arXiv subjects

Rucha Kulkarni

Publications and source records attributed to Rucha Kulkarni.

7 recordsLinked to original sources

arXiv2025

Fairly Dividing Non-identical Random Items: Just Sample or Match

We study the question of existence and fast computation of fair and efficient allocations of indivisible resources among agents with additive valuations. As such allocations may not exist for arbitrary instances, we ask if they exist for \textit{typical} or \textit{random} instances, meaning when the utility values of agents for the resources are drawn from certain distributions. If such allocations exist with high probability for typical instances, and furthermore if they can be computed efficiently, this would imply that we could quickly resolve a real world resource allocation scenario in a fair and efficient manner with high probability. This implication has made this setting popular and well studied in fair resource allocation. In this paper, we extend the previously studied formal models of this problem to non-identical items. We assume that every item is associated with a distribution $\mathcal{U}_j$, and every agent's utility value for the item is drawn independently from $\mathcal{U}_j$. We show that envy-free fair and maximum social welfare efficient allocations exist with high probability in the asymptotic setting, meaning when the number of agents $n$ and items $m$ are large. Further we show that when $m=O(n\log n),$ then by only sampling $O(\log m)$ or $O((\log m)^2)$ utility values per item instead of all the $n,$ we can compute these allocations in $\tilde{O}(m)$ time. Finally, we simulate our algorithms on randomly generated instances and show that even for small instances, we suffer small multiplicative losses in the fairness and efficiency guarantees even for small sized instances, and converge to fully optimal guarantees quickly.

cs.GT↗

arXiv2023

1/2 Approximate MMS Allocation for Separable Piecewise Linear Concave Valuations

We study fair distribution of a collection of m indivisible goods among a group of n agents, using the widely recognized fairness principles of Maximin Share (MMS) and Any Price Share (APS). These principles have undergone thorough investigation within the context of additive valuations. We explore these notions for valuations that extend beyond additivity. First, we study approximate MMS under the separable (piecewise-linear) concave (SPLC) valuations, an important class generalizing additive, where the best known factor was 1/3-MMS. We show that 1/2-MMS allocation exists and can be computed in polynomial time, significantly improving the state-of-the-art. We note that SPLC valuations introduce an elevated level of intricacy in contrast to additive. For instance, the MMS value of an agent can be as high as her value for the entire set of items. Further, the equilibrium computation problem, which is polynomial-time for additive valuations, becomes intractable for SPLC. We use a relax-and-round paradigm that goes through competitive equilibrium and LP relaxation. Our result extends to give (symmetric) 1/2-APS, a stronger guarantee than MMS. APS is a stronger notion that generalizes MMS by allowing agents with arbitrary entitlements. We study the approximation of APS under submodular valuation functions. We design and analyze a simple greedy algorithm using concave extensions of submodular functions. We prove that the algorithm gives a 1/3-APS allocation which matches the current best-known factor. Concave extensions are hard to compute in polynomial time and are, therefore, generally not used in approximation algorithms. Our approach shows a way to utilize it within analysis (while bypassing its computation), and might be of independent interest.

cs.GT↗

arXiv2023

Approximating APS under Submodular and XOS valuations with Binary Marginals

We study the problem of fairly dividing indivisible goods among a set of agents under the fairness notion of Any Price Share (APS). APS is known to dominate the widely studied Maximin share (MMS). Since an exact APS allocation may not exist, the focus has traditionally been on the computation of approximate APS allocations. Babaioff et al. studied the problem under additive valuations, and asked (i) how large can the APS value be compared to the MMS value? and (ii) what guarantees can one achieve beyond additive functions. We partly answer these questions by considering valuations beyond additive, namely submodular and XOS functions, with binary marginals. For the submodular functions with binary marginals, also known as matroid rank functions (MRFs), we show that APS is exactly equal to MMS. Consequently, we get that an exact APS allocation exists and can be computed efficiently while maximizing the social welfare. Complementing this result, we show that it is NP-hard to compute the APS value within a factor of 5/6 for submodular valuations with three distinct marginals of {0, 1/2, 1}. We then consider binary XOS functions, which are immediate generalizations of binary submodular functions in the complement free hierarchy. In contrast to the MRFs setting, MMS and APS values are not equal under this case. Nevertheless, we show that under binary XOS valuations, $MMS \leq APS \leq 2 \cdot MMS + 1$. Further, we show that this is almost the tightest bound we can get using MMS, by giving an instance where $APS \geq 2 \cdot MMS$. The upper bound on APS, implies a ~0.1222-approximation for APS under binary XOS valuations. And the lower bound implies the non-existence of better than 0.5-APS even when agents have identical valuations, which is in sharp contrast to the guaranteed existence of exact MMS allocation when agent valuations are identical.

cs.GT↗

arXiv2021

Dynamic Data-Race Detection through the Fine-Grained Lens

Data races are among the most common bugs in concurrency. The standard approach to data-race detection is via dynamic analyses, which work over executions of concurrent programs, instead of the program source code. The rich literature on the topic has created various notions of dynamic data races, which are known to be detected efficiently when certain parameters (e.g., number of threads) are small. However, the \emph{fine-grained} complexity of all these notions of races has remained elusive, making it impossible to characterize their trade-offs between precision and efficiency. In this work we establish several fine-grained separations between many popular notions of dynamic data races. The input is an execution trace with $N$ events, $T$ threads and $L$ locks. Our main results are as follows. First, we show that happens-before (HB) races can be detected in $O(N\cdot \min(T, L))$ time, improving over the standard $O(N\cdot T)$ bound when $L=o(T)$. Moreover, we show that even reporting an HB race that involves a read access is hard for 2-orthogonal vectors (2-OV). This is the first rigorous proof of the conjectured quadratic lower-bound in detecting HB races. Second, we show that the recently introduced synchronization-preserving races are hard to detect for OV-3 and thus have a cubic lower bound, when $T=\Omega(N)$. This establishes a complexity separation from HB races which are known to be less expressive. Third, we show that lock-cover races are hard for 2-OV, and thus have a quadratic lower-bound, even when $T=2$ and $L = \omega(\log N)$. The similar notion of lock-set races is known to be detectable in $O(N\cdot L)$ time, and thus we achieve a complexity separation between the two. Moreover, we show that lock-set races become hitting-set (HS)-hard when $L=\Theta(N)$, and thus also have a quadratic lower bound, when the input is sufficiently complex.

cs.PL↗

arXiv2020

Indivisible Mixed Manna: On the Computability of MMS + PO Allocations

In this paper we initiate the study of finding fair and efficient allocations of an indivisible mixed manna: Divide m indivisible items among n agents under the fairness notion of maximin share (MMS) and the efficiency notion of Pareto optimality (PO). A mixed manna allows an item to be a good for some agents and a chore for others. The problem of finding $\alpha$-MMS allocation for the (near) best $\alpha\in(0,1]$ for which it exists, remains unresolved even for a goods manna with constantly many agents, while the problem of finding $\alpha$-MMS+PO allocation is unexplored for any $\alpha\in(0,1]$. We make significant progress on the above questions for a mixed manna. First, we show that for any $\alpha>0$, an $\alpha$-MMS allocation may not always exist, thus ruling out solving the problem for a fixed $\alpha$. Second, towards computing $\alpha$-MMS+PO allocation for the best possible $\alpha$, we obtain a dichotomous result: We derive two conditions and show that the problem is tractable under these two conditions, while dropping either renders the problem intractable. The two conditions are: (i) number of agents is a constant, and (ii) for every agent, her absolute value for all the items is at least a constant factor of her total (absolute) value for all the goods or all the chores. In particular, first, for instances satisfying (i) and (ii) we design a PTAS - an efficient algorithm to find an $(\alpha-\epsilon)$-MMS and $\gamma$-PO allocation when given $\epsilon,\gamma>0$, for the highest possible $\alpha\in(0,1]$. Second, we show that if either condition is not satisfied then finding an $\alpha$-MMS allocation for any $\alpha\in(0,1]$ is NP-hard, even when a solution exists for $\alpha=1$. To the best of our knowledge, ours is the first algorithm that ensures both approximate MMS and PO guarantees.

cs.GT↗

arXiv2019

Approximating Nash Social Welfare under Submodular Valuations through (Un)Matchings

We study the problem of approximating maximum Nash social welfare (NSW) when allocating m indivisible items among n asymmetric agents with submodular valuations. The NSW is a well-established notion of fairness and efficiency, defined as the weighted geometric mean of agents' valuations. For special cases of the problem with symmetric agents and additive(-like) valuation functions, approximation algorithms have been designed using approaches customized for these specific settings, and they fail to extend to more general settings. Hence, no approximation algorithm with factor independent of m is known either for asymmetric agents with additive valuations or for symmetric agents beyond additive(-like) valuations. In this paper, we extend our understanding of the NSW problem to far more general settings. Our main contribution is two approximation algorithms for asymmetric agents with additive and submodular valuations respectively. Both algorithms are simple to understand and involve non-trivial modifications of a greedy repeated matchings approach. Allocations of high valued items are done separately by un-matching certain items and re-matching them, by processes that are different in both algorithms. We show that these approaches achieve approximation factors of O(n) and O(n log n) for additive and submodular case respectively, which is independent of the number of items. For additive valuations, our algorithm outputs an allocation that also achieves the fairness property of envy-free up to one item (EF1). Furthermore, we show that the NSW problem under submodular valuations is strictly harder than all currently known settings with an e/(e-1) factor of the hardness of approximation, even for constantly many agents. For this case, we provide a different approximation algorithm that achieves a factor of e/(e-1), hence resolving it completely.

cs.GT↗

arXiv2019

Smoothed Efficient Algorithms and Reductions for Network Coordination Games

Worst-case hardness results for most equilibrium computation problems have raised the need for beyond-worst-case analysis. To this end, we study the smoothed complexity of finding pure Nash equilibria in Network Coordination Games, a PLS-complete problem in the worst case. This is a potential game where the sequential-better-response algorithm is known to converge to a pure NE, albeit in exponential time. First, we prove polynomial (resp. quasi-polynomial) smoothed complexity when the underlying game graph is a complete (resp. arbitrary) graph, and every player has constantly many strategies. We note that the complete graph case is reminiscent of perturbing all parameters, a common assumption in most known smoothed analysis results. Second, we define a notion of smoothness-preserving reduction among search problems, and obtain reductions from $2$-strategy network coordination games to local-max-cut, and from $k$-strategy games (with arbitrary $k$) to local-max-cut up to two flips. The former together with the recent result of [BCC18] gives an alternate $O(n^8)$-time smoothed algorithm for the $2$-strategy case. This notion of reduction allows for the extension of smoothed efficient algorithms from one problem to another. For the first set of results, we develop techniques to bound the probability that an (adversarial) better-response sequence makes slow improvements on the potential. Our approach combines and generalizes the local-max-cut approaches of [ER14,ABPW17] to handle the multi-strategy case: it requires a careful definition of the matrix which captures the increase in potential, a tighter union bound on adversarial sequences, and balancing it with good enough rank bounds. We believe that the approach and notions developed herein could be of interest in addressing the smoothed complexity of other potential and/or congestion games.

cs.CC↗