activity
20172021
most citedRevisiting Design Choices in Proximal Policy Optimization

13 citations · 24 across the 7 of their papers we have counts for

collaborators

16 papers

cs.LG20212 cited

Alternative Microfoundations for Strategic Classification

Meena Jagadeesan, Celestine Mendler-Dünner, Moritz Hardt

When reasoning about strategic behavior in a machine learning context it is tempting to combine standard microfoundations of rational agents with the statistical decision theory un…

cs.LG202013 cited

Revisiting Design Choices in Proximal Policy Optimization

Chloe Ching-Yun Hsu, Celestine Mendler-Dünner, Moritz Hardt

Proximal Policy Optimization (PPO) is a popular deep policy gradient algorithm. In standard implementations, PPO regularizes policy updates with clipped probability ratios, and par…

cs.LG2020

Randomized Block-Diagonal Preconditioning for Parallel Learning

Celestine Mendler-Dünner, Aurelien Lucchi

We study preconditioned gradient-based optimization methods where the preconditioning matrix has block-diagonal form. Such a structural constraint comes with the advantage that the…

cs.LG2020

Differentially Private Stochastic Coordinate Descent

Georgios Damaskinos, Celestine Mendler-Dünner, Rachid Guerraoui +2

In this paper we tackle the challenge of making the stochastic coordinate descent algorithm differentially private. Compared to the classical gradient descent algorithm where updat…

cs.LG2020

Stochastic Optimization for Performative Prediction

Celestine Mendler-Dünner, Juan C. Perdomo, Tijana Zrnic +1

In performative prediction, the choice of a model influences the distribution of future data, typically through actions taken based on the model's predictions. We initiate the stud…

cs.LG2020

Performative Prediction

Juan C. Perdomo, Tijana Zrnic, Celestine Mendler-Dünner +1

When predictions support decisions they may influence the outcome they aim to predict. We call such predictions performative; the prediction influences the target. Performativity i…