Ensembling has proven to be a powerful technique for boosting model
perf...
The predictive information, the mutual information between the past and
...
Intelligent agents need to select long sequences of actions to solve com...
A longstanding goal of the field of AI is a strategy for compiling diver...
Imitation learning often needs a large demonstration set in order to han...
Learning effective visual representations that generalize well without h...
In discriminative settings such as regression and classification there a...
The Predictive Information is the mutual information between the past an...
In the causal learning setting, we wish to learn cause-and-effect
relati...
Tractable models of human perception have proved to be challenging to bu...
We demonstrate that the Conditional Entropy Bottleneck (CEB) can improve...
Much of the field of Machine Learning exhibits a prominent set of failur...
In the Information Bottleneck (IB), when tuning the relative strength be...
We propose a new method for learning image attention masks in a
semi-sup...
The Information Bottleneck (IB) method (tishby2000information)
provides ...
Variational autoencoders learn unsupervised data representations, but th...
Planning has been very successful for control tasks with known environme...
In this work we offer a framework for reasoning about a wide class of
ex...
We present a simple case study, demonstrating that Variational Informati...
We propose a simple, tractable lower bound on the mutual information
con...
We present an information-theoretic framework for understanding trade-of...
It is easy for people to imagine what a man with pink hair looks like, e...
Multiple different approaches of generating adversarial examples have be...
We explore methods of producing adversarial examples on deep generative
...
The goal of this paper is to serve as a guide for selecting a detection
...