Tags: Essays About ReligionChina Essay Great WallGreen Business PlanUsing Second Person In A Research PaperHomework ActivitiesTransition Words And Phrases To Use In EssaysBlocking Assignment Verilog
The key idea is to construct a weighted average of control units, known as a synthetic control (SC), that minimizes imbalance of pre-treatment outcomes between the treated unit and synthetic control.Our main result is that synthetic control weights are numerically equivalent to inverse propensity score weights (IPW) with pre-treatment outcomes as covariates and heavy regularization of the propensity score model.
Second, we directly apply existing results from the literature on estimating causal effects with high-dimensional covariates.
For instance, once we view SC as an IPW estimator, it is natural to consider an Augmented IPW estimator, combining the SC weights with an outcome model.
To this end, I will present a new Bayesian-learning inspired algorithm for online allocation problems, and show that it achieves the first horizon-independent and budget-independent regret bounds for online packing with stochastic inputs.
Surprisingly, the result stems from elementary tools - LP sensitivity and basic concentration of measures.
Efficient network reachability analysis using a succinct control plane representation Seyed K.
Nikhil Devanur Thesis Sublease Assignment
Fayaz, Tushar Sharma, Ari Fogel, Ratul Mahajan, Todd Millstein, Vyas Sekar, George Varghese USENIX OSDI, 2016 RAIL: A case for redundant arrays of inexpensive links in data center networks Danyang Zhuo, Monia Ghobadi, Ratul Mahajan, Amar Phanishayee, Xuan Kelvin Zou, Hang Guan, Arvind Krishnamurthy, Thomas Anderson USENIX NSDI, 2017 Projec To R: Agile reconfigurable datacenter interconnect Monia Ghobadi, Ratul Mahajan, Amar Phanishayee, Houman Rastegarfar, Pierre-Alexandre Blanche, Madeleine Glick, Daniel Kilper, Janardhan Kulkarni, Gireeja Ranade, Nikhil Devanur ACM SIGCOMM, 2016 Elastic optical networking in the Microsoft cloud Mark Filer, Jamie Gaudette, Monia Ghobadi, Ratul Mahajan, Tom Issenhuth, Buddy Klinkers, Jeff Cox Journal of Optical Communications and Networking (JOCN), 2016 Evaluation of elastic modulation gains in Microsoft’s optical backbone in North America Monia Ghobadi, Jamie Gaudette, Ratul Mahajan, Amar Phanishayee, Buddy Klinkers, Daniel Kilper The Optical Fiber Communication Conferene and Exhibition (OFC), 2016 Consistent updates in software-defined networks: On dependencies, loop freedom, and blackholes Klaus-Tycho Forster, Ratul Mahajan, Roger Wattenhofer IFIP Networking, 2016 Selected for forwarding to the IFIP TC6 journal Open Transactions on Communication Systems Efficiently delivering online services over integrated infrastructure Hongqiang Harry Liu, Raajay Viswanathan, Matt Calder, Aditya Akella, Ratul Mahajan, Jitendra Padhye, Ming Zhang USENIX NSDI, 2016 Technical report Packet-Level telemetry in large datacenter networks Yibo Zhu, Nanxi Kang, Jiaxin Cao, Albert Greenberg, Guohan Lu, Ratul Mahajan, Dave Maltz, Lihua Yuan, Ming Zhang, Ben Y.
He got his Ph D in ECE from UT Austin, following which he was a postdoctoral researcher in the Social Algorithms Lab at Stanford, as well as a technical consultant at Lyft.
The role of the propensity score in the synthetic control method Avi Feller, UC Berkeley Abstract: The synthetic control method is a popular approach for estimating the impact of a treatment on (typically one) treated unit in settings with many control units and observed pre-treatment outcomes for all units.
Allocating Resources, in the Future Sid Banerjee, Cornell Abstract: The online allocation of scarce resources is a canonical paradigm of decision-making under uncertainty, and is widely studied in many fields of engineering under a variety of titles (dynamic allocation/revenue management/prophet inequalities/etc.).
In this talk, I will re-examine the basic online allocation problem, with the aim of building bridges to the ever-improving predictive capabilities enabled by modern machine-learning methods.