相关论文: Performative Prediction: Past and Future

We study stochastic optimization in the context of performative shifts, where the data distribution changes in response to the deployed model. We demonstrate that naive retraining can be provably suboptimal even for simple distribution…

We propose a fair machine learning algorithm to model interpretable differences between observed and desired human decision-making, with the latter aimed at reducing disparity in a downstream outcome impacted by the human decision. Prior…

In the application of machine learning to real-life decision-making systems, e.g., credit scoring and criminal justice, the prediction outcomes might discriminate against people with sensitive attributes, leading to unfairness. The commonly…

When users stand to gain from certain predictions, they are prone to act strategically to obtain favorable predictive outcomes. Whereas most works on strategic classification consider user actions that manifest as feature modifications, we…

There is a sudden surge to model human behavior due to its vast and diverse applications which includes modeling public policies, economic behavior and consumer behavior. Most of the human behavior itself can be modeled into a choice…

We investigate the prominent class of fair representation learning methods for bias mitigation. Using causal reasoning to define and formalise different sources of dataset bias, we reveal important implicit assumptions inherent to these…

Adaptively forecasting human behavior in social settings is an important step toward achieving Artificial General Intelligence. Most existing research in social forecasting has focused either on unfocused interactions, such as pedestrian…

We propose measurement integrity, a property related to ex post reward fairness, as a novel desideratum for peer prediction mechanisms in many natural applications. Like robustness against strategic reporting, the property that has been the…

Understanding human perceptions of robot performance is crucial for designing socially intelligent robots that can adapt to human expectations. Current approaches often rely on surveys, which can disrupt ongoing human-robot interactions. As…

This paper addresses two main challenges facing systems neuroscience today: understanding the nature and function of a) cortical feedback between sensory areas and b) correlated variability. Starting from the old idea of perception as…

Sequential data - ranging from financial time series to natural language - has driven the growing adoption of autoregressive models. However, these algorithms rely on the presence of underlying patterns in the data, and their identification…

The ability of predicting the future is important for intelligent systems, e.g. autonomous vehicles and robots to plan early and make decisions accordingly. Future scene parsing and optical flow estimation are two key tasks that help agents…

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of…

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…

Feature engineering is a crucial step in the process of predictive modeling. It involves the transformation of given feature space, typically using mathematical functions, with the objective of reducing the modeling error for a given…

Structured prediction plays a central role in machine learning applications from computational biology to computer vision. These models require significantly more computation than unstructured models, and, in many applications, algorithms…

Functions or 'functionings' enable to give a structure to any activity and their combinations constitute the capabilities which characterize economic assets such as work utility. The basic law of supply and demand naturally emerges from…

Model uncertainty is pervasive in real world analysis situations and is an often-neglected issue in applied statistics. However, standard approaches to the research process do not address the inherent uncertainty in model building and,…

User performance is crucial in interactive systems, capturing how effectively users engage with task execution. Prospectively predicting performance enables the timely identification of users struggling with task demands. While ocular and…

The goal of machine learning is to provide solutions which are trained by data or by experience coming from the environment. Many training algorithms exist and some brilliant successes were achieved. But even in structured environments for…