arXiv subjects

Dimitris Fotakis

Publications and source records attributed to Dimitris Fotakis.

At least 37 records · Page 2Linked to original sources

arXiv2024

Strategyproof Facility Location in Perturbation Stable Instances

We consider $k$-Facility Location games, where $n$ strategic agents report their locations on the real line, and a mechanism maps them to $k\ge 2$ facilities. Each agent seeks to minimize her distance to the nearest facility. We are interested in (deterministic or randomized) strategyproof mechanisms without payments that achieve a reasonable approximation ratio to the optimal social cost of the agents. To circumvent the inapproximability of $k$-Facility Location by deterministic strategyproof mechanisms, we restrict our attention to perturbation stable instances. An instance of $k$-Facility Location on the line is $γ$-perturbation stable (or simply, $γ$-stable), for some $γ\ge 1$, if the optimal agent clustering is not affected by moving any subset of consecutive agent locations closer to each other by a factor at most $γ$. We show that the optimal solution is strategyproof in $(2+\sqrt{3})$-stable instances whose optimal solution does not include any singleton clusters, and that allocating the facility to the agent next to the rightmost one in each optimal cluster (or to the unique agent, for singleton clusters) is strategyproof and $(n-2)/2$-approximate for $5$-stable instances (even if their optimal solution includes singleton clusters). On the negative side, we show that for any $k\ge 3$ and any $δ> 0$, there is no deterministic anonymous mechanism that achieves a bounded approximation ratio and is strategyproof in $(\sqrt{2}-δ)$-stable instances. We also prove that allocating the facility to a random agent of each optimal cluster is strategyproof and $2$-approximate in $5$-stable instances. To the best of our knowledge, this is the first time that the existence of deterministic (resp. randomized) strategyproof mechanisms with a bounded (resp. constant) approximation ratio is shown for a large and natural class of $k$-Facility Location instances.

cs.GT↗

arXiv2023

Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods

Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems. In those methods a deep neural network is used as a solution generator which is then trained by gradient-based methods (e.g., policy gradient) to successively obtain better solution distributions. In this work we introduce a novel theoretical framework for analyzing the effectiveness of such methods. We ask whether there exist generative models that (i) are expressive enough to generate approximately optimal solutions; (ii) have a tractable, i.e, polynomial in the size of the input, number of parameters; (iii) their optimization landscape is benign in the sense that it does not contain sub-optimal stationary points. Our main contribution is a positive answer to this question. Our result holds for a broad class of combinatorial problems including Max- and Min-Cut, Max-$k$-CSP, Maximum-Weight-Bipartite-Matching, and the Traveling Salesman Problem. As a byproduct of our analysis we introduce a novel regularization process over vanilla gradient descent and provide theoretical and experimental evidence that it helps address vanishing-gradient issues and escape bad stationary points.

cs.LG↗

arXiv2023

Fairness Aware Counterfactuals for Subgroups

In this work, we present Fairness Aware Counterfactuals for Subgroups (FACTS), a framework for auditing subgroup fairness through counterfactual explanations. We start with revisiting (and generalizing) existing notions and introducing new, more refined notions of subgroup fairness. We aim to (a) formulate different aspects of the difficulty of individuals in certain subgroups to achieve recourse, i.e. receive the desired outcome, either at the micro level, considering members of the subgroup individually, or at the macro level, considering the subgroup as a whole, and (b) introduce notions of subgroup fairness that are robust, if not totally oblivious, to the cost of achieving recourse. We accompany these notions with an efficient, model-agnostic, highly parameterizable, and explainable framework for evaluating subgroup fairness. We demonstrate the advantages, the wide applicability, and the efficiency of our approach through a thorough experimental evaluation of different benchmark datasets.

cs.LG↗

arXiv2023

Efficient Algorithms for Learning from Coarse Labels

For many learning problems one may not have access to fine grained label information; e.g., an image can be labeled as husky, dog, or even animal depending on the expertise of the annotator. In this work, we formalize these settings and study the problem of learning from such coarse data. Instead of observing the actual labels from a set $\mathcal{Z}$, we observe coarse labels corresponding to a partition of $\mathcal{Z}$ (or a mixture of partitions). Our main algorithmic result is that essentially any problem learnable from fine grained labels can also be learned efficiently when the coarse data are sufficiently informative. We obtain our result through a generic reduction for answering Statistical Queries (SQ) over fine grained labels given only coarse labels. The number of coarse labels required depends polynomially on the information distortion due to coarsening and the number of fine labels $|\mathcal{Z}|$. We also investigate the case of (infinitely many) real valued labels focusing on a central problem in censored and truncated statistics: Gaussian mean estimation from coarse data. We provide an efficient algorithm when the sets in the partition are convex and establish that the problem is NP-hard even for very simple non-convex sets.

cs.LG↗

arXiv2023

Perfect Sampling from Pairwise Comparisons

In this work, we study how to efficiently obtain perfect samples from a discrete distribution $\mathcal{D}$ given access only to pairwise comparisons of elements of its support. Specifically, we assume access to samples $(x, S)$, where $S$ is drawn from a distribution over sets $\mathcal{Q}$ (indicating the elements being compared), and $x$ is drawn from the conditional distribution $\mathcal{D}_S$ (indicating the winner of the comparison) and aim to output a clean sample $y$ distributed according to $\mathcal{D}$. We mainly focus on the case of pairwise comparisons where all sets $S$ have size 2. We design a Markov chain whose stationary distribution coincides with $\mathcal{D}$ and give an algorithm to obtain exact samples using the technique of Coupling from the Past. However, the sample complexity of this algorithm depends on the structure of the distribution $\mathcal{D}$ and can be even exponential in the support of $\mathcal{D}$ in many natural scenarios. Our main contribution is to provide an efficient exact sampling algorithm whose complexity does not depend on the structure of $\mathcal{D}$. To this end, we give a parametric Markov chain that mixes significantly faster given a good approximation to the stationary distribution. We can obtain such an approximation using an efficient learning from pairwise comparisons algorithm (Shah et al., JMLR 17, 2016). Our technique for speeding up sampling from a Markov chain whose stationary distribution is approximately known is simple, general and possibly of independent interest.

cs.LG↗

arXiv2022

Graph Connectivity with Noisy Queries

Graph connectivity is a fundamental combinatorial optimization problem that arises in many practical applications, where usually a spanning subgraph of a network is used for its operation. However, in the real world, links may fail unexpectedly deeming the networks non-operational, while checking whether a link is damaged is costly and possibly erroneous. After an event that has damaged an arbitrary subset of the edges, the network operator must find a spanning tree of the network using non-damaged edges by making as few checks as possible. Motivated by such questions, we study the problem of finding a spanning tree in a network, when we only have access to noisy queries of the form "Does edge e exist?". We design efficient algorithms, even when edges fail adversarially, for all possible error regimes; 2-sided error (where any answer might be erroneous), false positives (where "no" answers are always correct) and false negatives (where "yes" answers are always correct). In the first two regimes we provide efficient algorithms and give matching lower bounds for general graphs. In the False Negative case we design efficient algorithms for large interesting families of graphs (e.g. bounded treewidth, sparse). Using the previous results, we provide tight algorithms for the practically useful family of planar graphs in all error regimes.

cs.DS↗

arXiv2022

Sampling and Optimal Preference Elicitation in Simple Mechanisms

In this work we are concerned with the design of efficient mechanisms while eliciting limited information from the agents. First, we study the performance of sampling approximations in facility location games. Our key result is to show that for any $ε> 0$, a sample of size $c(ε) = Θ(1/ε^2)$ yields in expectation a $1 + ε$ approximation with respect to the optimal social cost of the generalized median mechanism on the metric space $(\mathbb{R}^d, \| \cdot \|_1)$, while the number of agents $n \to \infty$. Moreover, we study a series of exemplar environments from auction theory through a communication complexity framework, measuring the expected number of bits elicited from the agents; we posit that any valuation can be expressed with $k$ bits, and we mainly assume that $k$ is independent of the number of agents $n$. In this context, we show that Vickrey's rule can be implemented with an expected communication of $1 + ε$ bits from an average bidder, for any $ε> 0$, asymptotically matching the trivial lower bound. As a corollary, we provide a compelling method to increment the price in an English auction. We also leverage our single-item format with an efficient encoding scheme to prove that the same communication bound can be recovered in the domain of additive valuations through simultaneous ascending auctions, assuming that the number of items is a constant. Finally, we propose an ascending-type multi-unit auction under unit demand bidders; our mechanism announces at every round two separate prices and is based on a sampling algorithm that performs approximate selection with limited communication, leading again to asymptotically optimal communication. Our results do not require any prior knowledge on the agents' valuations, and mainly follow from natural sampling techniques.

cs.GT↗

arXiv2022

Detecting and analysing the topology of the cosmic web with spatial clustering algorithms I: Methods

In this paper we explore the use of spatial clustering algorithms as a new computational approach for modeling the cosmic web. We demonstrate that such algorithms are efficient in terms of computing time needed. We explore three distinct spatial methods which we suitably adjust for (i) detecting the topology of the cosmic web and (ii) categorizing various cosmic structures as voids, walls, clusters and superclusters based on a variety of topological and physical criteria such as the physical distance between objects, their masses and local densities. The methods explored are (1) a new spatial method called Gravity Lattice ; (2) a modified version of another spatial clustering algorithm, the ABACUS; and (3) the well known spatial clustering algorithm HDBSCAN. We utilize HDBSCAN in order to detect cosmic structures and categorize them using their overdensity. We demonstrate that the ABACUS method can be combined with the classic DTFE method to obtain similar results in terms of the achieved accuracy with about an order of magnitude less computation time. To further solidify our claims, we draw insights from the computer science domain and compare the quality of the results with and without the application of our method. Finally, we further extend our experiments and verify their effectiveness by showing their ability to scale well with different cosmic web structures that formed at different redshifts.

astro-ph.IM↗

arXiv2022

The Online Min-Sum Set Cover Problem

We consider the online Min-Sum Set Cover (MSSC), a natural and intriguing generalization of the classical list update problem. In Online MSSC, the algorithm maintains a permutation on $n$ elements based on subsets $S_1, S_2, \ldots$ arriving online. The algorithm serves each set $S_t$ upon arrival, using its current permutation $π_{t}$, incurring an access cost equal to the position of the first element of $S_t$ in $π_{t}$. Then, the algorithm may update its permutation to $π_{t+1}$, incurring a moving cost equal to the Kendall tau distance of $π_{t}$ to $π_{t+1}$. The objective is to minimize the total access and moving cost for serving the entire sequence. We consider the $r$-uniform version, where each $S_t$ has cardinality $r$. List update is the special case where $r = 1$. We obtain tight bounds on the competitive ratio of deterministic online algorithms for MSSC against a static adversary, that serves the entire sequence by a single permutation. First, we show a lower bound of $(r+1)(1-\frac{r}{n+1})$ on the competitive ratio. Then, we consider several natural generalizations of successful list update algorithms and show that they fail to achieve any interesting competitive guarantee. On the positive side, we obtain a $O(r)$-competitive deterministic algorithm using ideas from online learning and the multiplicative weight updates (MWU) algorithm. Furthermore, we consider efficient algorithms. We propose a memoryless online algorithm, called Move-All-Equally, which is inspired by the Double Coverage algorithm for the $k$-server problem. We show that its competitive ratio is $Ω(r^2)$ and $2^{O(\sqrt{\log n \cdot \log r})}$, and conjecture that it is $f(r)$-competitive. We also compare Move-All-Equally against the dynamic optimal solution and obtain (almost) tight bounds by showing that it is $Ω(r \sqrt{n})$ and $O(r^{3/2} \sqrt{n})$-competitive.

cs.DS↗

arXiv2022

Assigning and Scheduling Generalized Malleable Jobs under Subadditive or Submodular Processing Speeds

Malleable scheduling is a model that captures the possibility of parallelization to expedite the completion of time-critical tasks. A malleable job can be allocated and processed simultaneously on multiple machines, occupying the same time interval on all these machines. We study a general version of this setting, in which the functions determining the joint processing speed of machines for a given job follow different discrete concavity assumptions (subadditivity, fractional subadditivity, submodularity, and matroid ranks). We show that under these assumptions the problem of scheduling malleable jobs at minimum makespan can be approximated by a considerably simpler assignment problem. Moreover, we provide efficient approximation algorithms for both the scheduling and the assignment problem, with increasingly stronger guarantees for increasingly stronger concavity assumptions, including a logarithmic approximation factor for the case of submodular processing speeds and a constant approximation factor when processing speeds are determined by matroid rank functions. Computational experiments indicate that our algorithms outperform the theoretical worst-case guarantees.

cs.DM↗

arXiv2022

Dimensionality, Coordination, and Robustness in Voting

We study the performance of voting mechanisms from a utilitarian standpoint, under the recently introduced framework of metric-distortion, offering new insights along three main lines. First, if $d$ represents the doubling dimension of the metric space, we show that the distortion of STV is $O(d \log \log m)$, where $m$ represents the number of candidates. For doubling metrics this implies an exponential improvement over the lower bound for general metrics, and as a special case it effectively answers a question left open by Skowron and Elkind (AAAI '17) regarding the distortion of STV under low-dimensional Euclidean spaces. More broadly, this constitutes the first nexus between the performance of any voting rule and the "intrinsic dimensionality" of the underlying metric space. We also establish a nearly-matching lower bound, refining the construction of Skowron and Elkind. Moreover, motivated by the efficiency of STV, we investigate whether natural learning rules can lead to low-distortion outcomes. Specifically, we introduce simple, deterministic and decentralized exploration/exploitation dynamics, and we show that they converge to a candidate with $O(1)$ distortion. Finally, driven by applications in facility location games, we consider several refinements and extensions of the standard metric-setting. Namely, we prove that the deterministic mechanism recently introduced by Gkatzelis, Halpern, and Shah (FOCS '20) attains the optimal distortion bound of $2$ under ultra-metrics, while it also comes close to our lower bound under distances satisfying approximate triangle inequalities.

cs.GT↗

arXiv2022

Differentially Private Regression with Unbounded Covariates

We provide computationally efficient, differentially private algorithms for the classical regression settings of Least Squares Fitting, Binary Regression and Linear Regression with unbounded covariates. Prior to our work, privacy constraints in such regression settings were studied under strong a priori bounds on covariates. We consider the case of Gaussian marginals and extend recent differentially private techniques on mean and covariance estimation (Kamath et al., 2019; Karwa and Vadhan, 2018) to the sub-gaussian regime. We provide a novel technical analysis yielding differentially private algorithms for the above classical regression settings. Through the case of Binary Regression, we capture the fundamental and widely-studied models of logistic regression and linearly-separable SVMs, learning an unbiased estimate of the true regression vector, up to a scaling factor.

cs.CR↗

arXiv2022

Label Ranking through Nonparametric Regression

Label Ranking (LR) corresponds to the problem of learning a hypothesis that maps features to rankings over a finite set of labels. We adopt a nonparametric regression approach to LR and obtain theoretical performance guarantees for this fundamental practical problem. We introduce a generative model for Label Ranking, in noiseless and noisy nonparametric regression settings, and provide sample complexity bounds for learning algorithms in both cases. In the noiseless setting, we study the LR problem with full rankings and provide computationally efficient algorithms using decision trees and random forests in the high-dimensional regime. In the noisy setting, we consider the more general cases of LR with incomplete and partial rankings from a statistical viewpoint and obtain sample complexity bounds using the One-Versus-One approach of multiclass classification. Finally, we complement our theoretical contributions with experiments, aiming to understand how the input regression noise affects the observed output.

cs.LG↗

arXiv2021

A Constant-Factor Approximation for Generalized Malleable Scheduling under $M^\natural$-Concave Processing Speeds

In generalized malleable scheduling, jobs can be allocated and processed simultaneously on multiple machines so as to reduce the overall makespan of the schedule. The required processing time for each job is determined by the joint processing speed of the allocated machines. We study the case that processing speeds are job-dependent $M^\natural$-concave functions and provide a constant-factor approximation for this setting, significantly expanding the realm of functions for which such an approximation is possible. Further, we explore the connection between malleable scheduling and the problem of fairly allocating items to a set of agents with distinct utility functions, devising a black-box reduction that allows to obtain resource-augmented approximation algorithms for the latter.

cs.DM↗

arXiv2021

Sampling Multiple Nodes in Large Networks: Beyond Random Walks

Sampling random nodes is a fundamental algorithmic primitive in the analysis of massive networks, with many modern graph mining algorithms critically relying on it. We consider the task of generating a large collection of random nodes in the network assuming limited query access (where querying a node reveals its set of neighbors). In current approaches, based on long random walks, the number of queries per sample scales linearly with the mixing time of the network, which can be prohibitive for large real-world networks. We propose a new method for sampling multiple nodes that bypasses the dependence in the mixing time by explicitly searching for less accessible components in the network. We test our approach on a variety of real-world and synthetic networks with up to tens of millions of nodes, demonstrating a query complexity improvement of up to $\times 20$ compared to the state of the art.

cs.SI↗

arXiv2021

On the Approximability of Multistage Min-Sum Set Cover

We investigate the polynomial-time approximability of the multistage version of Min-Sum Set Cover ($\mathrm{DSSC}$), a natural and intriguing generalization of the classical List Update problem. In $\mathrm{DSSC}$, we maintain a sequence of permutations $(π^0, π^1, \ldots, π^T)$ on $n$ elements, based on a sequence of requests $(R^1, \ldots, R^T)$. We aim to minimize the total cost of updating $π^{t-1}$ to $π^{t}$, quantified by the Kendall tau distance $\mathrm{D}_{\mathrm{KT}}(π^{t-1}, π^t)$, plus the total cost of covering each request $R^t$ with the current permutation $π^t$, quantified by the position of the first element of $R^t$ in $π^t$. Using a reduction from Set Cover, we show that $\mathrm{DSSC}$ does not admit an $O(1)$-approximation, unless $\mathrm{P} = \mathrm{NP}$, and that any $o(\log n)$ (resp. $o(r)$) approximation to $\mathrm{DSSC}$ implies a sublogarithmic (resp. $o(r)$) approximation to Set Cover (resp. where each element appears at most $r$ times). Our main technical contribution is to show that $\mathrm{DSSC}$ can be approximated in polynomial-time within a factor of $O(\log^2 n)$ in general instances, by randomized rounding, and within a factor of $O(r^2)$, if all requests have cardinality at most $r$, by deterministic rounding.

cs.DS↗

arXiv2021

Stochastic Opinion Dynamics for Interest Prediction in Social Networks

We exploit the core-periphery structure and the strong homophilic properties of online social networks to develop faster and more accurate algorithms for user interest prediction. The core of modern social networks consists of relatively few influential users, whose interest profiles are publicly available, while the majority of peripheral users follow enough of them based on common interests. Our approach is to predict the interests of the peripheral nodes starting from the interests of their influential connections. To this end, we need a formal model that explains how common interests lead to network connections. Thus, we propose a stochastic interest formation model, the Nearest Neighbor Influence Model (NNIM), which is inspired by the Hegselmann-Krause opinion formation model and aims to explain how homophily shapes the network. Based on NNIM, we develop an efficient approach for predicting the interests of the peripheral users. At the technical level, we use Variational Expectation-Maximization to optimize the instantaneous likelihood function using a mean-field approximation of NNIM. We prove that our algorithm converges fast and is capable of scaling smoothly to networks with millions of nodes. Our experiments on standard network benchmarks demonstrate that our algorithm runs up to two orders of magnitude faster than the best known node embedding methods and achieves similar accuracy.

cs.SI↗

arXiv2021

Metric-Distortion Bounds under Limited Information

In this work we study the metric distortion problem in voting theory under a limited amount of ordinal information. Our primary contribution is threefold. First, we consider mechanisms which perform a sequence of pairwise comparisons between candidates. We show that a widely-popular deterministic mechanism employed in most knockout phases yields distortion $\mathcal{O}(\log m)$ while eliciting only $m-1$ out of $Θ(m^2)$ possible pairwise comparisons, where $m$ represents the number of candidates. Our analysis for this mechanism leverages a powerful technical lemma recently developed by Kempe \cite{DBLP:conf/aaai/000120a}. We also provide a matching lower bound on its distortion. In contrast, we prove that any mechanism which performs fewer than $m-1$ pairwise comparisons is destined to have unbounded distortion. Moreover, we study the power of deterministic mechanisms under incomplete rankings. Most notably, when every agent provides her $k$-top preferences we show an upper bound of $6 m/k + 1$ on the distortion, for any $k \in \{1, 2, \dots, m\}$. Thus, we substantially improve over the previous bound of $12 m/k$ recently established by Kempe \cite{DBLP:conf/aaai/000120a,DBLP:conf/aaai/000120b}, and we come closer to matching the best-known lower bound. Finally, we are concerned with the sample complexity required to ensure near-optimal distortion with high probability. Our main contribution is to show that a random sample of $Θ(m/ε^2)$ voters suffices to guarantee distortion $3 + ε$ with high probability, for any sufficiently small $ε> 0$. This result is based on analyzing the sensitivity of the deterministic mechanism introduced by Gkatzelis, Halpern, and Shah \cite{DBLP:conf/focs/Gkatzelis0020}. Importantly, all of our sample-complexity bounds are distribution-independent.

cs.GT↗