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 13, 2019.
Over the next decade, the biggest generator of data is expected to be devices which sense and control the physical world. This explosion of real-time data that is emerging from the physical world requires a rapprochement of areas such as machine learning, control theory, and optimization. While control theory has been firmly rooted in tradition of model-based design, the availability and scale of data (both temporal and spatial) will require rethinking of the foundations of our discipline. From a machine…
Abstract: We first study the rate of convergence for learning distributions with the adversarial framework and Generative Adversarial Networks (GANs), which subsumes Wasserstein, Sobolev, and MMD GANs as special cases. We study a wide range of parametric and nonparametric target distributions, under a collection of objective evaluation metrics. On the nonparametric end, we investigate the minimax optimal rates and fundamental difficulty of the implicit density estimation under the adversarial framework. On the parametric end, we establish a theory for general…
IDS.190 - Topics in Bayesian Modeling and Computation Abstract: Many algorithms take prohibitively long to run on modern, large datasets. But even in complex data sets, many data points may be at least partially redundant for some task of interest. So one might instead construct and use a weighted subset of the data (called a "coreset") that is much smaller than the original dataset. Typically running algorithms on a much smaller data set will take much less computing time, but…
IDS.190 - Topics in Bayesian Modeling and Computation Speaker: Brian Patton (Google AI) Abstract: TensorFlow Probability provides a toolkit to enable researchers and practitioners to integrate uncertainty with gradient-based deep learning on modern accelerators. In this talk we'll walk through some practical problems addressed using TFP; discuss the high-level interfaces, goals, and principles of the library; and touch on some recent innovations in describing probabilistic graphical models. Time-permitting, we may touch on a couple areas of research interest for the…
Abstract: The problem of transfer and domain adaptation is ubiquitous in machine learning and concerns situations where predictive technologies, trained on a given source dataset, have to be transferred to a new target domain that is somewhat related. For example, transferring voice recognition trained on American English accents to apply to Scottish accents, with minimal retraining. A first challenge is to understand how to properly model the ‘distance’ between source and target domains, viewed as probability distributions over a feature…
Abstract: What are the most expressive classes of neural networks that can be learned, provably, in polynomial-time in a distribution-free setting? In this talk we give the first efficient algorithm for learning neural networks with two nonlinear layers using tools for solving isotonic regression, a nonconvex (but tractable) optimization problem. If we further assume the distribution is symmetric, we obtain the first efficient algorithm for recovering the parameters of a one-layer convolutional network. These results implicitly make use of a…
The seven-week course launches September 30, 2019. This course was developed by over ten MIT faculty members at IDSS. It is specially designed for data scientists, business analysts, engineers, and technical managers looking to learn the latest theories and strategies to harness data.
IDS.190 Topics in Bayesian Modeling and Computation *Note: The speaker this week will give two shorter talks within the usual session Title: Behavior of the Gibbs sampler in the imbalanced case Abstract: Many modern applications collect highly imbalanced categorical data, with some categories relatively rare. Bayesian hierarchical models combat data sparsity by borrowing information, while also quantifying uncertainty. However, posterior computation presents a fundamental barrier to routine use; a single class of algorithms does not work well in all settings and…
IDS.190 – Topics in Bayesian Modeling and Computation Abstract: Probabilistic programming is an emerging field at the intersection of programming languages, probability theory, and artificial intelligence. This talk will show how to use recently developed probabilistic programming languages to build systems for robust 3D computer vision, without requiring any labeled training data; for automatic modeling of complex real-world time series; and for machine-assisted analysis of experimental data that is too small and/or messy for standard approaches from machine learning and…
