Loading Events
Find Events

Event Views Navigation

Past Events

Events List Navigation

October 2018

LIDS Seminar Series – Ayfer Ozgur Aydin

October 22, 2018 @ 4:00 pm - 5:00 pm

Ayfer Ozgur Aydin (Stanford University)


LIDS Seminar Series Speaker: Ayfer Ozgur Aydi 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 »

Algorithmic thresholds for tensor principle component analysis

October 19, 2018 @ 11:00 am - 12:00 pm

Aukosh Jagannath (Harvard University)

Abstract: Consider the problem of recovering a rank 1 tensor of order k that has been subject to Gaussian noise. The log-likelihood for this problem is highly non-convex. It is information theoretically possible to recover the tensor with a finite number of samples via maximum likelihood estimation, however, it is expected that one needs a polynomially diverging number of samples to efficiently recover it. What is the cause of this large statistical–to–algorithmic gap? To study this question, we investigate the…

Find out more »

SES PhD Admissions Webinar

October 17, 2018 @ 12:00 pm - 1:00 pm

Munther Dahleh (MIT)


Learn about admission to the Social and Engineering Systems Doctoral Program. Webinars are led by a member of the IDSS faculty, who introduces the program and answers your questions. Please register in advance.

Find out more »

Can machine learning survive the artificial intelligence revolution?

October 16, 2018 @ 4:00 pm - 5:00 pm

Francis Bach (INRIA)


Abstract: Data and algorithms are ubiquitous in all scientific, industrial and personal domains. Data now come in multiple forms (text, image, video, web, sensors, etc.), are massive, and require more and more complex processing beyond their mere indexation or the computation of simple statistics, such as recognizing objects in images or translating texts. For all of these tasks, commonly referred to as artificial intelligence (AI), significant recent progress has allowed algorithms to reach performances that were deemed unreachable a few…

Find out more »

Augmented Lagrangians and Decomposition in Convex and Nonconvex Programming

October 15, 2018 @ 4:00 pm - 5:00 pm

Terry Rockafellar (University of Washington)


LIDS Seminar Series Speaker: Terry Rockafellar Affiliation: University of Washington Abstract: Multiplier methods based on augmented Lagrangians are attractive in convex and nonconvex programming for their stabilizing and even convexifying properties. They have widely been seen, however, as incompatible with taking advantage of a block-separable structure. In fact, when articulated in the right way, they can produce decomposition algorithms in which low-dimensional subproblems can be solved in parallel. Convergence in the nonconvex case is, of course, just local, but is…

Find out more »

Data Science and Big Data Analytics: Making Data-Driven Decisions

October 15, 2018

Developed by 10 MIT faculty members at IDSS, this seven-week course is specially designed for data scientists, business analysts, engineers and technical managers looking to learn strategies to harness data. Offered by MIT xPRO. Course begins Oct 15, 2018.

Find out more »

Locally private estimation, learning, inference, and optimality

October 12, 2018 @ 11:00 am - 12:00 pm

John Duchi (Stanford University)

Abstract: In this talk, we investigate statistical learning and estimation under local privacy constraints, where data providers do not trust the collector of the data and so privatize their data before it is even collected. We identify fundamental tradeoffs between statistical utility and privacy in such local models of privacy, providing instance-specific bounds for private estimation and learning problems by developing local minimax risks. In contrast to approaches based on worst-case (minimax) error, which are conservative, this allows us to…

Find out more »

Local Geometric Analysis and Applications

October 11, 2018 @ 4:00 pm - 5:00 pm

Lizhong Zheng (MIT)


Abstract: Local geometric analysis is a method to define a coordinate system in a small neighborhood in the space of distributions over a given alphabet. It is a powerful technique since the notions of distance, projection, and inner product defined this way are useful in the optimization problems involving distributions, such as regressions. It has been used in many places in the literature such as correlation analysis, correspondence analysis. In this talk, we will go through some of the basic…

Find out more »

HUBweek Policy Hackathon

October 8, 2018 @ 9:30 am - 4:30 pm

Tackle challenges on the future of cities, future of health, and future of work! For this IDSS student-run hackathon, teams will propose creative policy solutions to societal challenges using a combination of robust data analytics and domain knowledge. This event is a part of HUBweek, a leading ideas festival founded by institutions from the greater Boston area (including MIT).

Find out more »

Efficient Algorithms for the Graph Matching Problem in Correlated Random Graphs

October 5, 2018 @ 11:00 am - 12:00 pm

Tselil Schramm (Harvard University)

Abstract: The Graph Matching problem is a robust version of the Graph Isomorphism problem: given two not-necessarily-isomorphic graphs, the goal is to find a permutation of the vertices which maximizes the number of common edges. We study a popular average-case variant; we deviate from the common heuristic strategy and give the first quasi-polynomial time algorithm, where previously only sub-exponential time algorithms were known. Based on joint work with Boaz Barak, Chi-Ning Chou, Zhixian Lei, and Yueqi Sheng. Biography: Tselil Schramm…

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