Picture for Chris Cundy

Chris Cundy

LMPriors: Pre-Trained Language Models as Task-Specific Priors

Oct 22, 2022
Kristy Choi, Chris Cundy, Sanjari Srivastava, Stefano Ermon

Figure 1 for LMPriors: Pre-Trained Language Models as Task-Specific Priors

Figure 2 for LMPriors: Pre-Trained Language Models as Task-Specific Priors

Figure 3 for LMPriors: Pre-Trained Language Models as Task-Specific Priors

Figure 4 for LMPriors: Pre-Trained Language Models as Task-Specific Priors

* First two authors contributed equally

Access Paper or Ask Questions

Beyond Bayes-optimality: meta-learning what you know you don't know

Oct 12, 2022
Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Tim Genewein, Elliot Catt, Kevin Li, Anian Ruoss, Chris Cundy, Joel Veness, Jane Wang, Marcus Hutter, Christopher Summerfield, Shane Legg, Pedro Ortega

Figure 1 for Beyond Bayes-optimality: meta-learning what you know you don't know

Figure 2 for Beyond Bayes-optimality: meta-learning what you know you don't know

Figure 3 for Beyond Bayes-optimality: meta-learning what you know you don't know

Figure 4 for Beyond Bayes-optimality: meta-learning what you know you don't know

* 33 pages, 8 figures, technical report

Access Paper or Ask Questions

BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

Dec 06, 2021
Chris Cundy, Aditya Grover, Stefano Ermon

Figure 1 for BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

Figure 2 for BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

Figure 3 for BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

Figure 4 for BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

* Neural Information Processing Systems 2021

Access Paper or Ask Questions

Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

Jan 02, 2021
Chris Cundy, Stefano Ermon

Figure 1 for Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

Figure 2 for Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

Figure 3 for Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

Figure 4 for Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

* 8 pages; figure/table formatting fixed

Access Paper or Ask Questions

Exploring Hierarchy-Aware Inverse Reinforcement Learning

Jul 13, 2018
Chris Cundy, Daniel Filan

Figure 1 for Exploring Hierarchy-Aware Inverse Reinforcement Learning

Figure 2 for Exploring Hierarchy-Aware Inverse Reinforcement Learning

Figure 3 for Exploring Hierarchy-Aware Inverse Reinforcement Learning

Figure 4 for Exploring Hierarchy-Aware Inverse Reinforcement Learning

* 1st Workshop on Goal Specifications for Reinforcement Learning, ICML 2018, Stockholm, Sweden, 2018
* Presented at the first Workshop on Goal Specifications for Reinforcement Learning, ICML 2018, Stockholm, Sweden

Access Paper or Ask Questions

Parallelizing Linear Recurrent Neural Nets Over Sequence Length

Feb 22, 2018
Eric Martin, Chris Cundy

Figure 1 for Parallelizing Linear Recurrent Neural Nets Over Sequence Length

Figure 2 for Parallelizing Linear Recurrent Neural Nets Over Sequence Length

Figure 3 for Parallelizing Linear Recurrent Neural Nets Over Sequence Length

Figure 4 for Parallelizing Linear Recurrent Neural Nets Over Sequence Length

* 9 pages. Published as a conference paper at ICLR 2018

Access Paper or Ask Questions