Effective machine learning models learn both robust features that direct...
Errors of machine learning models are costly, especially in safety-criti...
Conventional approaches to robustness try to learn a model based on caus...
The fluency and factual knowledge of large language models (LLMs) height...
Distribution shift occurs when the test distribution differs from the
tr...
A common approach to transfer learning under distribution shift is to
fi...
A Bayesian pseudocoreset is a small synthetic dataset for which the post...
Many datasets are underspecified, which means there are several equally
...
Deep ensembles excel in large-scale image classification tasks both in t...
This paper studies probability distributions of penultimate activations ...
Amortized approaches to clustering have recently received renewed attent...
Unlike in the traditional statistical modeling for which a user typicall...
While various complexity measures for diverse model classes have been
pr...
We propose a deep amortized clustering (DAC), a neural architecture whic...
Without relevant human priors, neural networks may learn uninterpretable...
Learning compact discrete representations of data is itself a key task i...
Many machine learning tasks such as multiple instance learning, 3D shape...
Recent advances in meta-learning demonstrate that deep representations
c...