Search Results for author:
Found 31 papers, 16 papers with code
Fair Classification with Partial Feedback: An Exploration-Based Data-Collection Approach
For any exploration strategy, the approach comes with guarantees that (1) all sub-populations are explored, (2) the fraction of false positives is bounded, and (3) the trained classifier converges to a "desired" classifier.
Bias in Evaluation Processes: An Optimization-Based Model
We characterize the distributions that arise from our model and study the effect of the parameters on the observed distribution.
Subset Selection Based On Multiple Rankings in the Presence of Bias: Effectiveness of Fairness Constraints for Multiwinner Voting Score Functions
We consider the problem of subset selection where one is given multiple rankings of items and the goal is to select the highest ``quality'' subset.
Designing Closed-Loop Models for Task Allocation
Instead, we find ourselves in a "closed" decision-making loop in which the same fallible human decisions we rely on in practice must also be used to guide task allocation.
Addressing Strategic Manipulation Disparities in Fair Classification
In real-world classification settings, such as loan application evaluation or content moderation on online platforms, individuals respond to classifier predictions by strategically updating their features to increase their likelihood of receiving a particular (positive) decision (at a certain cost).
Auditing for Diversity using Representative Examples
Our proposed algorithm uses the pairwise similarity between elements in the dataset and elements in the control set to effectively bootstrap an approximation to the disparity of the dataset.
Fair Classification with Adversarial Perturbations
Our main contribution is an optimization framework to learn fair classifiers in this adversarial setting that comes with provable guarantees on accuracy and fairness.
Mitigating Bias in Set Selection with Noisy Protected Attributes
Subset selection algorithms are ubiquitous in AI-driven applications, including, online recruiting portals and image search engines, so it is imperative that these tools are not discriminatory on the basis of protected attributes such as gender or race.
The Effect of the Rooney Rule on Implicit Bias in the Long Term
Our main result is that, when the panel is constrained by the Rooney Rule, their implicit bias roughly reduces at a rate that is the inverse of the size of the shortlist--independent of the number of candidates, whereas without the Rooney Rule, the rate is inversely proportional to the number of candidates.
Dialect Diversity in Text Summarization on Twitter
Discussions on Twitter involve participation from different communities with different dialects and it is often necessary to summarize a large number of posts into a representative sample to provide a synopsis.
Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees
We present an optimization framework for learning a fair classifier in the presence of noisy perturbations in the protected attributes.
Interventions for Ranking in the Presence of Implicit Bias
Implicit bias is the unconscious attribution of particular qualities (or lack thereof) to a member from a particular social group (e. g., defined by gender or race).
Assessing Social and Intersectional Biases in Contextualized Word Representations
In this paper, we analyze the extent to which state-of-the-art models for contextual word representations, such as BERT and GPT-2, encode biases with respect to gender, race, and intersectional identities.
Data preprocessing to mitigate bias: A maximum entropy based approach
Unlike prior work, it can efficiently learn distributions over large domains, controllably adjust the representation rates of protected groups and achieve target fairness metrics such as statistical parity, yet remains close to the empirical distribution induced by the given dataset.
Improved Adversarial Learning for Fair Classification
Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machine learning research.
Toward Controlling Discrimination in Online Ad Auctions
To prevent this, we propose a constrained ad auction framework that maximizes the platform's revenue conditioned on ensuring that the audience seeing an advertiser's ad is distributed appropriately across sensitive types such as gender or race.
Implicit Diversity in Image Summarization
We develop a novel approach that takes as input a visibly diverse control set of images and uses this set to select a set of images of people in response to a query.
Balanced News Using Constrained Bandit-based Personalization
We present a prototype for a news search engine that presents balanced viewpoints across liberal and conservative articles with the goal of de-polarizing content and allowing users to escape their filter bubble.
Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees
The main contribution of this paper is a new meta-algorithm for classification that takes as input a large class of fairness constraints, with respect to multiple non-disjoint sensitive attributes, and which comes with provable guarantees.
An Algorithmic Framework to Control Bias in Bandit-based Personalization
Personalization is pervasive in the online space as it leads to higher efficiency and revenue by allowing the most relevant content to be served to each user.
Fair and Diverse DPP-based Data Summarization
Sampling methods that choose a subset of the data proportional to its diversity in the feature space are popular for data summarization.
Coordinate Descent with Bandit Sampling
Ideally, we would update the decision variable that yields the largest decrease in the cost function.
Multiwinner Voting with Fairness Constraints
Multiwinner voting rules are used to select a small representative subset of candidates or items from a larger set given the preferences of voters.
Stochastic Optimization with Bandit Sampling
This approach for sampling datapoints is general, and can be used in conjunction with any algorithm that uses an unbiased gradient estimation -- we expect it to have broad applicability beyond the specific examples explored in this work.
Fair Personalization
Personalization is pervasive in the online space as, when combined with learning, it leads to higher efficiency and revenue by allowing the most relevant content to be served to each user.
A Distributed Learning Dynamics in Social Groups
Finally, we observe that our infinite population dynamics is a stochastic variant of the classic multiplicative weights update (MWU) method.
Lean From Thy Neighbor: Stochastic & Adversarial Bandits in a Network
We provide algorithms for this setting, both for stochastic and adversarial bandits, and show that their regret smoothly interpolates between the regret in the classical bandit setting and that of the full-information setting as a function of the neighbors' exploration.
How to be Fair and Diverse?
However, in doing so, a question that seems to be overlooked is whether it is possible to produce fair subsamples that are also adequately representative of the feature space of the data set - an important and classic requirement in machine learning.
On the Complexity of Constrained Determinantal Point Processes
Consequently, we obtain a few algorithms of independent interest: 1) to count over the base polytope of regular matroids when there are additional (succinct) budget constraints and, 2) to evaluate and compute the mixed characteristic polynomials, that played a central role in the resolution of the Kadison-Singer problem, for certain special cases.
Sequential Voting Promotes Collective Discovery in Social Recommendation Systems
Domains in which content quality can be defined exogenously and measured objectively are thus needed in order to better assess the design choices of social recommendation systems.
