Search Results for author:
Found 15 papers, 2 papers with code
Certified Adversarial Robustness via Randomized Smoothing
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm.
Ranked #3 on
Robust classification
on CIFAR-10
Certified Robustness to Adversarial Label-Flipping Attacks via Randomized Smoothing
This paper considers label-flipping attacks, a type of data poisoning attack where an adversary relabels a small number of examples in a training set in order to degrade the performance of the resulting classifier.
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing
Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier.
Self-Reflective Variational Autoencoder
The Variational Autoencoder (VAE) is a powerful framework for learning probabilistic latent variable generative models.
The Risks of Invariant Risk Minimization
We furthermore present the very first results in the non-linear regime: we demonstrate that IRM can fail catastrophically unless the test data are sufficiently similar to the training distribution--this is precisely the issue that it was intended to solve.
An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization
A popular assumption for out-of-distribution generalization is that the training data comprises sub-datasets, each drawn from a distinct distribution; the goal is then to "interpolate" these distributions and "extrapolate" beyond them -- this objective is broadly known as domain generalization.
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments.
Deep Attentive Variational Inference
Moreover, the architecture for this class of models favors local interactions among the latent variables between neighboring layers when designing the conditioning factors of the involved distributions.
Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation
Noise-contrastive estimation (NCE) is a statistically consistent method for learning unnormalized probabilistic models.
Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization
Towards this end, we introduce Domain-Adjusted Regression (DARE), a convex objective for learning a linear predictor that is provably robust under a new model of distribution shift.
APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations
Recent advances in learning aligned multimodal representations have been primarily driven by training large neural networks on massive, noisy paired-modality datasets.
Learning Linear Causal Representations from Interventions under General Nonlinear Mixing
We study the problem of learning causal representations from unknown, latent interventions in a general setting, where the latent distribution is Gaussian but the mixing function is completely general.
Identifying Representations for Intervention Extrapolation
In this paper, we consider the task of intervention extrapolation: predicting how interventions affect an outcome, even when those interventions are not observed at training time, and show that identifiable representations can provide an effective solution to this task even if the interventions affect the outcome non-linearly.
One-Shot Strategic Classification Under Unknown Costs
The goal of strategic classification is to learn decision rules which are robust to strategic input manipulation.
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
We identify a new phenomenon in neural network optimization which arises from the interaction of depth and a particular heavy-tailed structure in natural data.
