Any fundamental discovery involves a significant degree of risk. If an idea is guaranteed to work then it moves from the realm of research to engineering. Unfortunately, this also means that most…
- Aug. 19 – Aug. 28, 2020
- Nike Sun (Massachusetts Institute of Technology; chair), Jian Ding (University of Pennsylvania), Ronen Eldan (Weizmann Institute), Elchanan Mossel (Massachusetts Institute of Technology), Joe Neeman (University of Texas at Austin), Jelani Nelson (UC Berkeley), Tselil Schramm (Stanford University; Microsoft Research Fellow)
Every minute, South Korea's household debt rises by US$90 thousand dollars. Every 12 minutes, a Korean is declared bankrupt. Ordinary households now owe some...
Have you ever wondered how will the machine learning frameworks of the '20s look like? In this essay, I examine the directions AI research might take and the requirements they impose on the tools at our disposal, concluding with an overview of what I believe to be the two strong candidates: `JAX` and `S4TF`.
This page contains list of mathematical Theorems which are at the same time (a) great, (b) easy to understand, and (c) published in the 21st century. See here for more details about these criteria. Click on any theorem to see the exact formulation, or click here for the formulations of all theorems. You can also…
- Aug. 31 – Sep. 4, 2020
- Csaba Szepesvari (University of Alberta, Google DeepMind; chair), Emma Brunskill (Stanford University), Sébastien Bubeck (MSR), Alan Malek (DeepMind), Sean Meyn (University of Florida), Ambuj Tewari (University of Michigan), Mengdi Wang (Princeton)
This program aims to reunite researchers across disciplines that have played a role in developing the theory of reinforcement learning. It will review past developments and identify promising directions of research, with an emphasis on addressing existing open problems, ranging from the design of efficient, scalable algorithms for exploration to how to control learning and planning. It also aims to deepen the understanding of model-free vs. model-based learning and control, and the design of efficient methods to exploit structure and adapt to easier environments.
Let’s imagine a hypothetical situation. There’s an infection going round, and we want to predict the future severity of someone’s illness. There is a test that offers a good prediction. Let’s say the outcome of the test has a correlation of 0.78 with the patient's severity of infection. The problem with the test is that…
H. Chawla, M. Jukola, T. Brouns, E. Arani, и B. Zonooz. (2020)cite arxiv:2007.12918Comment: Accepted at 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
M. Lindvall, и J. Molin. (2020)cite arxiv:2001.07455Comment: Accepted for presentation in poster format for the ACM CHI'19 Workshop <Emerging Perspectives in Human-Centered Machine Learning>.
Q. Qu, Z. Zhu, X. Li, M. Tsakiris, J. Wright, и R. Vidal. (2020)cite arxiv:2001.06970Comment: QQ and ZZ contributed equally to the work. Invited review paper for IEEE Signal Processing Magazine Special Issue on non-convex optimization for signal processing and machine learning. This article contains 26 pages with 11 figures.
M. Cook, A. Zare, и P. Gader. (2020)cite arxiv:2007.01263Comment: 6 pages, 4 figures, Presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning.
R. Hanocka, G. Metzer, R. Giryes, и D. Cohen-Or. (2020)cite arxiv:2005.11084Comment: SIGGRAPH 2020; Project page: https://ranahanocka.github.io/point2mesh/.
H. Tajima, и F. Fujisawa. (2020)cite arxiv:2007.00926Comment: 6 pages, 5 figures, accepted by Scientific and Educational Reports of the Faculty of Science and Technology, Kochi University.