research
∙
06/22/2023
The Inductive Bias of Flatness Regularization for Deep Matrix Factorization
Recent works on over-parameterized neural networks have shown that the s...
share
research
∙
01/31/2023
Debiasing Vision-Language Models via Biased Prompts
Machine learning models have been shown to inherit biases from their tra...
research
∙
10/06/2022
InfoOT: Information Maximizing Optimal Transport
Optimal transport aligns samples across distributions by minimizing the ...
research
∙
10/04/2022
Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks
Understanding generalization and robustness of machine learning models f...
research
∙
01/12/2022
Robust Contrastive Learning against Noisy Views
Contrastive learning relies on an assumption that positive pairs contain...
research
∙
06/07/2021
Measuring Generalization with Optimal Transport
Understanding the generalization of deep neural networks is one of the m...
research
∙
03/11/2021
Fair Mixup: Fairness via Interpolation
Training classifiers under fairness constraints such as group fairness, ...
research
∙
10/09/2020
Contrastive Learning with Hard Negative Samples
We consider the question: how can you sample good negative examples for ...
research
∙
07/06/2020
Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
When machine learning models are deployed on a test distribution differe...
research
∙
07/01/2020
Debiased Contrastive Learning
A prominent technique for self-supervised representation learning has be...
research
∙
10/13/2019
The Role of Embedding Complexity in Domain-invariant Representations
Unsupervised domain adaptation aims to generalize the hypothesis trained...
research
∙
12/20/2017
Learning to Act Properly: Predicting and Explaining Affordances from Images
We address the problem of affordance reasoning in diverse scenes that ap...
research
∙
05/02/2017
Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
Impressive image captioning results are achieved in domains with plenty ...
research
∙
11/12/2016