no code implementations • 28 Aug 2023 • Sahil Verma, Ashudeep Singh, Varich Boonsanong, John P. Dickerson, Chirag Shah
To the best of our knowledge, this work is the first to conceptualize and empirically test a generalized framework for generating recourses for recommender systems.
no code implementations • 10 Mar 2023 • Teresa Datta, John P. Dickerson
Deployed artificial intelligence (AI) often impacts humans, and there is no one-size-fits-all metric to evaluate these tools.
no code implementations • 14 Dec 2022 • Teresa Datta, Daniel Nissani, Max Cembalest, Akash Khanna, Haley Massa, John P. Dickerson
Motivated by mitigating potentially harmful impacts of technologies, the AI community has formulated and accepted mathematical definitions for certain pillars of accountability: e. g. privacy, fairness, and model transparency.
1 code implementation • 9 Dec 2022 • Christine Herlihy, John P. Dickerson
Restless multi-armed bandits are often used to model budget-constrained resource allocation tasks where receipt of the resource is associated with an increased probability of a favorable state transition.
2 code implementations • 29 Nov 2022 • Samuel Dooley, George Z. Wei, Tom Goldstein, John P. Dickerson
Many existing algorithmic audits examine the performance of these systems on later stage elements of facial analysis systems like facial recognition and age, emotion, or perceived gender prediction; however, a core component to these systems has been vastly understudied from a fairness perspective: face detection, sometimes called face localization.
no code implementations • 27 Nov 2022 • Sahil Verma, Chirag Shah, John P. Dickerson, Anurag Beniwal, Narayanan Sadagopan, Arjun Seshadri
We evaluate RecXplainer on five real-world and large-scale recommendation datasets using five different kinds of recommender systems to demonstrate the efficacy of RecXplainer in capturing users' preferences over item attributes and using them to explain recommendations.
no code implementations • 9 Nov 2022 • Vishnu Dutt Sharma, John P. Dickerson, Pratap Tokekar
Green Security Games with real-time information (GSG-I) add the real-time information about the agents' movement to the typical GSG formulation.
2 code implementations • NeurIPS 2023 • Samuel Dooley, Rhea Sanjay Sukthanker, John P. Dickerson, Colin White, Frank Hutter, Micah Goldblum
Our search outputs a suite of models which Pareto-dominate all other high-performance architectures and existing bias mitigation methods in terms of accuracy and fairness, often by large margins, on the two most widely used datasets for face identification, CelebA and VGGFace2.
no code implementations • 5 Oct 2022 • I. Elizabeth Kumar, Keegan E. Hines, John P. Dickerson
Credit is an essential component of financial wellbeing in America, and unequal access to it is a large factor in the economic disparities between demographic groups that exist today.
1 code implementation • 23 Jun 2022 • Vedant Nanda, Till Speicher, Camila Kolling, John P. Dickerson, Krishna P. Gummadi, Adrian Weller
Our work offers a new view on robustness by using another reference NN to define the set of perturbations a given NN should be invariant to, thus generalizing the reliance on a reference ``human NN'' to any NN.
1 code implementation • 23 Jun 2022 • Duncan McElfresh, Sujay Khandagale, Jonathan Valverde, John P. Dickerson, Colin White
By using far more meta-training data than prior work, RecZilla is able to substantially reduce the level of human involvement when faced with a new recommender system application.
no code implementations • 28 May 2022 • Seyed A. Esmaeili, Sharmila Duppala, John P. Dickerson, Brian Brubach
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.
no code implementations • 27 May 2022 • Marina Knittel, Max Springer, John P. Dickerson, Mohammadtaghi Hajiaghayi
We evaluate our results using Dasgupta's cost function, perhaps one of the most prevalent theoretical metrics for hierarchical clustering evaluation.
no code implementations • 14 May 2022 • Ryan Sullivan, J. K. Terry, Benjamin Black, John P. Dickerson
Visualizing optimization landscapes has led to many fundamental insights in numeric optimization, and novel improvements to optimization techniques.
no code implementations • 22 Feb 2022 • Marina Knittel, Samuel Dooley, John P. Dickerson
We also assume the agent's preferences over entire matchings are determined by a general weighted valuation function of their (and their affiliates') matches.
no code implementations • 25 Jan 2022 • Samuel Dooley, George Z. Wei, Tom Goldstein, John P. Dickerson
When we compare the size of these disparities to that of commercial models, we conclude that commercial models - in contrast to their relatively larger development budget and industry-level fairness commitments - are always as biased or more biased than an academic model.
no code implementations • 16 Jan 2022 • Seyed A. Esmaeili, Sharmila Duppala, Davidson Cheng, Vedant Nanda, Aravind Srinivasan, John P. Dickerson
Since fairness has become an important consideration that was ignored in the existing algorithms a collection of online matching algorithms have been developed that give a fair treatment guarantee for one side of the market at the expense of a drop in the operator's profit.
1 code implementation • 29 Nov 2021 • Vedant Nanda, Ayan Majumdar, Camila Kolling, John P. Dickerson, Krishna P. Gummadi, Bradley C. Love, Adrian Weller
One necessary criterion for a network's invariances to align with human perception is for its IRIs look 'similar' to humans.
1 code implementation • 27 Aug 2021 • Samuel Dooley, Tom Goldstein, John P. Dickerson
Facial detection and analysis systems have been deployed by large companies and critiqued by scholars and activists for the past decade.
1 code implementation • 14 Jun 2021 • Christine Herlihy, Aviva Prins, Aravind Srinivasan, John P. Dickerson
Restless and collapsing bandits are often used to model budget-constrained resource allocation in settings where arms have action-dependent transition probabilities, such as the allocation of health interventions among patients.
no code implementations • NeurIPS 2021 • Seyed A. Esmaeili, Brian Brubach, Aravind Srinivasan, John P. Dickerson
We derive fundamental lower bounds on the approximation of the utilitarian and egalitarian objectives and introduce algorithms with provable guarantees for them.
no code implementations • 14 Jun 2021 • Sahil Verma, Aditya Lahiri, John P. Dickerson, Su-In Lee
The goal of explainable ML is to intuitively explain the predictions of a ML system, while adhering to the needs to various stakeholders.
1 code implementation • 9 Jun 2021 • Darshan Chakrabarti, John P. Dickerson, Seyed A. Esmaeili, Aravind Srinivasan, Leonidas Tsepenekas
Clustering is a fundamental problem in unsupervised machine learning, and fair variants of it have recently received significant attention due to its societal implications.
1 code implementation • 7 Jun 2021 • Sahil Verma, Keegan Hines, John P. Dickerson
We propose a novel stochastic-control-based approach that generates sequential ARs, that is, ARs that allow x to move stochastically and sequentially across intermediate states to a final state x'.
1 code implementation • NeurIPS 2021 • Neehar Peri, Michael J. Curry, Samuel Dooley, John P. Dickerson
In addition, we introduce a new metric to evaluate an auction allocations' adherence to such socially desirable constraints and demonstrate that our proposed method is competitive with current state-of-the-art neural-network based auction designs.
1 code implementation • 2 Mar 2021 • Brian Brubach, Darshan Chakrabarti, John P. Dickerson, Aravind Srinivasan, Leonidas Tsepenekas
Metric clustering is fundamental in areas ranging from Combinatorial Optimization and Data Mining, to Machine Learning and Operations Research.
1 code implementation • 24 Feb 2021 • Stephanie Allen, John P. Dickerson, Steven A. Gabriel
As demonstrated by Ratliff et al. (2014), inverse optimization can be used to recover the objective function parameters of players in multi-player Nash games.
no code implementations • 12 Feb 2021 • Valeriia Cherepanova, Vedant Nanda, Micah Goldblum, John P. Dickerson, Tom Goldstein
As machine learning algorithms have been widely deployed across applications, many concerns have been raised over the fairness of their predictions, especially in high stakes settings (such as facial recognition and medical imaging).
no code implementations • NeurIPS 2021 • Jingling Li, Mozhi Zhang, Keyulu Xu, John P. Dickerson, Jimmy Ba
Our framework measures a network's robustness via the predictive power in its representations -- the test performance of a linear model trained on the learned representations using a small set of clean labels.
no code implementations • 20 Oct 2020 • Sahil Verma, Varich Boonsanong, Minh Hoang, Keegan E. Hines, John P. Dickerson, Chirag Shah
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders.
no code implementations • 13 Oct 2020 • Kevin Kuo, Anthony Ostuni, Elizabeth Horishny, Michael J. Curry, Samuel Dooley, Ping-Yeh Chiang, Tom Goldstein, John P. Dickerson
Inspired by these advances, in this paper, we extend techniques for approximating auctions using deep learning to address concerns of fairness while maintaining high revenue and strong incentive guarantees.
no code implementations • 24 Sep 2020 • Samuel Dooley, John P. Dickerson
We model this affiliate matching problem in a generalization of the classic stable marriage setting by permitting firms to state preferences over not just which workers to whom they are matched, but also to which firms their affiliated workers are matched.
no code implementations • ICML 2020 • Brian Brubach, Darshan Chakrabarti, John P. Dickerson, Samir Khuller, Aravind Srinivasan, Leonidas Tsepenekas
Clustering is a foundational problem in machine learning with numerous applications.
no code implementations • 7 Jul 2020 • Hoda Bidkhori, John P. Dickerson, Duncan C. McElfresh, Ke Ren
To the best of our knowledge, the state-of-the-art approaches are only tractable when failure probabilities are identical.
no code implementations • 1 Jul 2020 • Vedant Nanda, Till Speicher, John P. Dickerson, Krishna P. Gummadi, Muhammad Bilal Zafar
Our framework defines a large number of concepts that the DNN explanations could be based on and performs the explanation-conformity check at test time to assess prediction robustness.
2 code implementations • 22 Jun 2020 • Avi Schwarzschild, Micah Goldblum, Arjun Gupta, John P. Dickerson, Tom Goldstein
Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference.
no code implementations • NeurIPS 2020 • Seyed A. Esmaeili, Brian Brubach, Leonidas Tsepenekas, John P. Dickerson
In fair clustering problems, vertices are endowed with a color (e. g., membership in a group), and the features of a valid clustering might also include the representation of colors in that clustering.
1 code implementation • 17 Jun 2020 • Vedant Nanda, Samuel Dooley, Sahil Singla, Soheil Feizi, John P. Dickerson
In this paper, we argue that traditional notions of fairness that are only based on models' outputs are not sufficient when the model is vulnerable to adversarial attacks.
1 code implementation • 19 May 2020 • Rachel Freedman, Jana Schaich Borg, Walter Sinnott-Armstrong, John P. Dickerson, Vincent Conitzer
In kidney exchanges, a central market maker allocates living kidney donors to patients in need of an organ.
1 code implementation • 18 Dec 2019 • Vedant Nanda, Pan Xu, Karthik Abinav Sankararaman, John P. Dickerson, Aravind Srinivasan
Moreover, if in such a scenario, the assignment of requests to drivers (by the platform) is made only to maximize profit and/or minimize wait time for riders, requests of a certain type (e. g. from a non-popular pickup location, or to a non-popular drop-off location) might never be assigned to a driver.
2 code implementations • ICML 2020 • Debjani Saha, Candice Schumann, Duncan C. McElfresh, John P. Dickerson, Michelle L. Mazurek, Michael Carl Tschantz
Bias in machine learning has manifested injustice in several areas, such as medicine, hiring, and criminal justice.
1 code implementation • 9 Dec 2019 • Candice Schumann, Zhi Lang, Nicholas Mattei, John P. Dickerson
We propose a novel formulation of group fairness with biased feedback in the contextual multi-armed bandit (CMAB) setting.
no code implementations • 30 Nov 2019 • Michael J. Curry, John P. Dickerson, Karthik Abinav Sankararaman, Aravind Srinivasan, Yuhao Wan, Pan Xu
Rideshare platforms such as Uber and Lyft dynamically dispatch drivers to match riders' requests.
1 code implementation • 29 Sep 2019 • Neehar Peri, Neal Gupta, W. Ronny Huang, Liam Fowl, Chen Zhu, Soheil Feizi, Tom Goldstein, John P. Dickerson
Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a particular test sample during inference.
no code implementations • 7 Sep 2019 • Saba Ahmadi, Faez Ahmed, John P. Dickerson, Mark Fuge, Samir Khuller
Bipartite b-matching, where agents on one side of a market are matched to one or more agents or items on the other, is a classical model that is used in myriad application areas such as healthcare, advertising, education, and general resource allocation.
1 code implementation • NeurIPS 2019 • Candice Schumann, Zhi Lang, Jeffrey S. Foster, John P. Dickerson
Given a huge set of applicants, how should a firm allocate sequential resume screenings, phone interviews, and in-person site visits?
1 code implementation • 8 Nov 2018 • Duncan C. McElfresh, Hoda Bidkhori, John P. Dickerson
Transactions in barter exchanges are often facilitated via a central clearinghouse that must match participants even in the face of uncertainty---over participants, existence and quality of potential trades, and so on.
no code implementations • 22 Nov 2017 • John P. Dickerson, Karthik A. Sankararaman, Aravind Srinivasan, Pan Xu
Prior work addresses online bipartite matching markets, where agents arrive over time and are dynamically matched to a known set of disposable resources.
1 code implementation • 11 Sep 2017 • Candice Schumann, Samsara N. Counts, Jeffrey S. Foster, John P. Dickerson
We apply our general algorithm to a real-world problem with combinatorial structure: incorporating diversity into university admissions.
no code implementations • 19 Jun 2017 • Hanan Rosemarin, John P. Dickerson, Sarit Kraus
The use of semi-autonomous and autonomous robotic assistants to aid in care of the elderly is expected to ease the burden on human caretakers, with small-stage testing already occurring in a variety of countries.
no code implementations • 25 May 2017 • Gabriele Farina, John P. Dickerson, Tuomas Sandholm
A kidney exchange is a centrally-administered barter market where patients swap their willing yet incompatible donors.
no code implementations • 27 Feb 2017 • Duncan C. McElfresh, John P. Dickerson
Balancing fairness and efficiency in resource allocation is a classical economic and computational problem.
1 code implementation • 23 Feb 2017 • Faez Ahmed, John P. Dickerson, Mark Fuge
Bipartite matching, where agents on one side of a market are matched to agents or items on the other, is a classical problem in computer science and economics, with widespread application in healthcare, education, advertising, and general resource allocation.
no code implementations • 6 Jun 2016 • John P. Dickerson, David F. Manlove, Benjamin Plaut, Tuomas Sandholm, James Trimble
The recent introduction of chains, where a donor without a paired patient triggers a sequence of donations without requiring a kidney in return, increased the efficacy of fielded kidney exchanges---while also dramatically raising the empirical computational hardness of clearing the market in practice.
no code implementations • 1 Jun 2016 • Benjamin Plaut, John P. Dickerson, Tuomas Sandholm
One of the leading techniques has been branch and price, where column generation is used to incrementally bring cycles and chains into the optimization model on an as-needed basis.
no code implementations • 25 May 2016 • John P. Dickerson, Aleksandr M. Kazachkov, Ariel D. Procaccia, Tuomas Sandholm
This growth results in more lives saved, but exacerbates the empirical hardness of the $\mathcal{NP}$-complete problem of optimally matching patients to donors.