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 Ludwig Schmidt

Ludwig Schmidt

Robust fine-tuning of zero-shot models


Sep 04, 2021
Mitchell Wortsman, Gabriel Ilharco, Mike Li, Jong Wook Kim, Hannaneh Hajishirzi, Ali Farhadi, Hongseok Namkoong, Ludwig Schmidt

Figure 1 for Robust fine-tuning of zero-shot models
Figure 2 for Robust fine-tuning of zero-shot models
Figure 3 for Robust fine-tuning of zero-shot models
Figure 4 for Robust fine-tuning of zero-shot models

  Access Paper or Ask Questions

Retiring Adult: New Datasets for Fair Machine Learning


Aug 10, 2021
Frances Ding, Moritz Hardt, John Miller, Ludwig Schmidt

Figure 1 for Retiring Adult: New Datasets for Fair Machine Learning
Figure 2 for Retiring Adult: New Datasets for Fair Machine Learning
Figure 3 for Retiring Adult: New Datasets for Fair Machine Learning
Figure 4 for Retiring Adult: New Datasets for Fair Machine Learning

  Access Paper or Ask Questions

Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning


Jul 20, 2021
Timo Milbich, Karsten Roth, Samarth Sinha, Ludwig Schmidt, Marzyeh Ghassemi, Björn Ommer

Figure 1 for Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
Figure 2 for Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
Figure 3 for Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
Figure 4 for Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning

  Access Paper or Ask Questions

Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization


Jul 09, 2021
John Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, Ludwig Schmidt

Figure 1 for Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
Figure 2 for Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
Figure 3 for Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
Figure 4 for Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization

  Access Paper or Ask Questions

Predicting with Confidence on Unseen Distributions


Jul 07, 2021
Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi, Trevor Darrell, Ludwig Schmidt

Figure 1 for Predicting with Confidence on Unseen Distributions
Figure 2 for Predicting with Confidence on Unseen Distributions
Figure 3 for Predicting with Confidence on Unseen Distributions
Figure 4 for Predicting with Confidence on Unseen Distributions

  Access Paper or Ask Questions

Contrasting Contrastive Self-Supervised Representation Learning Models


Mar 25, 2021
Klemen Kotar, Gabriel Ilharco, Ludwig Schmidt, Kiana Ehsani, Roozbeh Mottaghi

Figure 1 for Contrasting Contrastive Self-Supervised Representation Learning Models
Figure 2 for Contrasting Contrastive Self-Supervised Representation Learning Models
Figure 3 for Contrasting Contrastive Self-Supervised Representation Learning Models
Figure 4 for Contrasting Contrastive Self-Supervised Representation Learning Models

  Access Paper or Ask Questions

Measuring Robustness to Natural Distribution Shifts in Image Classification


Jul 01, 2020
Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Benjamin Recht, Ludwig Schmidt

Figure 1 for Measuring Robustness to Natural Distribution Shifts in Image Classification
Figure 2 for Measuring Robustness to Natural Distribution Shifts in Image Classification
Figure 3 for Measuring Robustness to Natural Distribution Shifts in Image Classification
Figure 4 for Measuring Robustness to Natural Distribution Shifts in Image Classification

  Access Paper or Ask Questions

The Effect of Natural Distribution Shift on Question Answering Models


Apr 29, 2020
John Miller, Karl Krauth, Benjamin Recht, Ludwig Schmidt

Figure 1 for The Effect of Natural Distribution Shift on Question Answering Models
Figure 2 for The Effect of Natural Distribution Shift on Question Answering Models
Figure 3 for The Effect of Natural Distribution Shift on Question Answering Models
Figure 4 for The Effect of Natural Distribution Shift on Question Answering Models

  Access Paper or Ask Questions

Neural Kernels Without Tangents


Mar 05, 2020
Vaishaal Shankar, Alex Fang, Wenshuo Guo, Sara Fridovich-Keil, Ludwig Schmidt, Jonathan Ragan-Kelley, Benjamin Recht

Figure 1 for Neural Kernels Without Tangents
Figure 2 for Neural Kernels Without Tangents
Figure 3 for Neural Kernels Without Tangents
Figure 4 for Neural Kernels Without Tangents
* code used to produce our results can be found at: https://github.com/modestyachts/neural_kernels_code 
  Access Paper or Ask Questions

Unlabeled Data Improves Adversarial Robustness


Jun 10, 2019
Yair Carmon, Aditi Raghunathan, Ludwig Schmidt, Percy Liang, John C. Duchi

Figure 1 for Unlabeled Data Improves Adversarial Robustness
Figure 2 for Unlabeled Data Improves Adversarial Robustness
Figure 3 for Unlabeled Data Improves Adversarial Robustness
Figure 4 for Unlabeled Data Improves Adversarial Robustness

  Access Paper or Ask Questions

A systematic framework for natural perturbations from videos


Jun 05, 2019
Vaishaal Shankar, Achal Dave, Rebecca Roelofs, Deva Ramanan, Benjamin Recht, Ludwig Schmidt

Figure 1 for A systematic framework for natural perturbations from videos
Figure 2 for A systematic framework for natural perturbations from videos
Figure 3 for A systematic framework for natural perturbations from videos
Figure 4 for A systematic framework for natural perturbations from videos
* 16 pages, 5 tables, 6 figures. Paper Website: https://modestyachts.github.io/natural-perturbations-website/ 
  Access Paper or Ask Questions

Model Similarity Mitigates Test Set Overuse


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

Figure 1 for Model Similarity Mitigates Test Set Overuse
Figure 2 for Model Similarity Mitigates Test Set Overuse
Figure 3 for Model Similarity Mitigates Test Set Overuse
Figure 4 for Model Similarity Mitigates Test Set Overuse
* 18 pages, 7 figures 
  Access Paper or Ask Questions

Do ImageNet Classifiers Generalize to ImageNet?


Feb 13, 2019
Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, Vaishaal Shankar

Figure 1 for Do ImageNet Classifiers Generalize to ImageNet?
Figure 2 for Do ImageNet Classifiers Generalize to ImageNet?
Figure 3 for Do ImageNet Classifiers Generalize to ImageNet?
Figure 4 for Do ImageNet Classifiers Generalize to ImageNet?

  Access Paper or Ask Questions

Model Reconstruction from Model Explanations


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

Figure 1 for Model Reconstruction from Model Explanations
Figure 2 for Model Reconstruction from Model Explanations
Figure 3 for Model Reconstruction from Model Explanations
Figure 4 for Model Reconstruction from Model Explanations

  Access Paper or Ask Questions

A Classification-Based Study of Covariate Shift in GAN Distributions


Jun 06, 2018
Shibani Santurkar, Ludwig Schmidt, Aleksander MÄ…dry

Figure 1 for A Classification-Based Study of Covariate Shift in GAN Distributions
Figure 2 for A Classification-Based Study of Covariate Shift in GAN Distributions
Figure 3 for A Classification-Based Study of Covariate Shift in GAN Distributions
Figure 4 for A Classification-Based Study of Covariate Shift in GAN Distributions

  Access Paper or Ask Questions

On the Limitations of First-Order Approximation in GAN Dynamics


Jun 03, 2018
Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt

Figure 1 for On the Limitations of First-Order Approximation in GAN Dynamics
Figure 2 for On the Limitations of First-Order Approximation in GAN Dynamics
Figure 3 for On the Limitations of First-Order Approximation in GAN Dynamics
* 18 pages, 4 figures, accepted to ICML 2018 
  Access Paper or Ask Questions

Do CIFAR-10 Classifiers Generalize to CIFAR-10?


Jun 01, 2018
Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, Vaishaal Shankar

Figure 1 for Do CIFAR-10 Classifiers Generalize to CIFAR-10?
Figure 2 for Do CIFAR-10 Classifiers Generalize to CIFAR-10?
Figure 3 for Do CIFAR-10 Classifiers Generalize to CIFAR-10?
Figure 4 for Do CIFAR-10 Classifiers Generalize to CIFAR-10?

  Access Paper or Ask Questions

Adversarially Robust Generalization Requires More Data


May 02, 2018
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander MÄ…dry

Figure 1 for Adversarially Robust Generalization Requires More Data
Figure 2 for Adversarially Robust Generalization Requires More Data
Figure 3 for Adversarially Robust Generalization Requires More Data
Figure 4 for Adversarially Robust Generalization Requires More Data
* Small changes for biblatex compatibility 
  Access Paper or Ask Questions

Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms


Feb 23, 2018
Ilias Diakonikolas, Jerry Li, Ludwig Schmidt

Figure 1 for Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms

  Access Paper or Ask Questions

A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations


Feb 13, 2018
Logan Engstrom, Brandon Tran, Dimitris Tsipras, Ludwig Schmidt, Aleksander Madry

Figure 1 for A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations
Figure 2 for A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations
Figure 3 for A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations
Figure 4 for A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations
* Preliminary version appeared in the NIPS 2017 Workshop on Machine Learning and Computer Security 
  Access Paper or Ask Questions

Graph-Sparse Logistic Regression


Dec 15, 2017
Alexander LeNail, Ludwig Schmidt, Johnathan Li, Tobias Ehrenberger, Karen Sachs, Stefanie Jegelka, Ernest Fraenkel

Figure 1 for Graph-Sparse Logistic Regression
Figure 2 for Graph-Sparse Logistic Regression
* 7 pages, 2 figures, NIPS DISCML workshop paper 
  Access Paper or Ask Questions

Towards Deep Learning Models Resistant to Adversarial Attacks


Nov 09, 2017
Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu

Figure 1 for Towards Deep Learning Models Resistant to Adversarial Attacks
Figure 2 for Towards Deep Learning Models Resistant to Adversarial Attacks
Figure 3 for Towards Deep Learning Models Resistant to Adversarial Attacks
Figure 4 for Towards Deep Learning Models Resistant to Adversarial Attacks

  Access Paper or Ask Questions

On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks


Apr 10, 2017
Arturs Backurs, Piotr Indyk, Ludwig Schmidt


  Access Paper or Ask Questions

Fast Algorithms for Segmented Regression


Jul 14, 2016
Jayadev Acharya, Ilias Diakonikolas, Jerry Li, Ludwig Schmidt

Figure 1 for Fast Algorithms for Segmented Regression
Figure 2 for Fast Algorithms for Segmented Regression
Figure 3 for Fast Algorithms for Segmented Regression
* 27 pages, appeared in ICML 2016 
  Access Paper or Ask Questions

A Nearly Optimal and Agnostic Algorithm for Properly Learning a Mixture of k Gaussians, for any Constant k


Jun 03, 2015
Jerry Li, Ludwig Schmidt

Figure 1 for A Nearly Optimal and Agnostic Algorithm for Properly Learning a Mixture of k Gaussians, for any Constant k

  Access Paper or Ask Questions

Sample-Optimal Density Estimation in Nearly-Linear Time


Jun 01, 2015
Jayadev Acharya, Ilias Diakonikolas, Jerry Li, Ludwig Schmidt

Figure 1 for Sample-Optimal Density Estimation in Nearly-Linear Time
Figure 2 for Sample-Optimal Density Estimation in Nearly-Linear Time
Figure 3 for Sample-Optimal Density Estimation in Nearly-Linear Time
Figure 4 for Sample-Optimal Density Estimation in Nearly-Linear Time

  Access Paper or Ask Questions