Search Results for author: Ludwig Schmidt

Found 40 papers, 17 papers with code

Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)

1 code implementation3 May 2022 Alex Fang, Gabriel Ilharco, Mitchell Wortsman, Yuhao Wan, Vaishaal Shankar, Achal Dave, Ludwig Schmidt

Contrastively trained image-text models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts.

CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration

no code implementations20 Mar 2022 Samir Yitzhak Gadre, Mitchell Wortsman, Gabriel Ilharco, Ludwig Schmidt, Shuran Song

Employing this philosophy, we design CLIP on Wheels (CoW) baselines for the task and evaluate each zero-shot model in both Habitat and RoboTHOR simulators.

Image Classification Object Localization

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

2 code implementations10 Mar 2022 Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, Ludwig Schmidt

In this paper, we revisit the second step of this procedure in the context of fine-tuning large pre-trained models, where fine-tuned models often appear to lie in a single low error basin.

 Ranked #1 on Image Classification on ImageNet V2 (using extra training data)

Domain Generalization Image Classification +1

Robust fine-tuning of zero-shot models

1 code implementation4 Sep 2021 Mitchell Wortsman, Gabriel Ilharco, Jong Wook Kim, Mike Li, Simon Kornblith, Rebecca Roelofs, Raphael Gontijo Lopes, Hannaneh Hajishirzi, Ali Farhadi, Hongseok Namkoong, Ludwig Schmidt

Compared to standard fine-tuning, WiSE-FT provides large accuracy improvements under distribution shift, while preserving high accuracy on the target distribution.

Transfer Learning

Retiring Adult: New Datasets for Fair Machine Learning

1 code implementation NeurIPS 2021 Frances Ding, Moritz Hardt, John Miller, Ludwig Schmidt

Our primary contribution is a suite of new datasets derived from US Census surveys that extend the existing data ecosystem for research on fair machine learning.


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

2 code implementations NeurIPS 2021 Timo Milbich, Karsten Roth, Samarth Sinha, Ludwig Schmidt, Marzyeh Ghassemi, Björn Ommer

Finally, we propose few-shot DML as an efficient way to consistently improve generalization in response to unknown test shifts presented in ooDML.

Metric Learning

Predicting with Confidence on Unseen Distributions

no code implementations ICCV 2021 Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi, Trevor Darrell, Ludwig Schmidt

Our work connects techniques from domain adaptation and predictive uncertainty literature, and allows us to predict model accuracy on challenging unseen distributions without access to labeled data.

Domain Adaptation

The Effect of Natural Distribution Shift on Question Answering Models

no code implementations ICML 2020 John Miller, Karl Krauth, Benjamin Recht, Ludwig Schmidt

We build four new test sets for the Stanford Question Answering Dataset (SQuAD) and evaluate the ability of question-answering systems to generalize to new data.

Question Answering

Neural Kernels Without Tangents

1 code implementation ICML 2020 Vaishaal Shankar, Alex Fang, Wenshuo Guo, Sara Fridovich-Keil, Ludwig Schmidt, Jonathan Ragan-Kelley, Benjamin Recht

We investigate the connections between neural networks and simple building blocks in kernel space.

A Meta-Analysis of Overfitting in Machine Learning

no code implementations NeurIPS 2019 Rebecca Roelofs, Vaishaal Shankar, Benjamin Recht, Sara Fridovich-Keil, Moritz Hardt, John Miller, Ludwig Schmidt

By systematically comparing the public ranking with the final ranking, we assess how much participants adapted to the holdout set over the course of a competition.

Do Image Classifiers Generalize Across Time?

1 code implementation ICCV 2021 Vaishaal Shankar, Achal Dave, Rebecca Roelofs, Deva Ramanan, Benjamin Recht, Ludwig Schmidt

Additionally, we evaluate three detection models and show that natural perturbations induce both classification as well as localization errors, leading to a median drop in detection mAP of 14 points.

General Classification Video Object Detection

Unlabeled Data Improves Adversarial Robustness

4 code implementations NeurIPS 2019 Yair Carmon, aditi raghunathan, Ludwig Schmidt, Percy Liang, John C. Duchi

We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning.

Adversarial Robustness Robust classification

Model Similarity Mitigates Test Set Overuse

no code implementations NeurIPS 2019 Horia Mania, John Miller, Ludwig Schmidt, Moritz Hardt, Benjamin Recht

Excessive reuse of test data has become commonplace in today's machine learning workflows.

A Systematic Framework for Natural Perturbations from Videos

no code implementations ICML Workshop Deep_Phenomen 2019 Vaishaal Shankar, Achal Dave, Rebecca Roelofs, Deva Ramanan, Benjamin Recht, Ludwig Schmidt

We introduce a systematic framework for quantifying the robustness of classifiers to naturally occurring perturbations of images found in videos.

Video Object Detection

Model Reconstruction from Model Explanations

no code implementations13 Jul 2018 Smitha Milli, Ludwig Schmidt, Anca D. Dragan, Moritz Hardt

We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself.

Do CIFAR-10 Classifiers Generalize to CIFAR-10?

3 code implementations1 Jun 2018 Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, Vaishaal Shankar

Although we ensure that the new test set is as close to the original data distribution as possible, we find a large drop in accuracy (4% to 10%) for a broad range of deep learning models.

Adversarially Robust Generalization Requires More Data

no code implementations NeurIPS 2018 Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Mądry

We postulate that the difficulty of training robust classifiers stems, at least partially, from this inherently larger sample complexity.

General Classification Image Classification

Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms

no code implementations23 Feb 2018 Ilias Diakonikolas, Jerry Li, Ludwig Schmidt

We give an algorithm for this learning problem that uses $n = \tilde{O}_d(k/\epsilon^2)$ samples and runs in time $\tilde{O}_d(n)$.

On the limitations of first order approximation in GAN dynamics

no code implementations ICLR 2018 Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt

This suggests that such usage of the first order approximation of the discriminator, which is a de-facto standard in all the existing GAN dynamics, might be one of the factors that makes GAN training so challenging in practice.

Learning Representations for Faster Similarity Search

no code implementations ICLR 2018 Ludwig Schmidt, Kunal Talwar

Based on our experiments, we propose a number of training modifications that lead to significantly better datasets for nearest neighbor algorithms.

General Classification

A Classification-Based Perspective on GAN Distributions

no code implementations ICLR 2018 Shibani Santurkar, Ludwig Schmidt, Aleksander Madry

A fundamental, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether GANs are actually able to capture the key characteristics of the datasets they are trained on.

Classification General Classification

Graph-Sparse Logistic Regression

1 code implementation15 Dec 2017 Alexander LeNail, Ludwig Schmidt, Johnathan Li, Tobias Ehrenberger, Karen Sachs, Stefanie Jegelka, Ernest Fraenkel

We introduce Graph-Sparse Logistic Regression, a new algorithm for classification for the case in which the support should be sparse but connected on a graph.

General Classification

Communication-Efficient Distributed Learning of Discrete Distributions

no code implementations NeurIPS 2017 Ilias Diakonikolas, Elena Grigorescu, Jerry Li, Abhiram Natarajan, Krzysztof Onak, Ludwig Schmidt

For the case of structured distributions, such as k-histograms and monotone distributions, we design distributed learning algorithms that achieve significantly better communication guarantees than the naive ones, and obtain tight upper and lower bounds in several regimes.

Density Estimation

A Classification-Based Study of Covariate Shift in GAN Distributions

no code implementations ICML 2018 Shibani Santurkar, Ludwig Schmidt, Aleksander Mądry

A basic, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether they are truly able to capture all the fundamental characteristics of the distributions they are trained on.

Classification General Classification

On the Limitations of First-Order Approximation in GAN Dynamics

no code implementations ICML 2018 Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt

While Generative Adversarial Networks (GANs) have demonstrated promising performance on multiple vision tasks, their learning dynamics are not yet well understood, both in theory and in practice.

Towards Deep Learning Models Resistant to Adversarial Attacks

45 code implementations ICLR 2018 Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu

Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.

Adversarial Attack Adversarial Defense +6

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

no code implementations NeurIPS 2017 Arturs Backurs, Piotr Indyk, Ludwig Schmidt

We also give similar hardness results for computing the gradient of the empirical loss, which is the main computational burden in many non-convex learning tasks.

Fast recovery from a union of subspaces

no code implementations NeurIPS 2016 Chinmay Hegde, Piotr Indyk, Ludwig Schmidt

We address the problem of recovering a high-dimensional but structured vector from linear observations in a general setting where the vector can come from an arbitrary union of subspaces.

Compressive Sensing

Fast Algorithms for Segmented Regression

no code implementations14 Jul 2016 Jayadev Acharya, Ilias Diakonikolas, Jerry Li, Ludwig Schmidt

We study the fixed design segmented regression problem: Given noisy samples from a piecewise linear function $f$, we want to recover $f$ up to a desired accuracy in mean-squared error.

Differentially Private Learning of Structured Discrete Distributions

no code implementations NeurIPS 2015 Ilias Diakonikolas, Moritz Hardt, Ludwig Schmidt

We investigate the problem of learning an unknown probability distribution over a discrete population from random samples.

Practical and Optimal LSH for Angular Distance

1 code implementation NeurIPS 2015 Alexandr Andoni, Piotr Indyk, Thijs Laarhoven, Ilya Razenshteyn, Ludwig Schmidt

Our lower bound implies that the above LSH family exhibits a trade-off between evaluation time and quality that is close to optimal for a natural class of LSH functions.

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

no code implementations3 Jun 2015 Jerry Li, Ludwig Schmidt

One notion of learning a GMM is proper learning: here, the goal is to find a mixture of $k$ Gaussians $\mathcal{M}$ that is close to the density $f$ of the unknown distribution from which we draw samples.

Learning Theory

Sample-Optimal Density Estimation in Nearly-Linear Time

no code implementations1 Jun 2015 Jayadev Acharya, Ilias Diakonikolas, Jerry Li, Ludwig Schmidt

Let $f$ be the density function of an arbitrary univariate distribution, and suppose that $f$ is $\mathrm{OPT}$-close in $L_1$-distance to an unknown piecewise polynomial function with $t$ interval pieces and degree $d$.

Density Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.