research
∙
11/18/2022
Weighted Ensemble Self-Supervised Learning
Ensembling has proven to be a powerful technique for boosting model perf...
share
research
∙
10/15/2022
PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale
The predictive information, the mutual information between the past and ...
research
∙
06/08/2022
Deep Hierarchical Planning from Pixels
Intelligent agents need to select long sequences of actions to solve com...
research
∙
05/30/2022
Multi-Game Decision Transformers
A longstanding goal of the field of AI is a strategy for compiling diver...
research
∙
05/16/2022
An Empirical Investigation of Representation Learning for Imitation
Imitation learning often needs a large demonstration set in order to han...
research
∙
09/27/2021
Compressive Visual Representations
Learning effective visual representations that generalize well without h...
research
∙
11/17/2020
VIB is Half Bayes
In discriminative settings such as regression and classification there a...
research
∙
07/24/2020
Predictive Information Accelerates Learning in RL
The Predictive Information is the mutual information between the past an...
research
∙
07/24/2020
Cycles in Causal Learning
In the causal learning setting, we wish to learn cause-and-effect relati...
research
∙
06/11/2020
An Unsupervised Information-Theoretic Perceptual Quality Metric
Tractable models of human perception have proved to be challenging to bu...
research
∙
02/13/2020
CEB Improves Model Robustness
We demonstrate that the Conditional Entropy Bottleneck (CEB) can improve...
research
∙
02/13/2020
The Conditional Entropy Bottleneck
Much of the field of Machine Learning exhibits a prominent set of failur...
research
∙
01/07/2020
Phase Transitions for the Information Bottleneck in Representation Learning
In the Information Bottleneck (IB), when tuning the relative strength be...
research
∙
07/22/2019
Information-Bottleneck Approach to Salient Region Discovery
We propose a new method for learning image attention masks in a semi-sup...
research
∙
07/17/2019
Learnability for the Information Bottleneck
The Information Bottleneck (IB) method (tishby2000information) provides ...
research
∙
05/17/2019
Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces
Variational autoencoders learn unsupervised data representations, but th...
research
∙
11/12/2018
Learning Latent Dynamics for Planning from Pixels
Planning has been very successful for control tasks with known environme...
research
∙
07/11/2018
TherML: Thermodynamics of Machine Learning
In this work we offer a framework for reasoning about a wide class of ex...
research
∙
07/02/2018
Uncertainty in the Variational Information Bottleneck
We present a simple case study, demonstrating that Variational Informati...
research
∙
02/13/2018
GILBO: One Metric to Measure Them All
We propose a simple, tractable lower bound on the mutual information con...
research
∙
11/01/2017
An Information-Theoretic Analysis of Deep Latent-Variable Models
We present an information-theoretic framework for understanding trade-of...
research
∙
05/30/2017
Generative Models of Visually Grounded Imagination
It is easy for people to imagine what a man with pink hair looks like, e...
research
∙
03/28/2017
Adversarial Transformation Networks: Learning to Generate Adversarial Examples
Multiple different approaches of generating adversarial examples have be...
research
∙
02/22/2017
Adversarial examples for generative models
We explore methods of producing adversarial examples on deep generative ...
research
∙
11/30/2016