相关论文: Post-Match Error Mitigation for Deferred Acceptanc…

Automatic matching of job offers and job candidates is a major problem for a number of organizations and job applicants that if it were successfully addressed could have a positive impact in many countries around the world. In this context,…

Recent research has shown that seemingly fair machine learning models, when used to inform decisions that have an impact on peoples' lives or well-being (e.g., applications involving education, employment, and lending), can inadvertently…

Currently, many machine learning algorithms contain lots of iterations. When it comes to existing large-scale distributed systems, some slave nodes may break down or have lower efficiency. Therefore traditional machine learning algorithm…

Machine learning algorithms that aid human decision-making may inadvertently discriminate against certain protected groups. We formalize direct discrimination as a direct causal effect of the protected attributes on the decisions, while…

We address the question of repeatedly learning linear classifiers against agents who are strategically trying to game the deployed classifiers, and we use the Stackelberg regret to measure the performance of our algorithms. First, we show…

Data-driven AI systems can lead to discrimination on the basis of protected attributes like gender or race. One reason for this behavior is the encoded societal biases in the training data (e.g., females are underrepresented), which is…

Although the distributed machine learning methods can speed up the training of large deep neural networks, the communication cost has become the non-negligible bottleneck to constrain the performance. To address this challenge, the gradient…

Most research on fair machine learning has prioritized optimizing criteria such as Demographic Parity and Equalized Odds. Despite these efforts, there remains a limited understanding of how different bias mitigation strategies affect…

Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time. Conventional wisdom suggests that fairness criteria promote the…

Recent advancements in machine learning research, i.e., deep learning, introduced methods that excel conventional algorithms as well as humans in several complex tasks, ranging from detection of objects in images and speech recognition to…

In this paper, we study the fundamental problem of finding a stable matching in two-sided matching markets. In the classic variant, it is assumed that both sides of the market submit a ranked list of all agents on the other side. However,…

Predictive models often reinforce biases which were originally embedded in their training data, through skewed decisions. In such cases, mitigation methods are critical to ensure that, regardless of the prevailing disparities, model…

This paper examines the identification and estimation of treatment effects in staggered adoption designs -- a common extension of the canonical Difference-in-Differences (DiD) model to multiple groups and time-periods -- in the presence of…

Large pre-trained language models contain societal biases and carry along these biases to downstream tasks. Current in-processing bias mitigation approaches (like adversarial training) impose debiasing by updating a model's parameters,…

Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning…

The spectral deferred correction method is a variant of the deferred correction method for solving ordinary differential equations. A benefit of this method is that is uses low order schemes iteratively to produce a high order…

We study distributed user association in 5G and beyond millimeter-wave enabled heterogeneous networks using matching theory. We propose a novel and efficient distributed matching game, called early acceptance (EA), which allows users to…

Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we…

Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on…

Although federated learning has achieved many breakthroughs recently, the heterogeneous nature of the learning environment greatly limits its performance and hinders its real-world applications. The heterogeneous data, time-varying wireless…