Metaresearch

How blockers can turn into a paper: A retrospective on 'Towards The Systematic Reporting of the Energy and Carbon Footprints of Machine Learning'

Talk based on the paper, 'Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning' which was written with co-authors: Jieru Hu, Joshua Romoff, Emma Brunskill, Dan Jurafsky, and Joelle Pineau. I reflect on the journey …

Distilling Information from a Flood: A Possibility for the Use of Meta-Analysis and Systematic Review in Machine Learning Research

Talk based on paper with co-authors: Emma Brunskill. The current flood of information in all areas of machine learning research, from computer vision to reinforcement learning, has made it difficult to make aggregate scientific inferences. It can be …

Ethical Challenges in Data-Driven Dialogue Systems

Talk based on work with co-authors: Koustuv Sinha, Nicolas Angelard-Gontier, Nan Rosemary Ke, Genevieve Fried, Ryan Lowe, Joelle Pineau. The use of dialogue systems as a medium for human-machine interaction is an increasingly prevalent paradigm. A …

Benchmarking and Evaluation in Inverse Reinforcement Learning

Benchmarks are particularly useful for characterizing algorithms and determining their usefulness in different settings. Here I highlight the need for more standardization of performance evaluations in inverse reinforcement learning.

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning Methods)

In recent years, significant progress has been made in solving challenging problems using deep learning. Reproducing existing work and accurately judging the improvements offered by novel methods is vital to sustaining this progress. Unfortunately, …

Show Me the Data! On the Reproducibility of Policy Gradient Methods for Continuous Control

Talk based on work with co-authors: Riashat Islam, Maziar Gomrokchi and Doina Precup. A brief discussion on some difficulties that students may encounter in reproducing modern policy gradient methods in continuous control tasks and best practices …