Loading Events
Find Events

Event Views Navigation

Past Events › LIDS Seminar Series

Distinguished speakers provide an overview and discuss recent progress in research areas spanning communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing. Intended for a broad audience.

Events List Navigation

April 2019

Memory-Efficient Adaptive Optimization for Humungous-Scale Learning

April 23, 2019 @ 4:00 pm - 5:00 pm

Yoram Singer (Google)

32-G449 (KIva/Patel)

Title Talk: LIDS Seminar Speaker: Yoram Singer Affiliation: Princeton University & Google Abstract: 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 behemoth-size applications, this memory overhead restricts the size of the model being used as well as the number of examples in a mini-batch. We describe a novel, simple, and flexible adaptive…

Find out more »

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

April 9, 2019 @ 4:00 pm - 5:00 pm

Gah-Yi Ban (London Business School)

32-155

Title Talk: LIDS Seminar Speaker: Gah-Yi Ban Affiliation: London Business School Abstract: 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, parameters of which depend on $s$ out of the $d$ features. The seller initially does not know the relationship between the customer features and the product demand, but learns this through sales…

Find out more »
March 2019

*CANCELED* LIDS Seminar Series – Marija Ilic

March 19, 2019 @ 4:00 pm - 5:00 pm

Marija Ilic (MIT)

32-155

Title Talk: TBD Speaker: Marija Ilic Affiliation: MIT Abstract: TBD Bio: TBD ____________________________________ The LIDS Seminar Series features distinguished speakers who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing. 

Find out more »

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

March 12, 2019 @ 4:00 pm - 5:00 pm

Julien Hendrickx (UCLouvain)

32-155

Title Talk: Automatic Computation of Exact Worst-Case Performance for First-Order Methods Speaker: Julien Hendrickx Affiliation: UCLouvain Abstract: 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 provide both the performance bounds and functions on which these are reached.  Our formulation is based on a necessary and sufficient condition for smooth (strongly) convex interpolation, allowing…

Find out more »
February 2019

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

February 26, 2019 @ 4:00 pm - 5:00 pm

Salman Avestimehr (University of Southern California)

32-155

Title Talk: Coded Computing: A Transformative Framework for Resilient, Secure, and Private Distributed Learning Speaker: Salman Avestimehr Affiliation: University of Southern California Abstract: 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 machine learning, such as resiliency to stragglers and bandwidth bottleneck. Furthermore, coded computing can enable (information-theoretically) secure and private learning over untrusted workers that…

Find out more »

Safeguarding Privacy in Dynamic Decision-Making Problems

February 19, 2019 @ 4:00 pm - 5:00 pm

Kuang Xu (Stanford University)

32-155

Title Talk: Safeguarding Privacy in Dynamic Decision-Making Problems Speaker: Kuang Xu Affiliation: Stanford University Abstract: 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 in dynamic decision-making problems. The central question is: how can a decision maker take actions that are efficient for her goal, while simultaneously ensuring these actions do not inadvertently…

Find out more »
December 2018

Naomi E. Leonard

December 10, 2018 @ 4:00 pm - 5:00 pm

Naomi E. Leonard (Princeton University)

32-155

Title Talk: Symmetry, Bifurcation, and Multi-Agent Decision-Making Speaker: Naomi E. Leonard Affiliation: Princeton University Abstract: Prof. Leonard will present nonlinear dynamics for distributed decision-making that derive from principles of symmetry and bifurcation. Inspired by studies of animal groups, including house-hunting honeybees and schooling fish, the nonlinear dynamics describe a group of interacting agents that can manage flexibility as well as stability in response to a changing environment. Bio: Prof. Naomi Ehrich Leonard is Edwin S. Wilsey Professor of Mechanical and…

Find out more »
November 2018

Saurabh Amin

November 26, 2018 @ 4:00 pm - 5:00 pm

Saurabh Amin (MIT)

32-155

LIDS Seminar Series Speaker: Saurabh Amin Affiliation: MIT ____________________________________ The LIDS Seminar Series features distinguished speakers who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing. 

Find out more »

Benjamin Hobbs

November 19, 2018 @ 4:00 pm - 5:00 pm

Benjamin Hobbs (Johns Hopkins University)

32-155

Title Talk: Modeling Electricity Markets with Complementarity: Why It's Important (and Fun) Speaker: Benjamin Hobbs Affiliation: Johns Hopkins University Abstract: Electric power: done wrong, it drags the economy and environment down; done right, it could help to create a more efficient, brighter, and cleaner future. Better policy, planning, and operations models--both simple analytical, and complex computational ones--are essential if we're going to do it right. Better modeling is also fun, as the math of electricity models is inherently interesting and revealing…

Find out more »

Abbas El Gamal

November 13, 2018 @ 8:00 am - 5:00 pm

Abbas El Gamal (Stanford University)

32-141

LIDS Seminar Series Speaker: Abbas El Gamal Affiliation: Stanford University ____________________________________ The LIDS Seminar Series features distinguished speakers who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing. 

Find out more »
+ Export Events

© MIT Institute for Data, Systems, and Society | 77 Massachusetts Avenue | Cambridge, MA 02139-4307 | 617-253-1764 | Design by Opus