Kartic Subr |
Thu 20 May 2021, 13:00 - 14:00 |
Online (Blackboard collaborate) |
If you have a question about this talk, please contact: Jodie Cameron (jcamero9)
Title: Taming Timely Inverses
Abstract: Last year, at the IPAB seminar, I spoke about the importance of timely (rapid) approximations of physical simulations. Currently, I am excited about developing rapid approximations for inverse problems involving physical simulation. Despite troves of methods for solving inverse problems, sparingly few consider timeliness as a measure of error. In many real-time applications, obtaining an accurate or precise answer is only useful if it can be estimated within a narrow temporal window. Conversely, rapid estimates are indeed less useful if they are not accompanied by analyses of popular error criteria such as accuracy and precision. In my talk this week, I will present a couple of recent works [1,2] that are early steps in this direction. In addition, I will also briefly discuss other recent work [3,4,5].
[1] Q-NET: A Network for Low-Dimensional Integrals of Neural Proxies
Kartic Subr
https://arxiv.org/pdf/2006.14396
[2] IV-Posterior: Inverse Value Estimation for Interpretable Policy Certificates
Tatiana Lopez-Guevara, Michael Burke, Nicholas K. Taylor, Kartic Subr
https://arxiv.org/pdf/2012.01925
[3] Action sequencing using visual permutations
Michael Burke, Kartic Subr, Subramanian Ramamoorthy
https://arxiv.org/pdf/2008.01156
[4] Jittering Samples using a kd-Tree Stratification
Alexandros D. Keros, Divakaran Divakaran, Kartic Subr
https://arxiv.org/pdf/2002.07002
[5] On Improved Training of CNNs for Acoustic Localisation
Elizabeth Vargas, James Hopgood, Keith Brown, Kartic Subr
https://homepages.inf.ed.ac.uk/ksubr/Files/Papers/TASLP21.pdf