LIDS Seminar Series

The LIDS seminar series serves as a focal point in the intellectual life of the lab.

February 19, 2019

Safeguarding Privacy in Dynamic Decision-Making Problems

Kuang Xu (Stanford University)

The increasing ubiquity of large-scale infrastructures for surveillance and data analysis has made understanding the impact of privacy a pressing priority in many domains. We propose a framework for studying a fundamental cost vs. privacy tradeoff...

February 26, 2019

Coded Computing: A Transformative Framework for Resilient, Secure, and Private Distributed Learning

Salman Avestimehr (University of Southern California)

This talk introduces "Coded Computing”, a new framework that brings concepts and tools from information theory and coding into distributed computing to mitigate several performance bottlenecks that arise in large-scale distributed computing and...

March 12, 2019

Automatic Computation of Exact Worst-Case Performance for First-Order Methods

Julien Hendrickx (UCLouvain)

Joint work with Adrien Taylor (INRIA) and Francois Glineur (UCLouvain). We show that the exact worst-case performances of a wide class of first-order convex optimization algorithms can be obtained as solutions to semi-definite programs, which...

April 9, 2019

Personalized Dynamic Pricing with Machine Learning: High Dimensional Covariates and Heterogeneous Elasticity

Gah-Yi Ban (London Business School)

We consider a seller who can dynamically adjust the price of a product at the individual customer level, by utilizing information about customers’ characteristics encoded as a $d$-dimensional feature vector. We assume a personalized demand model,...

April 23, 2019

Memory-Efficient Adaptive Optimization for Humungous-Scale Learning

Yoram Singer (Princeton University & Google)

Adaptive gradient-based optimizers such as AdaGrad and Adam are among the methods of choice in modern machine learning. These methods maintain second-order statistics of each model parameter, thus doubling the memory footprint of the optimizer. In...

April 30, 2019

On Coupling Methods for Nonlinear Filtering and Smoothing

Youssef Marzouk (MIT)

Bayesian inference for non-Gaussian state-space models is a ubiquitous problem with applications ranging from geophysical data assimilation to mathematical finance. We will discuss how deterministic couplings between probability distributions enable...

May 14, 2019

Learning Engines for Healthcare: Using Machine Learning to Transform Clinical Practice and Discovery

Mihaela van der Schaar (University of Cambridge)

The overarching goal of my research is to develop cutting-edge machine learning, AI and operations research theory, methods, algorithms, and systems to understand the basis of health and disease; develop methodology to catalyze clinical research;...