ML Reading Group

In October 2021 I started a reading group among my cohort in the MSc in Advanced Computer Science at Oxford University. We read papers that highlight important activity in the field of Machine Learning, going for breadth over depth. The point is to develop a spanning view of the field so that we might have good ideas on how to change it.

List

29 October 2021

• Rubin and Berant 2021: SmBoP: Semi-autoregressive Bottom-up Semantic Parsing presented by Kyle Duffy
• Vaswani et. al. 2017: Attention Is All You Need presented by Oliver Rausch

5 November 2021

• Raffel et. al. 2019: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (usually referred to as “T5”) presented by Kyle Duffy
• Rausch Ben-Nun et. al. 2021: A Data-Centric Optimization Framework for Machine Learning presented by Oliver Rausch

12 November 2021

• Lundberg and Lee 2017: A Unified Approach to Interpreting Model Predictions (usually referred to as “SHAP”) presented by Fernando Almansa
• Lewis et. al. 2019: BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension discussed but not presented. Today the group went to a talk called Off-Belief Learning and Zero-Shot Coordination given by Jakob Foerster

19 November 2021

• Moll et. al. 2018: Quantum optimization using variational algorithms on near-term quantum devices presented by Vasilis Ntogramatzis
• Kumar and Talukdar 2020: NILE : Natural Language Inference with Faithful Natural Language Explanations presented by Wilfried Bounsi

26 November 2021

• Komeili, Shuster, and Weston 2021: Internet-Augmented Dialogue Generation presented by Kyle Duffy
• Kerenidis, Landman, Prakash 2019: Quantum Algorithms for Deep Convolutional Neural Networks presented by Snehal Raj

21 January 2022

• Lee-Thorp et. al. 2021: FNet: Mixing Tokens with Fourier Transforms presented by Kyle Duffy
• Borgeaud et. al. 2021: Improving language models by retrieving from trillions of tokens presented by Fernando Almansa

11 February 2022

• Chen et. al. 2020: A Simple Framework for Contrastive Learning of Visual Representations presented by Oliver Rausch
• Veličković et. al. 2018: Graph Attention Networks presented by Kyle Duffy

18 February 2022

• Lester, Al-Rfou, and Constant 2021: The Power of Scale for Parameter-Efficient Prompt Tuning presented by Hunar Batra
• Li et. al. 2022: Competition-Level Code Generation with AlphaCode presented by Fernando Almansa

25 February 2022

• Rezende and Mohamed 2016: Variational Inference with Normalizing Flows presented by Marcel Rød

11 March 2022

• Nye et. al. 2021: Show Your Work: Scratchpads for Intermediate Computation with Language Models presented by Hunar Batra
• Drexler 2019: Reframing Superintelligence: Comprehensive AI Services as General Intelligence presented by Oliver Rausch