AKAdam Karczmarz

Adam Karczmarz

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Adam Karczmarz has a total of 25 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Strongly Polynomial Parallel Work-Depth Tradeoffs for Directed SSSP

    by Adam Karczmarz, Wojciech Nadara, Marek Sokołowski

    In this paper, we show new strongly polynomial work-depth tradeoffs for computing single-source shortest paths (SSSP) in non-negatively weighted directed graphs in parallel. Most importantly, we prove that directed SSSP can be solved within $\tilde{O}(m+n^{2-ε})$ work and $\tilde{O}(n^{1-ε})$ depth for some positive $ε>0$. In particular, for dense graphs with non-negative real weights, we provide the first nearly work-efficient strongly polynomial algorithm with sublinear depth. Our result immediately yields improved strongly polynomial parallel algorithms for min-cost flow and the assignment problem. It also leads to the first non-trivial strongly polynomial dynamic algorithm for minimum mean cycle. Moreover, we develop efficient parallel algorithms in the Word RAM model for several variants of SSSP in graphs with exponentially large edge weights.

  • Open Access

    Towards Scalable and Practical Batch-Dynamic Connectivity (Abstract)

    by Quinten De Man, Laxman Dhulipala, Adam Karczmarz, Jakub Łącki, Julian Shun, Zhongqi Wang


  • Open Access

    Accurate Estimation of Feature Importance Faithfulness for Tree Models

    by Mateusz Gajewski, Adam Karczmarz, Mateusz Rapicki, Piotr Sankowski

    In this paper, we consider a perturbation-based metric of predictive faithfulness of feature rankings (or attributions) that we call PGI squared When applied to decision tree-based regression models, the metric can be computed exactly and efficiently for arbitrary independent feature perturbation distributions. In particular, the computation does not involve Monte Carlo sampling that has been typically used for computing similar metrics and which is inherently prone to inaccuracies. As a second contribution, we proposed a procedure for constructing feature ranking based on PGI squared. Our results indicate the proposed ranking method is comparable to the widely recognized SHAP explainer, offering a viable alternative for assessing feature importance in tree-based models.

  • Open Access

    Towards Scalable and Practical Batch-Dynamic Connectivity

    by Quinten De Man, Laxman Dhulipala, Adam Karczmarz, Jakub Łącki, Julian Shun, Zhongqi Wang

    We study the problem of dynamically maintaining the connected components of an undirected graph subject to edge insertions and deletions. We give the first parallel algorithm for the problem which is work-efficient, supports batches of updates, runs in polylogarithmic depth, and uses only linear total space. The existing algorithms for the problem either use super-linear space, do not come with strong theoretical bounds, or are not parallel. On the empirical side, we provide the first implementation of the cluster forest algorithm, the first linear-space and poly-logarithmic update time algorithm for dynamic connectivity. Experimentally, we find that our algorithm uses up to 19.7x less space and is up to 6.2x faster than the level-set algorithm of HDT, arguably the most widely-implemented dynamic connectivity algorithm with strong theoretical guarantees.

  • Open Access

    Exact Shortest Paths with Rational Weights on the Word RAM

    by Adam Karczmarz, Wojciech Nadara, Marek Sokołowski

    Exact computation of shortest paths in weighted graphs has been traditionally studied in one of two settings. First, one can assume that the edge weights are real numbers and all the performed operations on reals (typically comparisons and additions) take constant time. Classical Dijkstra's and Bellman-Ford algorithms have been described in this setting. More efficient exact shortest paths algorithms have been obtained for integer-weighted graphs. Integrality assumption not only enables faster algorithms but also allows implementing the aforementioned algorithms in a much more realistic word RAM model where only arithmetic operations on $O(\log{n})$-bit integers are performed in constant time. On the word RAM one can as efficiently exactly encode even \emph{rational-weighted} instances with $O(\log{n})$-bit numerators and denominators. However, the known exact real-weighted shortest paths algorithms, run on such a rational input, can easily encounter intermediate values of $Θ(n)$ bits if represented exactly. This leads to a factor-$Ω(n)$ slowdown on the word RAM. At the same time, the scaling algorithms suited for integer weights do not produce exact solutions for rational inputs without dramatically increasing their accuracy. In this paper, we design randomized exact single-source shortest paths algorithms for rational-weighted graphs on the word RAM. Most importantly, in the non-negative case, we obtain a near-linear time algorithm matching Dijkstra's algorithm running time up to polylogarithmic factors. In presence of negative weights, we give an $\tilde{O}(n^{2.5})$-time algorithm breaking through the best known strongly polynomial bound attained by Bellman-Ford for sufficiently dense graphs.

  • Open Access

    Max $s,t$-Flow Oracles and Negative Cycle Detection in Planar Digraphs

    by Adam Karczmarz

    We study the maximum $s,t$-flow oracle problem on planar directed graphs where the goal is to design a data structure answering max $s,t$-flow value (or equivalently, min $s,t$-cut value) queries for arbitrary source-target pairs $(s,t)$. For the case of polynomially bounded integer edge capacities, we describe an exact max $s,t$-flow oracle with truly subquadratic space and preprocessing, and sublinear query time. Moreover, if $(1-ε)$-approximate answers are acceptable, we obtain a static oracle with near-linear preprocessing and $\tilde{O}(n^{3/4})$ query time and a dynamic oracle supporting edge capacity updates and queries in $\tilde{O}(n^{6/7})$ worst-case time. To the best of our knowledge, for directed planar graphs, no (approximate) max $s,t$-flow oracles have been described even in the unweighted case, and only trivial tradeoffs involving either no preprocessing or precomputing all the $n^2$ possible answers have been known. One key technical tool we develop on the way is a sublinear (in the number of edges) algorithm for finding a negative cycle in so-called dense distance graphs. By plugging it in earlier frameworks, we obtain improved bounds for other fundamental problems on planar digraphs. In particular, we show: (1) a deterministic $O(n\log(nC))$ time algorithm for negatively-weighted SSSP in planar digraphs with integer edge weights at least $-C$. This improves upon the previously known bounds in the important case of weights polynomial in $n$, and (2) an improved $O(n\log{n})$ bound on finding a perfect matching in a bipartite planar graph.

  • Open Access

    Deterministic Fully Dynamic SSSP and More

    by Jan van Den Brand, Adam Karczmarz

    We present the first non-trivial fully dynamic algorithm maintaining exact single-source distances in unweighted graphs. This resolves an open problem stated by Sankowski [COCOON 2005] and van den Brand and Nanongkai [FOCS 2019]. Previous fully dynamic single-source distances data structures were all approximate, but so far, non-trivial dynamic algorithms for the exact setting could only be ruled out for polynomially weighted graphs (Abboud and Vassilevska Williams, [FOCS 2014]). The exact unweighted case remained the main case for which neither a subquadratic dynamic algorithm nor a quadratic lower bound was known. Our dynamic algorithm works on directed graphs, is deterministic, and can report a single-source shortest paths tree in subquadratic time as well. Thus we also obtain the first deterministic fully dynamic data structure for reachability (transitive closure) with subquadratic update and query time. This answers an open problem of van den Brand, Nanongkai, and Saranurak [FOCS 2019]. Finally, using the same framework we obtain the first fully dynamic data structure maintaining all-pairs $(1+ε)$-approximate distances within non-trivial sub-$n^ω$ worst-case update time while supporting optimal-time approximate shortest path reporting at the same time. This data structure is also deterministic and therefore implies the first known non-trivial deterministic worst-case bound for recomputing the transitive closure of a digraph.

  • Open Access

    Subquadratic dynamic path reporting in directed graphs against an adaptive adversary

    by Adam Karczmarz, Anish Mukherjee, Piotr Sankowski

    We study reachability and shortest paths problems in dynamic directed graphs. Whereas algebraic dynamic data structures supporting edge updates and reachability/distance queries have been known for quite a long time, they do not, in general, allow reporting the underlying paths within the same time bounds, especially against an adaptive adversary. In this paper we develop the first known fully dynamic reachability data structures working against an adaptive adversary and supporting edge updates and path queries for two natural variants: (1) point-to-point path reporting, and (2) single-source reachability tree reporting. For point-to-point queries in DAGs, we achieve O(n1.529) worst-case update and query bounds, whereas for tree reporting in DAGs, the respective worst-case bounds are O(n1.765). More importantly, we show how to lift these algorithms to work on general graphs at the cost of increasing the bounds to n1+5/6+o(1) and making the update times amortized. On the way to accomplishing these goals, we obtain two interesting subresults. We give subquadratic fully dynamic algorithms for topological order (in a DAG), and strongly connected components. To the best of our knowledge, such algorithms have not been described before. Additionally, we provide deterministic incremental data structures for (point-to-point or single-source) reachability and shortest paths that can handle edge insertions and report the respective paths within subquadratic worst-case time bounds. For reachability and (1+є)-approximate shortest paths in weighted directed graphs, these bounds match the best known dynamic matrix inverse-based randomized bounds for fully dynamic reachability [v.d.Brand, Nanongkai and Saranurak, FOCS’19]. For exact shortest paths in unweighted graphs, the obtained bounds in the incremental setting polynomially improve upon the respective best known randomized update/distance query bounds in the fully dynamic setting.