
Robust finetuning of zeroshot models
Large pretrained models such as CLIP offer consistent accuracy across a...
read it

Retiring Adult: New Datasets for Fair Machine Learning
Although the fairness community has recognized the importance of data, r...
read it

Characterizing Generalization under OutOfDistribution Shifts in Deep Metric Learning
Deep Metric Learning (DML) aims to find representations suitable for zer...
read it

Accuracy on the Line: On the Strong Correlation Between OutofDistribution and InDistribution Generalization
For machine learning systems to be reliable, we must understand their pe...
read it

Predicting with Confidence on Unseen Distributions
Recent work has shown that the performance of machine learning models ca...
read it

Contrasting Contrastive SelfSupervised Representation Learning Models
In the past few years, we have witnessed remarkable breakthroughs in sel...
read it

Measuring Robustness to Natural Distribution Shifts in Image Classification
We study how robust current ImageNet models are to distribution shifts a...
read it

The Effect of Natural Distribution Shift on Question Answering Models
We build four new test sets for the Stanford Question Answering Dataset ...
read it

Neural Kernels Without Tangents
We investigate the connections between neural networks and simple buildi...
read it

A systematic framework for natural perturbations from videos
We introduce a systematic framework for quantifying the robustness of cl...
read it

Unlabeled Data Improves Adversarial Robustness
We demonstrate, theoretically and empirically, that adversarial robustne...
read it

Model Similarity Mitigates Test Set Overuse
Excessive reuse of test data has become commonplace in today's machine l...
read it

Model Reconstruction from Model Explanations
We show through theory and experiment that gradientbased explanations o...
read it

Do CIFAR10 Classifiers Generalize to CIFAR10?
Machine learning is currently dominated by largely experimental work foc...
read it

Adversarially Robust Generalization Requires More Data
Machine learning models are often susceptible to adversarial perturbatio...
read it

Fast and Sample NearOptimal Algorithms for Learning Multidimensional Histograms
We study the problem of robustly learning multidimensional histograms. ...
read it

A Fast Algorithm for Separated Sparsity via Perturbed Lagrangians
Sparsitybased methods are widely used in machine learning, statistics, ...
read it

GraphSparse Logistic Regression
We introduce GraphSparse Logistic Regression, a new algorithm for class...
read it

A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations
Recent work has shown that neural networkbased vision classifiers exhib...
read it

A ClassificationBased Perspective on GAN Distributions
A fundamental, and still largely unanswered, question in the context of ...
read it

Towards Deep Learning Models Resistant to Adversarial Attacks
Recent work has demonstrated that neural networks are vulnerable to adve...
read it

On the FineGrained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks
Empirical risk minimization (ERM) is ubiquitous in machine learning and ...
read it
Ludwig Schmidt
is this you? claim profile