Search Results for author:
Found 15 papers, 9 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.
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).
Designing Closed Human-in-the-loop Deferral Pipelines
Our key insight is that by exploiting weak prior information, we can match experts to input examples to ensure fairness and accuracy of the resulting deferral framework, even when imperfect and biased experts are used in place of ground truth labels.
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.
Towards Unbiased and Accurate Deferral to Multiple Experts
Machine learning models are often implemented in cohort with humans in the pipeline, with the model having an option to defer to a domain expert in cases where it has low confidence in its inference.
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.
A Convergent and Dimension-Independent Min-Max Optimization Algorithm
The equilibrium point found by our algorithm depends on the proposal distribution, and when applying our algorithm to train GANs we choose the proposal distribution to be a distribution of stochastic gradients.
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.
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.
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.
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.
