In representative democracy, a redistricting map is chosen to partition an electorate into districts which each elects a representative. A valid redistricting map must satisfy a collection of constraints such as being compact, contiguous, and of almost-equal population. However, these constraints are loose enough to enable an enormous ensemble of valid redistricting maps. This enables a partisan legislature to gerrymander by choosing a map which unfairly favors it. In this paper, we introduce an interpretable and tractable distance measure over redistricting maps which does not use election results and study its implications over the ensemble of redistricting maps. Specifically, we define a central map which may be considered "most typical" and give a rigorous justification for it by showing that it mirrors the Kemeny ranking in a scenario where we have a committee voting over a collection of redistricting maps to be drawn. We include runnning time and sample complexity analysis for our algorithms, including some negative results which hold using any algorithm. We further study outlier detection based on this distance measure and show that our framework can detect some gerrymandered maps. More precisely, we show some maps that are widely considered to be gerrymandered that lie very far away from our central maps in comparison to a large ensemble of valid redistricting maps. Since our distance measure does not rely on election results, this gives a significant advantage in gerrymandering detection which is lacking in all previous methods.

The widespread use of machine learning algorithms in settings that directly affect human lives has instigated significant interest in designing variants of these algorithms that are provably fair. Recent work in this direction has produced numerous algorithms for the fundamental problem of clustering under many different notions of fairness. Perhaps the most common family of notions currently studied is group fairness, in which proportional group representation is ensured in every cluster. We extend this direction by considering the downstream application of clustering and how group fairness should be ensured for such a setting. Specifically, we consider a common setting in which a decision-maker runs a clustering algorithm, inspects the center of each cluster, and decides an appropriate outcome (label) for its corresponding cluster. In hiring for example, there could be two outcomes, positive (hire) or negative (reject), and each cluster would be assigned one of these two outcomes. To ensure group fairness in such a setting, we would desire proportional group representation in every label but not necessarily in every cluster as is done in group fair clustering. We provide algorithms for such problems and show that in contrast to their NP-hard counterparts in group fair clustering, they permit efficient solutions. We also consider a well-motivated alternative setting where the decision-maker is free to assign labels to the clusters regardless of the centers' positions in the metric space. We show that this setting exhibits interesting transitions from computationally hard to easy according to additional constraints on the problem. Moreover, when the constraint parameters take on natural values we show a randomized algorithm for this setting that always achieves an optimal clustering and satisfies the fairness constraints in expectation. Finally, we run experiments on real world datasets that validate the effectiveness of our algorithms.

Metric clustering is fundamental in areas ranging from Combinatorial Optimization and Data Mining, to Machine Learning and Operations Research. However, in a variety of situations we may have additional requirements or knowledge, distinct from the underlying metric, regarding which pairs of points should be clustered together. To capture and analyze such scenarios, we introduce a novel family of stochastic pairwise constraints, which we incorporate into several essential clustering objectives (radius/median/means). Moreover, we demonstrate that these constraints can succinctly model an intriguing collection of applications, including among others Individual Fairness in clustering and Must-link constraints in semi-supervised learning. Our main result consists of a general framework that yields approximation algorithms with provable guarantees for important clustering objectives, while at the same time producing solutions that respect the stochastic pairwise constraints. Furthermore, for certain objectives we devise improved results in the case of Must-link constraints, which are also the best possible from a theoretical perspective. Finally, we present experimental evidence that validates the effectiveness of our algorithms.

The main focus of this paper is radius-based (supplier) clustering in the two-stage stochastic setting with recourse, where the inherent stochasticity of the model comes in the form of a budget constraint. We also explore a number of variants where additional constraints are imposed on the first-stage decisions, specifically matroid and multi-knapsack constraints. Our eventual goal is to provide results for supplier problems in the most general distributional setting, where there is only black-box access to the underlying distribution. To that end, we follow a two-step approach. First, we develop algorithms for a restricted version of each problem, in which all possible scenarios are explicitly provided; second, we employ a novel scenario-discarding variant of the standard Sample Average Approximation (SAA) method, in which we crucially exploit properties of the restricted-case algorithms. We finally note that the scenario-discarding modification to the SAA method is necessary in order to optimize over the radius.

Matching is one of the most fundamental and broadly applicable problems across many domains. In these diverse real-world applications, there is often a degree of uncertainty in the input which has led to the study of stochastic matching models. Here, each edge in the graph has a known, independent probability of existing derived from some prediction. Algorithms must probe edges to determine existence and match them irrevocably if they exist. Further, each vertex may have a patience constraint denoting how many of its neighboring edges can be probed. We present new ordered contention resolution schemes yielding improved approximation guarantees for some of the foundational problems studied in this area. For stochastic matching with patience constraints in general graphs, we provide a $0.382$-approximate algorithm, significantly improving over the previous best $0.31$-approximation of Baveja et al. (2018). When the vertices do not have patience constraints, we describe a $0.432$-approximate random order probing algorithm with several corollaries such as an improved guarantee for the Prophet Secretary problem under Edge Arrivals. Finally, for the special case of bipartite graphs with unit patience constraints on one of the partitions, we show a $0.632$-approximate algorithm that improves on the recent $1/3$-guarantee of Hikima et al. (2021).

Clustering is a fundamental unsupervised learning problem where a dataset is partitioned into clusters that consist of nearby points in a metric space. A recent variant, fair clustering, associates a color with each point representing its group membership and requires that each color has (approximately) equal representation in each cluster to satisfy group fairness. In this model, the cost of the clustering objective increases due to enforcing fairness in the algorithm. The relative increase in the cost, the ```````''price of fairness,'' can indeed be unbounded. Therefore, in this paper we propose to treat an upper bound on the clustering objective as a constraint on the clustering problem, and to maximize equality of representation subject to it. We consider two fairness objectives: the group utilitarian objective and the group egalitarian objective, as well as the group leximin objective which generalizes the group egalitarian objective. We derive fundamental lower bounds on the approximation of the utilitarian and egalitarian objectives and introduce algorithms with provable guarantees for them. For the leximin objective we introduce an effective heuristic algorithm. We further derive impossibility results for other natural fairness objectives. We conclude with experimental results on real-world datasets that demonstrate the validity of our algorithms.

Clustering is a foundational problem in machine learning with numerous applications. As machine learning increases in ubiquity as a backend for automated systems, concerns about fairness arise. Much of the current literature on fairness deals with discrimination against protected classes in supervised learning (group fairness). We define a different notion of fair clustering wherein the probability that two points (or a community of points) become separated is bounded by an increasing function of their pairwise distance (or community diameter). We capture the situation where data points represent people who gain some benefit from being clustered together. Unfairness arises when certain points are deterministically separated, either arbitrarily or by someone who intends to harm them as in the case of gerrymandering election districts. In response, we formally define two new types of fairness in the clustering setting, pairwise fairness and community preservation. To explore the practicality of our fairness goals, we devise an approach for extending existing $k$-center algorithms to satisfy these fairness constraints. Analysis of this approach proves that reasonable approximations can be achieved while maintaining fairness. In experiments, we compare the effectiveness of our approach to classical $k$-center algorithms/heuristics and explore the tradeoff between optimal clustering and fairness.

In clustering problems, a central decision-maker is given a complete metric graph over vertices and must provide a clustering of vertices that minimizes some objective function. In fair clustering problems, vertices are endowed with a color (e.g., membership in a group), and the requirements of a valid clustering might also include the representation of colors in the solution. Prior work in fair clustering assumes complete knowledge of group membership. In this paper, we generalize this by assuming imperfect knowledge of group membership through probabilistic assignments, and present algorithms in this more general setting with approximation ratio guarantees. We also address the problem of "metric membership", where group membership has a notion of order and distance. Experiments are conducted using our proposed algorithms as well as baselines to validate our approach, and also surface nuanced concerns when group membership is not known deterministically.

Gerrymandering is the process of drawing electoral district maps in order to manipulate the outcomes of elections. Partisan gerrymandering occurs when political parties use this practice to gain an advantage. Increasingly, computers are involved in both drawing biased, partisan districts and in attempts to measure and regulate this practice. Several of the most high-profile proposals to measure partisan gerrymandering involve the use of past voting data. Prior work primarily studies the ability of these metrics to detect gerrymandering. However, it does not account for how legislation based on the metrics could affect voter behavior or be circumvented via strategic voting. We show that even in a two-party election, using past voting data can affect strategyproofness. We further focus on the proposal to ban "outlier maps," which appear biased toward a particular party when compared to a random sampling of legal maps. We introduce a game which models the iterative sequence of voting and redrawing districts under the restriction that outlier maps are forbidden. Using this game, we illustrate strategies for a majority party to increase its seat count by voting strategically. This leads to a heuristic for gaming the system when outliers are banned, which we explore experimentally. Applying a version of our heuristic to past North Carolina voting data shows that these strategies can be found for real states under some stricter assumptions. Finally, we address some questions from the recent US Supreme Court case, Rucho v. Common Cause, that relate to our model.

Column-sparse packing problems arise in several contexts in both deterministic and stochastic discrete optimization. We present two unifying ideas, (non-uniform) attenuation and multiple-chance algorithms , to obtain improved approximation algorithms for some well-known families of such problems. As three main examples, we attain the integrality gap, up to lower-order terms, for known LP relaxations for k -column-sparse packing integer programs (Bansal et al., Theory of Computing , 2012) and stochastic k -set packing (Bansal et al., Algorithmica , 2012), and go “half the remaining distance” to optimal for a major integrality-gap conjecture of Füredi, Kahn, and Seymour on hypergraph matching ( Combinatorica , 1993).

We present a new approach to approximating the Maximum Duo-Preservation String Mapping Problem (MPSM) based on massaging the constraints into a tractable matching problem. MPSM was introduced in Chen, Chen, Samatova, Peng, Wang, and Tang [Chen et al., 2014] as the complement to the well-studied Minimum Common String Partition problem (MCSP). Prior work also considers the k-MPSM and k-MCSP variants in which each letter occurs at most k times in each string. The authors of [Chen et al., 2014] showed a k^2-appoximation for k >= 3 and 2-approximation for k = 2. Boria, Kurpisz, Leppänen, and Mastrolilli [Boria et al., 2014] gave a 4-approximation independent of k and showed that even 2-MPSM is APX-Hard. A series of improvements led to the current best bounds of a (2 + epsilon)-approximation for any epsilon > 0 in n^{O(1/epsilon)} time for strings of length n and a 2.67-approximation running in O(n^2) time, both by Dudek, Gawrychowski, and Ostropolski-Nalewaja [Dudek et al., 2017]. Here, we show that a 2.67-approximation can surprisingly be achieved in O(n) time for alphabets of constant size and O(n + alpha^7) for alphabets of size alpha. Recently, Mehrabi [Mehrabi, 2017] introduced the more general weighted variant, Maximum Weight Duo-Preservation String Mapping (MWPSM) and provided a 6-approximation. Our approach gives a 2.67-approximation to this problem running in O(n^3) time. This approach can also find an 8/(3(1-epsilon))-approximation to MWPSM for any epsilon > 0 in O(n^2 epsilon^{-1} lg{epsilon^{-1}}) time using the approximate weighted matching algorithm of Duan and Pettie [Duan and Pettie, 2014]. Finally, we introduce the first streaming algorithm for MPSM. We show that a single pass suffices to find a 4-approximation on the size of an optimal solution using only O(alpha^2 lg{n}) space.

The classical Four Russians speedup for computing edit distance (a.k.a. Levenshtein distance), due to Masek and Paterson [Masek and Paterson, 1980], involves partitioning the dynamic programming table into k-by-k square blocks and generating a lookup table in O(psi^{2k} k^2 |Sigma|^{2k}) time and O(psi^{2k} k |Sigma|^{2k}) space for block size k, where psi depends on the cost function (for unit costs psi = 3) and |Sigma| is the size of the alphabet. We show that the O(psi^{2k} k^2) and O(psi^{2k} k) factors can be improved to O(k^2 lg{k}) time and O(k^2) space. Thus, we improve the time and space complexity of that aspect compared to Masek and Paterson [Masek and Paterson, 1980] and remove the dependence on psi. We further show that for certain problems the O(|Sigma|^{2k}) factor can also be reduced. Using this technique, we show a new algorithm for the fundamental problem of one-against-many banded alignment. In particular, comparing one string of length m to n other strings of length m with maximum distance d can be performed in O(n m + m d^2 lg{d} + n d^3) time. When d is reasonably small, this approaches or meets the current best theoretic result of O(nm + n d^2) achieved by using the best known pairwise algorithm running in O(m + d^2) time [Myers, 1986][Ukkonen, 1985] while potentially being more practical. It also improves on the standard practical approach which requires O(n m d) time to iteratively run an O(md) time pairwise banded alignment algorithm. Regarding pairwise comparison, we extend the classic result of Masek and Paterson [Masek and Paterson, 1980] which computes the edit distance between two strings in O(m^2/log{m}) time to remove the dependence on psi even when edits have arbitrary costs from a penalty matrix. Crochemore, Landau, and Ziv-Ukelson [Crochemore, 2003] achieved a similar result, also allowing for unrestricted scoring matrices, but with variable-sized blocks. In practical applications of the Four Russians speedup wherein space efficiency is important and smaller block sizes k are used (notably k < |Sigma|), Kim, Na, Park, and Sim [Kim et al., 2016] showed how to remove the dependence on the alphabet size for the unit cost version, generating a lookup table in O(3^{2k} (2k)! k^2) time and O(3^{2k} (2k)! k) space. Combining their work with our result yields an improvement to O((2k)! k^2 lg{k}) time and O((2k)! k^2) space.

Column-sparse packing problems arise in several contexts in both deterministic and stochastic discrete optimization. We present two unifying ideas, (non-uniform) attenuation and multiple-chance algorithms, to obtain improved approximation algorithms for some well-known families of such problems. As three main examples, we attain the integrality gap, up to lower-order terms, for known LP relaxations for k-column sparse packing integer programs (Bansal et al., Theory of Computing, 2012) and stochastic k-set packing (Bansal et al., Algorithmica, 2012), and go “half the remaining distance” to optimal for a major integrality-gap conjecture of Füredi, Kahn and Seymour on hypergraph matching (Combinatorica, 1993).

Comparing a string to a large set of sequences is a key subroutine in greedy heuristics for clustering genomic data. Clustering 16S rRNA gene sequences into operational taxonomic units (OTUs) is a common method used in studying microbial communities. We present a new approach to greedy clustering using a trie-like data structure and Four Russians speedup. We evaluate the running time of our method in terms of the number of comparisons it makes during clustering and show in experimental results that the number of comparisons grows linearly with the size of the dataset as opposed to the quadratic running time of other methods. We compare the clusters output by our method to the popular greedy clustering tool UCLUST. We show that the clusters we generate can be both tighter and larger.

Online matching has received significant attention over the last 15 years due to its close connection to Internet advertising. As the seminal work of Karp, Vazirani, and Vazirani has an optimal (1 - 1/epsilon) competitive ratio in the standard adversarial online model, much effort has gone into developing useful online models that incorporate some stochasticity in the arrival process. One such popular model is the "known I.I.D. model" where different customer-types arrive online from a known distribution. We develop algorithms with improved competitive ratios for some basic variants of this model with integral arrival rates, including: (a) the case of general weighted edges, where we improve the best-known ratio of 0.667 due to [Haeupler, Mirrokni and Zadimoghaddam WINE 2011] to 0.705; and (b) the vertex-weighted case, where we improve the 0.7250 ratio of [Jaillet and Lu Math. Oper. Res 2013] to 0.7299. We also consider two extensions, one is "known I.I.D." with non-integral arrival rate and stochastic rewards; the other is "known I.I.D." b-matching with non-integral arrival rate and stochastic rewards. We present a simple non-adaptive algorithm which works well simultaneously on the two extensions. One of the key ingredients of our improvement is the following (offline) approach to bipartite-matching polytopes with additional constraints. We first add several valid constraints in order to get a good fractional solution f; however, these give us less control over the structure of f. We next remove all these additional constraints and randomly move from f to a feasible point on the matching polytope with all coordinates being from the set {0, 1/k, 2/k,..., 1} for a chosen integer k. The structure of this solution is inspired by [Jaillet and Lu Math. Oper. Res 2013] and is a tractable structure for algorithm design and analysis. The appropriate random move preserves many of the removed constraints (approximately [exactly] with high probability [in expectation]). This underlies some of our improvements, and, we hope, could be of independent interest.