Thoughts on reviewing

During ICML reviews I noticed that my personal take on reviewing is becoming increasingly distinct from my peers. Personally, I want to go to a conference and come away with renewed creativity and productivity. Thus, I like works that are thought provoking, groundbreaking, or particularly innovative; even if the execution is a bit off.

Read Full Story

ICML 2016 Thoughts

ICML is too big for me to “review” it per se, but I can provide a myopic perspective.The heavy hitting topics were Deep Learning, Reinforcement Learning, and Optimization; but there was a heavy tail of topics receiving attention. It felt like deep learning was less dominant this year; but the success of deep learning has led to multiple application specific alternative venues (e.g.

Read Full Story

ICML 2017 Workshop on Implicit Models

David Blei,
Ian Goodfellow,
Balaji Lakshminarayanan,
Shakir Mohamed,
Rajesh Ranganath,
and I are organizing a workshop at ICML this year, titled
“Implicit Models”.
Workshop URL: https://sites.google.com/view/implicitmodels/
Leveraging this recent and highly impactful topic, I’m personally
excited to see how we might foster discussion across communities.

Read Full Story

ICML 2017 Thoughts

ICML 2017 has just ended. While Sydney is remote for those in Europe and North America, the conference centeris a wonderful venue (with good coffee!), and the city is a lot of fun. Everything went smoothly and the organizers did a great job.You can get a list of papers that I liked from my Twitter feed, so instead I’d like to discuss some broad themes I sensed.

Read Full Story

A Divergence Bound For Hybrids of MCMC and Variational Inference and …

At ICML I recently published a paper that I somehow decided to title “A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI”. This paper gives one framework for building “hybrid” algorithms between Markov chain Monte Carlo (MCMC) and Variational inference (VI) algorithms.

Read Full Story

Code submission should be encouraged but not compulsory

ICML, ICLR, and NeurIPS are all considering or experimenting with code and data submission as a part of the reviewer or publication process with the hypothesis that it aids reproducibility of results. Reproducibility has been a rising concern with discussions in paper, workshop, and invited talk.
The fundamental driver is of course lack of reproducibility.

Read Full Story