
Our third and final session will have two presentations “Prediction of hospital demand from the COVID19 death curve: IHME Model” and “Molecular epidemiology of SARSCov2: what…
Creation Date
April 24th, 2020




Title: Is Deep Learning a Black Box Statistically? Abstract: Deep learning has benefited almost every aspect of modern big data applications. Yet its statistical properties still largely remain…




The information revolution is spawning systems that require very frequent decisions and provide high volumes of data concerning past outcomes. Fueling the design of algorithms used in such systems is…


Continuous optimization is a key component of modern data analysis. Recently, the demands
of extremely largescale applications have shifted the focus from high cost, high accuracy
methods to low…


Tuesday, March 25, 2014 at 4:15pm
Frank H. T. Rhodes Hall, 253
ORIE Colloquium: Rob Freund (MIT)  A FirstOrder View of Some Boosting Methods: Computational Guarantees and Connections to…


Thursday, February 6, 2014 at 4:15pm
Frank H. T. Rhodes Hall, 253
ORIE Colloquium: PoLing Loh (CalBerkeley)  Nonconvex Methods for HighDimensional Regression with Noisy and Missing Data
Noisy and…


Many operational problems in datarich environments can be characterized by three primitives: data on uncertain quantities of interest such as simultaneous demands, concurrent auxiliary data such as…


Computing reliable solutions to inverse problems is important in many applications such as biomedical imaging, computer graphics, and security. Regularization by incorporating prior knowledge is…


ORIE/Statistics Colloquium: Sahand Negahban (MIT)  Structured Estimation in HighDimensions
Wednesday, February 20, 2013 at 4:15pm
Frank H. T. Rhodes Hall, 253
Modern techniques in data accumulation…


In many markets, it is common for headquarters to create a price list while local salespeople have discretion to negotiate prices for individual deals. How much (if any) pricing discretion to grant…


Standard approaches to solving stochastic dynamic programs suffer from the curse of dimensionality. Taking advantage of structural properties such as convexity can help reduce the effect of dimension…






Abstract: In this talk, we show how to transform any optimization problem that arises from fitting a machine learning model into one that (1) detects and removes contaminated data from the…
