Loading Events
Find Events

Event Views Navigation

Past Events › Stochastics and Statistics Seminar Series

Events List Navigation

December 2017

Stochastics and Statistics Seminar: Challenges in Developing Learning Algorithms to Personalize Treatment in Real Time

December 1, 2017 @ 11:00 am - 12:00 pm

Susan Murphy (Harvard)

MIT Building E18, Room 304

Abstract:  A formidable challenge in designing sequential treatments is to  determine when and in which context it is best to deliver treatments.  Consider treatment for individuals struggling with chronic health conditions.  Operationally designing the sequential treatments involves the construction of decision rules that input current context of an individual and output a recommended treatment.   That is, the treatment is adapted to the individual’s context; the context may include  current health status, current level of social support and current level of…

Find out more »
November 2017

Stochastics and Statistics Seminar: Generative Models and Compressed Sensing

November 17, 2017 @ 11:00 am - 12:00 pm

Alex Dimakis (University of Texas at Austuin)

MIT Building E18, Room 304

Abstract:  The goal of compressed sensing is to estimate a vector from an under-determined system of noisy linear measurements, by making use of prior knowledge in the relevant domain. For most results in the literature, the structure is represented by sparsity in a well-chosen basis. We show how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all. Instead, we assume that the unknown vectors lie near the range of a generative model, e.g. a GAN…

Find out more »

Statistics, Computation and Learning with Graph Neural Networks

November 3, 2017 @ 11:00 am - 12:00 pm

Joan Bruna Estrach (NYU)

Abstract: Deep Learning, thanks mostly to Convolutional architectures, has recently transformed computer vision and speech recognition. Their ability to encode geometric stability priors, while offering enough expressive power, is at the core of their success. In such settings, geometric stability is expressed in terms of local deformations, and it is enforced thanks to localized convolutional operators that separate the estimation into scales. Many problems across applied sciences, from particle physics to recommender systems, are formulated in terms of signals defined…

Find out more »

Unbiased Markov chain Monte Carlo with couplings

November 1, 2017 @ 11:00 am - 12:00 pm

Pierre Jacob (Harvard)

MIT Building E18, Room 304

Abstract: Markov chain Monte Carlo methods provide consistent approximations of integrals as the number of iterations goes to infinity. However, these estimators are generally biased after any fixed number of iterations, which complicates both parallel computation. In this talk I will explain how to remove this burn-in  bias by using couplings of Markov chains and a telescopic sum argument, inspired by Glynn & Rhee (2014). The resulting unbiased estimators can be computed independently in parallel, and averaged. I will present coupling…

Find out more »
October 2017

Stochastics and Statistics Seminar – Amit Daniely (Google)

October 27, 2017 @ 11:00 am - 12:00 pm

MIT Building E18, Room 304

Abstract:  Can learning theory, as we know it today, form a theoretical basis for neural networks. I will try to discuss this question in light of two new results — one positive and one negative. Based on joint work with Roy Frostig, Vineet Gupta and Yoram Singer, and with Vitaly Feldman Biography: Amit Daniely is an Assistant Professor at the Hebrew University in Jerusalem, and a research scientist at Google Research, Tel-Aviv. Prior to that, he was a research scientist at Google Research,…

Find out more »

Inference in dynamical systems and the geometry of learning group actions – Sayan Mukherjee (Duke)

October 20, 2017 @ 11:00 am - 12:00 pm

MIT Building E18, Room 304

Inference in dynamical systems and the geometry of learning group actions – Sayan Mukherjee (Duke)

Find out more »

Special Stochastics and Statistics Seminar – John Cunningham (Columbia)

October 19, 2017 @ 4:30 pm - 5:30 pm

MIT Building E18, Room 304

Find out more »

Additivity of Information in Deep Generative Network: The I-MMSE Transform Method – Galen Reeves (Duke University)

October 13, 2017 @ 11:00 am - 12:00 pm

MIT Building E18, Room 304

Find out more »

Transport maps for Bayesian computation – Youssef Marzouk (MIT)

October 6, 2017 @ 11:00 am - 12:00 pm

MIT Building E18, Room 304

Find out more »
September 2017

New Provable Techniques for Learning and Inference in Probabilistic Graphical Models

September 8, 2017 @ 11:00 am - 12:00 pm

MIT Building E18, Room 304

Speaker: Andrej Risteski (Princeton University) A common theme in machine learning is succinct modeling of distributions over large domains. Probabilistic graphical models are one of the most expressive frameworks for doing this. The two major tasks involving graphical models are learning and inference. Learning is the task of calculating the “best fit” model parameters from raw data, while inference is the task of answering probabilistic queries for a model with known parameters (e.g. what is the marginal distribution of a…

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