339 citations · 1.1k across the 15 of their papers we have counts for
15 papers
PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale
Kuang-Huei Lee, Ted Xiao, Adrian Li +3
The predictive information, the mutual information between the past and future, has been shown to be a useful representation learning auxiliary loss for training reinforcement lear…
Weighted Ensemble Self-Supervised Learning
Yangjun Ruan, Saurabh Singh, Warren Morningstar +4
Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning. Advances in self-supervised learning…
Deep Hierarchical Planning from Pixels
Danijar Hafner, Kuang-Huei Lee, Ian Fischer +1
Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle com…
An Empirical Investigation of Representation Learning for Imitation
Xin Chen, Sam Toyer, Cody Wild +9
Imitation learning often needs a large demonstration set in order to handle the full range of situations that an agent might find itself in during deployment. However, collecting e…
Multi-Game Decision Transformers
Kuang-Huei Lee, Ofir Nachum, Mengjiao Yang +8
A longstanding goal of the field of AI is a method for learning a highly capable, generalist agent from diverse experience. In the subfields of vision and language, this was largel…
Compressive Visual Representations
Kuang-Huei Lee, Anurag Arnab, Sergio Guadarrama +2
Learning effective visual representations that generalize well without human supervision is a fundamental problem in order to apply Machine Learning to a wide variety of tasks. Rec…
CEB Improves Model Robustness
Ian Fischer, Alexander A. Alemi
We demonstrate that the Conditional Entropy Bottleneck (CEB) can improve model robustness. CEB is an easy strategy to implement and works in tandem with data augmentation procedure…
The Conditional Entropy Bottleneck
Ian Fischer
Much of the field of Machine Learning exhibits a prominent set of failure modes, including vulnerability to adversarial examples, poor out-of-distribution (OoD) detection, miscalib…
Phase Transitions for the Information Bottleneck in Representation Learning
Tailin Wu, Ian Fischer
In the Information Bottleneck (IB), when tuning the relative strength between compression and prediction terms, how do the two terms behave, and what's their relationship with the…
Learning Latent Dynamics for Planning from Pixels
Danijar Hafner, Timothy Lillicrap, Ian Fischer +4
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from intera…
Uncertainty in the Variational Information Bottleneck
Alexander A. Alemi, Ian Fischer, Joshua V. Dillon
We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-…
Fixing a Broken ELBO
Alexander A. Alemi, Ben Poole, Ian Fischer +3
Recent work in unsupervised representation learning has focused on learning deep directed latent-variable models. Fitting these models by maximizing the marginal likelihood or evid…
Generative Models of Visually Grounded Imagination
Ramakrishna Vedantam, Ian Fischer, Jonathan Huang +1
It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before. We call the ability to create images of novel semantic con…
Adversarial Transformation Networks: Learning to Generate Adversarial Examples
Shumeet Baluja, Ian Fischer
Multiple different approaches of generating adversarial examples have been proposed to attack deep neural networks. These approaches involve either directly computing gradients wit…
Speed/accuracy trade-offs for modern convolutional object detectors
Jonathan Huang, Vivek Rathod, Chen Sun +8
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To…