Upcoming Seminars

No upcoming events found.

Previous Seminars

Optimizing for Fairness in ML

Thu, Nov 7, 2019, 4:30 pm
Recent events have made evident the fact that algorithms can be discriminatory, reinforce human prejudices, accelerate the spread of misinformation, and are generally not as objective as they are widely thought to be.

Word Embeddings: What works, what doesn’t, and how to tell the difference for applied research

Fri, Oct 25, 2019, 12:00 pm
We consider the properties and performance of word embeddings techniques in the context of political science research. In particular, we explore key parameter choices—including context window length, embedding vector dimensions and the use of pre-trained vs locally fit variants—with respect to efficiency and quality of inferences possible with...

Meisam Razaviyayn

Thu, Oct 17, 2019, 4:30 pm
Recent applications that arise in machine learning have surged significant interest in solving min-max saddle point games. This problem has been extensively studied in the convex-concave regime for which a global equilibrium solution can be computed efficiently. In this talk, we study the problem in the non-convex regime and show that an $\epsilon...

Deep Neural Networks for Estimation and Inference: Application to Causal Effects and Other Semiparametric Estimands

Mon, Oct 14, 2019, 12:30 pm
We study deep neural networks and their use in semiparametric inference. We prove valid inference after first-step estimation with deep learning, a result new to the literature. We provide new rates of convergence for deep feedforward neural nets and, because our rates are sufficiently fast (in some cases minimax optimal), obtain valid...

Control with Learning On the Fly: First Toy Problems

Thu, Oct 10, 2019, 4:30 pm
How can we control a system without knowing beforehand what the controls do? In particular, how should we balance the imperatives to "explore" (learn what the controls do) and "exploit" (use what we've learned so far to make the system do what we want)? We won't have enough data to apply deep learning. The talk poses several toy problems and...

Provable Reinforcement Learning From Small Data

Fri, Oct 4, 2019, 4:30 pm
Recent years have witnessed increasing empirical successes in reinforcement learning (RL). However, many theoretical questions about RL were not well understood. For example, how many observations are necessary and sufficient for learning a good policy? How to learn to control using structural information with provable regret? In this talk, we...

Beyond Supervised Learning for Biomedical Imaging

Wed, Oct 2, 2019, 4:30 pm
Many biomedical imaging tasks, such as 3D reconstruction, denoising, detection, registration, and segmentation, are ill-posed inverse problems. In this talk, I will present a flexible machine learning-based framework that has allowed us to derive efficient solutions for a variety of such problems, without relying on heavy supervision. I will...

Prediction with Confidence – General Framework for Predictive Inference

Fri, Sep 27, 2019, 12:00 pm
We propose a general framework for prediction in which a prediction is in the form of a distribution function, called ‘predictive distribution function’. This predictive distribution function is well suited for prescribing the notion of confidence under the frequentist interpretation and  providing meaningful answers for prediction-related...

Multiscale Model Reduction in Physics with Deep Networks

Mon, May 13, 2019, 4:15 pm
Approximating high-dimensional functionals with low-dimensional models is a central issue of machine learning and physics. This talk shows deep convolutional neural network architectures take advantage of scale separation, symmetries and sparse representations. We introduce simplified architectures which can be analyzed mathematically. Scale...

Inherent Trade-Offs in Algorithmic Fairness

Fri, Mar 29, 2019, 12:00 pm to 1:00 pm
Recent discussion in the public sphere about classification by algorithms has involved tension between competing notions of what it means for such a classification to be fair to different groups. We consider several of the key fairness conditions that lie at the heart of these debates, and discuss recent research establishing inherent trade-offs...