003) and the popular $k$-means$\|$ of Bahmani et al. (PVLDB 2012). A theoretical application of our techniques is an algorithm with running time $\tilde{O}(nk^2/z)$ that achieves an $O(1)$-approximation to the objective function while outputting $O(z)$ outliers, assuming $k \ll z \ll n$. This is complemented with a matching lower bound of $Ω(nk^2/z)$ for this problem in the oracle model.

Davin Choo, Christoph Grunau, Julian Portmann et al.

The k-means++ algorithm of Arthur and Vassilvitskii (SODA 2007) is a state-of-the-art algorithm for solving the k-means clustering problem and is known to give an O(log k)-approximation in expectation. Recently, Lattanzi and Sohler (ICML 2019) proposed augmenting k-means++ with O(k log log k) local search steps to yield a constant approximation (in expectation) to the k-means clustering problem. In this paper, we improve their analysis to show that, for any arbitrarily small constant $\eps > 0$, with only $\eps k$ additional local search steps, one can achieve a constant approximation guarantee (with high probability in k), resolving an open problem in their paper.