no code implementations • 3 May 2024 • Tanya Chowdhury, Yair Zick, James Allan
Next, we introduce Rank-SHAP, a feature attribution algorithm for the general ranking task, which is an extension to classical Shapley values.
2 code implementations • NeurIPS 2023 • Elita A. Lobo, Cyrus Cousins, Yair Zick, Marek Petrik
The percentile criterion is approximately solved by constructing an \emph{ambiguity set} that contains the true model with high probability and optimizing the policy for the worst model in the set.
no code implementations • 29 Sep 2023 • Gagan Biradar, Yacine Izza, Elita Lobo, Vignesh Viswanathan, Yair Zick
We also evaluate them on multiple datasets and show that these explanations are robust to the attacks that fool SHAP and LIME.
no code implementations • 25 Jul 2023 • Przemyslaw Grabowicz, Nicholas Perello, Yair Zick
This white paper is a response to the "AI Accountability Policy Request for Comments" by the National Telecommunications and Information Administration of the United States.
no code implementations • 27 Jun 2023 • Jenny Hamer, Jake Valladares, Vignesh Viswanathan, Yair Zick
We propose a novel data-driven framework for algorithmic recourse that offers users interventions to change their predicted outcome.
no code implementations • 10 Mar 2023 • Vignesh Viswanathan, Yair Zick
We study the problem of allocating indivisible chores among agents with binary supermodular cost functions.
no code implementations • 6 Feb 2023 • Cyrus Cousins, Vignesh Viswanathan, Yair Zick
This is surprising since for the simpler classes of bivalued additive valuations and binary submodular valuations, MNW allocations are known to be envy free up to any good (EFX).
no code implementations • 17 Jun 2022 • Vignesh Viswanathan, Yair Zick
We study fair allocation of indivisible goods when agents have matroid rank valuations.
1 code implementation • 8 Sep 2021 • Gagan Biradar, Vignesh Viswanathan, Yair Zick
Thus, our work is the first to formally bridge the gap between model explanations, game-theoretic influence, and causal analysis.
no code implementations • 29 Dec 2020 • Vignesh Viswanathan, Omer Lev, Neel Patel, Yair Zick
Equilibrium computation in markets usually considers settings where player valuation functions are known.
no code implementations • 16 Jun 2020 • Neel Patel, Martin Strobel, Yair Zick
We propose a new axiomatization for a generalization of the Banzhaf index; our method can also be thought of as an approximation of a black-box model by a higher-order polynomial.
no code implementations • 16 Jun 2020 • Neel Patel, Reza Shokri, Yair Zick
The drawback is that model explanations can leak information about the training data and the explanation data used to generate them, thus undermining data privacy.
no code implementations • 16 Mar 2020 • Nawal Benabbou, Mithun Chakraborty, Ayumi Igarashi, Yair Zick
In this paper, we present new results on the fair and efficient allocation of indivisible goods to agents whose preferences correspond to {\em matroid rank functions}.
no code implementations • 23 Sep 2019 • Mithun Chakraborty, Ayumi Igarashi, Warut Suksompong, Yair Zick
We introduce and analyze new envy-based fairness concepts for agents with weights that quantify their entitlements in the allocation of indivisible items.
no code implementations • 29 Jun 2019 • Reza Shokri, Martin Strobel, Yair Zick
We analyze connections between model explanations and the leakage of sensitive information about the model's training set.
no code implementations • 20 Mar 2019 • Tushant Jha, Yair Zick
The past few years have seen several works on learning economic solutions from data; these include optimal auction design, function optimization, stable payoffs in cooperative games and more.
1 code implementation • 3 Mar 2019 • Alan Tsang, Bryan Wilder, Eric Rice, Milind Tambe, Yair Zick
Influence maximization is a widely used model for information dissemination in social networks.
Computer Science and Game Theory Social and Information Networks
no code implementations • 28 Nov 2017 • Nawal Benabbou, Mithun Chakraborty, Vinh Ho Xuan, Jakub Sliwinski, Yair Zick
The two parts of the graph are partitioned into subsets called types and blocks; we seek a matching with the largest sum of weights under the constraint that there is a pre-specified cap on the number of vertices matched in every type-block pair.
no code implementations • 7 Aug 2017 • Jakub Sliwinski, Martin Strobel, Yair Zick
We study the following problem: given a labeled dataset and a specific datapoint x, how did the i-th feature influence the classification for x?
1 code implementation • 30 Apr 2015 • Maria-Florina Balcan, Ariel D. Procaccia, Yair Zick
This paper explores a PAC (probably approximately correct) learning model in cooperative games.
Computer Science and Game Theory