activity
20182021
most citedMinimax Pareto Fairness: A Multi Objective Perspective

56 citations · 71 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG20211 cited

Federating for Learning Group Fair Models

Afroditi Papadaki, Natalia Martinez, Martin Bertran +2

Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minmax group fairness…

stat.ML202056 cited

Minimax Pareto Fairness: A Multi Objective Perspective

Natalia Martinez, Martin Bertran, Guillermo Sapiro

In this work we formulate and formally characterize group fairness as a multi-objective optimization problem, where each sensitive group risk is a separate objective. We propose a…

cs.LG20201 cited

Instance based Generalization in Reinforcement Learning

Martin Bertran, Natalia Martinez, Mariano Phielipp +1

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels.…

cs.LG201910 cited

Fairness With Minimal Harm: A Pareto-Optimal Approach For Healthcare

Natalia Martinez, Martin Bertran, Guillermo Sapiro

Common fairness definitions in machine learning focus on balancing notions of disparity and utility. In this work, we study fairness in the context of risk disparity among sub-popu…

cs.CV20193 cited

Non-contact photoplethysmogram and instantaneous heart rate estimation from infrared face video

Natalia Martinez, Martin Bertran, Guillermo Sapiro +1

Extracting the instantaneous heart rate (iHR) from face videos has been well studied in recent years. It is well known that changes in skin color due to blood flow can be captured…

stat.ML2018

Learning to Collaborate for User-Controlled Privacy

Martin Bertran, Natalia Martinez, Afroditi Papadaki +3

It is becoming increasingly clear that users should own and control their data. Utility providers are also becoming more interested in guaranteeing data privacy. As such, users and…