Prof. Anima Anandkumar

#PeerReview quality gets worse with each upcoming #AI conference. Our #ICLR2020 reviews has extreme swings (8s and 1s). Reviewers giving low scores are nasty and bitter. Its like they are out on a war and want to destroy competition. Not healthy. What are the alternatives?

I have serious concerns on emotional health of young people submitting to these #AI conferences. It has huge impact on them. We don't spend enough time thinking about it. I have thought about just posting on @arXiv_Daily and let community decide if this is useful to them.

I ask students and new authors of #ICLR2020 to not take reviews to heart. If you believe in your work, you have to keep fighting for it. Try to read objectively and decide which comments are constructive. Don't let reviewers determine your self worth. You deserve to be here!

In current #PeerReview system #ICLR2020 negative reviewers write long statements making every attempt to destroy it. Often wrong and claiming to be experts. Positive reviewers write a few sentences like "good contribution, relevant.." Often they don't claim to be experts

Self-evaluation of expertise in #PeerReview #ICLR2020 is bizarre. Clueless people claim to be experts (often of privileged class). Humble people don't want to do that. I have seen as AC, professors who rank themselves in the middle and undergrads rank themselves as experts.