Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Moritz Hardt

Patterns, predictions, and actions: A story about machine learning


Feb 10, 2021
Moritz Hardt, Benjamin Recht


  Access Paper or Ask Questions

Revisiting Design Choices in Proximal Policy Optimization


Sep 23, 2020
Chloe Ching-Yun Hsu, Celestine Mendler-Dünner, Moritz Hardt


  Access Paper or Ask Questions

From Optimizing Engagement to Measuring Value


Aug 21, 2020
Smitha Milli, Luca Belli, Moritz Hardt


  Access Paper or Ask Questions

Stochastic Optimization for Performative Prediction


Jun 16, 2020
Celestine Mendler-Dünner, Juan C. Perdomo, Tijana Zrnic, Moritz Hardt

* 24 pages, 6 figures 

  Access Paper or Ask Questions

Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning


Mar 15, 2020
Esther Rolf, Max Simchowitz, Sarah Dean, Lydia T. Liu, Daniel Björkegren, Moritz Hardt, Joshua Blumenstock


  Access Paper or Ask Questions

Performative Prediction


Feb 16, 2020
Juan C. Perdomo, Tijana Zrnic, Celestine Mendler-Dünner, Moritz Hardt

* 31 pages, 4 figures 

  Access Paper or Ask Questions

Strategic Adaptation to Classifiers: A Causal Perspective


Nov 01, 2019
John Miller, Smitha Milli, Moritz Hardt


  Access Paper or Ask Questions

Test-Time Training for Out-of-Distribution Generalization


Oct 25, 2019
Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt


  Access Paper or Ask Questions

Linear Dynamics: Clustering without identification


Sep 02, 2019
Chloe Ching-Yun Hsu, Michaela Hardt, Moritz Hardt


  Access Paper or Ask Questions

Explaining an increase in predicted risk for clinical alerts


Jul 10, 2019
Michaela Hardt, Alvin Rajkomar, Gerardo Flores, Andrew Dai, Michael Howell, Greg Corrado, Claire Cui, Moritz Hardt


  Access Paper or Ask Questions

Model Similarity Mitigates Test Set Overuse


May 29, 2019
Horia Mania, John Miller, Ludwig Schmidt, Moritz Hardt, Benjamin Recht

* 18 pages, 7 figures 

  Access Paper or Ask Questions

The advantages of multiple classes for reducing overfitting from test set reuse


May 24, 2019
Vitaly Feldman, Roy Frostig, Moritz Hardt


  Access Paper or Ask Questions

Identity Crisis: Memorization and Generalization under Extreme Overparameterization


Feb 15, 2019
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Yoram Singer


  Access Paper or Ask Questions

Natural Analysts in Adaptive Data Analysis


Jan 30, 2019
Tijana Zrnic, Moritz Hardt

* 22 pages 

  Access Paper or Ask Questions

Sanity Checks for Saliency Maps


Oct 28, 2018
Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim

* NIPS 2018 Camera Ready Version 

  Access Paper or Ask Questions

Massively Parallel Hyperparameter Tuning


Oct 17, 2018
Liam Li, Kevin Jamieson, Afshin Rostamizadeh, Ekaterina Gonina, Moritz Hardt, Benjamin Recht, Ameet Talwalkar

* Corrected typo in Algorithm 1 

  Access Paper or Ask Questions

Group calibration is a byproduct of unconstrained learning


Aug 29, 2018
Lydia T. Liu, Max Simchowitz, Moritz Hardt

* 26 pages, 8 figures 

  Access Paper or Ask Questions

The Social Cost of Strategic Classification


Aug 25, 2018
Smitha Milli, John Miller, Anca D. Dragan, Moritz Hardt


  Access Paper or Ask Questions

Identity Matters in Deep Learning


Jul 20, 2018
Moritz Hardt, Tengyu Ma

* ICLR 2017; fixed minor typos in the previous version 

  Access Paper or Ask Questions

Model Reconstruction from Model Explanations


Jul 13, 2018
Smitha Milli, Ludwig Schmidt, Anca D. Dragan, Moritz Hardt


  Access Paper or Ask Questions

When Recurrent Models Don't Need To Be Recurrent


May 29, 2018
John Miller, Moritz Hardt


  Access Paper or Ask Questions

Delayed Impact of Fair Machine Learning


Apr 07, 2018
Lydia T. Liu, Sarah Dean, Esther Rolf, Max Simchowitz, Moritz Hardt

* Proceedings of the 35th International Conference on Machine Learning, PMLR 80:3150-3158, 2018 
* 37 pages, 6 figures 

  Access Paper or Ask Questions

Avoiding Discrimination through Causal Reasoning


Jan 21, 2018
Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf

* Advances in Neural Information Processing Systems 30, 2017, p. 656--666 
* Advances in Neural Information Processing Systems 30, 2017 http://papers.nips.cc/paper/6668-avoiding-discrimination-through-causal-reasoning 

  Access Paper or Ask Questions

Climbing a shaky ladder: Better adaptive risk estimation


Jun 08, 2017
Moritz Hardt


  Access Paper or Ask Questions

Understanding deep learning requires rethinking generalization


Feb 26, 2017
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals

* Published in ICLR 2017 

  Access Paper or Ask Questions

Equality of Opportunity in Supervised Learning


Oct 07, 2016
Moritz Hardt, Eric Price, Nathan Srebro


  Access Paper or Ask Questions