Loading Events

Past Events

Events Search and Views Navigation

Event Views Navigation

April 2020

On Using Graph Distances to Estimate Euclidean and Related Distances

Ery Arias-Castro (University of California, San Diego)

April 17 @ 11:00 am - 12:00 pm

Abstract:  Graph distances have proven quite useful in machine learning/statistics, particularly in the estimation of Euclidean or geodesic distances. The talk will include a partial review of the literature, and then present more recent developments on the estimation of curvature-constrained distances on a surface, as well as on the estimation of Euclidean distances based on an unweighted and noisy neighborhood graph. - About the Speaker:  Ery Arias-Castro received his Ph.D. in Statistics from Stanford University in 2004. He then took…

Find out more »

How to Trap a Gradient Flow

Sébastien Bubeck (Microsoft Research)

April 24 @ 11:00 am - 12:00 pm

Abstract: In 1993, Stephen A. Vavasis proved that in any finite dimension, there exists a faster method than gradient descent to find stationary points of smooth non-convex functions. In dimension 2 he proved that 1/eps gradient queries are enough, and that 1/sqrt(eps) queries are necessary. We close this gap by providing an algorithm based on a new local-to-global phenomenon for smooth non-convex functions. Some higher dimensional results will also be discussed. I will also present an extension of the 1/sqrt(eps)…

Find out more »

May 2020

Naive Feature Selection: Sparsity in Naive Bayes

Alexandre d'Aspremont (ENS, CNRS)

May 1 @ 11:00 am - 12:00 pm

Abstract: Due to its linear complexity, naive Bayes classification remains an attractive supervised learning method, especially in very large-scale settings. We propose a sparse version of naive Bayes, which can be used for feature selection. This leads to a combinatorial maximum-likelihood problem, for which we provide an exact solution in the case of binary data, or a bound in the multinomial case. We prove that our bound becomes tight as the marginal contribution of additional features decreases. Both binary and…

Find out more »

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

May 4

Developed by 11 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 May 4, 2020.

Find out more »

The Ethical Algorithm

Michael Kearns (University of Pennsylvania)

May 19 @ 4:00 pm - 5:00 pm

Title: The Ethical Algorithm Abstract: Many recent mainstream media articles and popular books have raised alarms over anti-social algorithmic behavior, especially regarding machine learning and artificial intelligence. The concerns include leaks of sensitive personal data by predictive models, algorithmic discrimination as a side-effect of machine learning, and inscrutable decisions made by complex models. While standard and legitimate responses to these phenomena include calls for stronger and better laws and regulations, researchers in machine learning, statistics and related areas are also…

Find out more »

August 2020

SES & IDPS Dissertation Defense – Rui Sun

Rui Sun

August 19 @ 1:00 pm - 3:00 pm

Online Learning and Optimization in Operations Management ABSTRACT We study in this thesis online learning and optimization problems in operations management where we need to make decisions in the face of incomplete information and operational constraints in a dynamic environment. We first consider an online matching problem where a central platform needs to match a number of limited resources to different groups of users that arrive sequentially over time. The platform does not know the reward of each matching option…

Find out more »

September 2020

Stein’s method for multivariate continuous distributions and applications

Gesine Reinert, University of Oxford

September 11 @ 11:00 am - 12:00 pm

Abstract: Stein’s method is a key method for assessing distributional distance, mainly for one-dimensional distributions. In this talk we provide a general approach to Stein’s method for multivariate continuous distributions. Among the applications we consider is the Wasserstein distance between two continuous probability distributions under the assumption of existence of a Poincare constant. This is joint work with Guillaume Mijoule (INRIA Paris) and Yvik Swan (Liege). - Bio: Gesine Reinert is a Research Professor of the Department of Statistics and…

Find out more »

Causal Inference and Overparameterized Autoencoders in the Light of Drug Repurposing for SARS-CoV-2

Caroline Uhler, MIT

September 18 @ 11:00 am - 12:00 pm

Abstract:  Massive data collection holds the promise of a better understanding of complex phenomena and ultimately, of better decisions. An exciting opportunity in this regard stems from the growing availability of perturbation / intervention data (drugs, knockouts, overexpression, etc.) in biology. In order to obtain mechanistic insights from such data, a major challenge is the development of a framework that integrates observational and interventional data and allows predicting the effect of yet unseen interventions or transporting the effect of interventions…

Find out more »

Webinar: Inside the MITx MicroMasters Program in Statistics and Data Science

September 23 @ 11:00 am - 12:00 pm

Ready to start your data science journey? To help train for this in-demand field, IDSS has created the MITx MicroMasters® Program in Statistics and Data Science. In this 60-minute engaging and interactive webinar, you will: Learn more about the courses in the program. Find out how these courses could bring you to MIT or other universities around the world for a graduate program. Hear about the exclusive benefits for learners who upgrade to the MicroMasters Program track. Get real-time answers to your questions.…

Find out more »

Separating Estimation from Decision Making in Contextual Bandits

Dylan Foster, MIT

September 25 @ 11:00 am - 12:00 pm

Abstract: The contextual bandit is a sequential decision making problem in which a learner repeatedly selects an action (e.g., a news article to display) in response to a context (e.g., a user’s profile) and receives a reward, but only for the action they selected. Beyond the classic explore-exploit tradeoff, a fundamental challenge in contextual bandits is to develop algorithms that can leverage flexible function approximation to model similarity between contexts, yet have computational requirements comparable to classical supervised learning tasks…

Find out more »
+ Export Events