85 citations · 236 across the 13 of their papers we have counts for
19 papers
Explaining Probabilistic Models with Distributional Values
Luca Franceschi, Michele Donini, Cédric Archambeau +1
A large branch of explainable machine learning is grounded in cooperative game theory. However, research indicates that game-theoretic explanations may mislead or be hard to interp…
Efficient fair PCA for fair representation learning
Matthäus Kleindessner, Michele Donini, Chris Russell +1
We revisit the problem of fair principal component analysis (PCA), where the goal is to learn the best low-rank linear approximation of the data that obfuscates demographic informa…
Fortuna: A Library for Uncertainty Quantification in Deep Learning
Gianluca Detommaso, Alberto Gasparin, Michele Donini +3
We present Fortuna, an open-source library for uncertainty quantification in deep learning. Fortuna supports a range of calibration techniques, such as conformal prediction that ca…
Diverse Counterfactual Explanations for Anomaly Detection in Time Series
Deborah Sulem, Michele Donini, Muhammad Bilal Zafar +6
Data-driven methods that detect anomalies in times series data are ubiquitous in practice, but they are in general unable to provide helpful explanations for the predictions they m…
More Than Words: Towards Better Quality Interpretations of Text Classifiers
Muhammad Bilal Zafar, Philipp Schmidt, Michele Donini +4
The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of tru…
Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models
David Nigenda, Zohar Karnin, Muhammad Bilal Zafar +4
With the increasing adoption of machine learning (ML) models and systems in high-stakes settings across different industries, guaranteeing a model's performance after deployment ha…
Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
Michaela Hardt, Xiaoguang Chen, Xiaoyi Cheng +18
Understanding the predictions made by machine learning (ML) models and their potential biases remains a challenging and labor-intensive task that depends on the application, the da…
Multi-objective Asynchronous Successive Halving
Robin Schmucker, Michele Donini, Muhammad Bilal Zafar +2
Hyperparameter optimization (HPO) is increasingly used to automatically tune the predictive performance (e.g., accuracy) of machine learning models. However, in a plethora of real-…
On the Lack of Robust Interpretability of Neural Text Classifiers
Muhammad Bilal Zafar, Michele Donini, Dylan Slack +3
With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted…
Amazon SageMaker Automatic Model Tuning: Scalable Gradient-Free Optimization
Valerio Perrone, Huibin Shen, Aida Zolic +12
Tuning complex machine learning systems is challenging. Machine learning typically requires to set hyperparameters, be it regularization, architecture, or optimization parameters,…
Fair Bayesian Optimization
Valerio Perrone, Michele Donini, Muhammad Bilal Zafar +3
Given the increasing importance of machine learning (ML) in our lives, several algorithmic fairness techniques have been proposed to mitigate biases in the outcomes of the ML model…
MARTHE: Scheduling the Learning Rate Via Online Hypergradients
Michele Donini, Luca Franceschi, Massimiliano Pontil +2
We study the problem of fitting task-specific learning rate schedules from the perspective of hyperparameter optimization, aiming at good generalization. We describe the structure…
Voting with Random Classifiers (VORACE): Theoretical and Experimental Analysis
Cristina Cornelio, Michele Donini, Andrea Loreggia +2
In many machine learning scenarios, looking for the best classifier that fits a particular dataset can be very costly in terms of time and resources. Moreover, it can require deep…
Learning Fair and Transferable Representations
Luca Oneto, Michele Donini, Andreas Maurer +1
Developing learning methods which do not discriminate subgroups in the population is a central goal of algorithmic fairness. One way to reach this goal is by modifying the data rep…
General Fair Empirical Risk Minimization
Luca Oneto, Michele Donini, Massimiliano Pontil
We tackle the problem of algorithmic fairness, where the goal is to avoid the unfairly influence of sensitive information, in the general context of regression with possible contin…
Taking Advantage of Multitask Learning for Fair Classification
Luca Oneto, Michele Donini, Amon Elders +1
A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information…
Empirical Risk Minimization under Fairness Constraints
Michele Donini, Luca Oneto, Shai Ben-David +2
We address the problem of algorithmic fairness: ensuring that sensitive variables do not unfairly influence the outcome of a classifier. We present an approach based on empirical r…
A Bridge Between Hyperparameter Optimization and Learning-to-learn
Luca Franceschi, Michele Donini, Paolo Frasconi +1
We consider a class of a nested optimization problems involving inner and outer objectives. We observe that by taking into explicit account the optimization dynamics for the inner…
Forward and Reverse Gradient-Based Hyperparameter Optimization
Luca Franceschi, Michele Donini, Paolo Frasconi +1
We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm s…