Abstract:

# Upcoming Events

### Convergence Rates of Stochastic Algorithms in Nonsmooth Nonconvex Optimization

Thu, Nov 14, 2019, 4:30 pm

Location:
B205 Engineering Quadrangle

Speaker(s):

Dmitriy Drusvyatskiy

University of Washington

Convergence Rates of Stochastic Algorithms in Nonsmooth Nonconvex Optimization

Tags:
Seminars

### Can learning theory resist deep learning?

### Diving into TensorFlow 2.0

Fri, Nov 15, 2019, 2:00 pm

Description: Please join us for this 90-minute workshop, taught at an intermediate level. We will briefly introduce TensorFlow 2.0, then dive in to writing a few flavors of neural networks. Attendees will need a laptop and an internet connection.

Location:
Lewis Science Library 138

Speaker(s):

Josh Gordon

Google

Diving in to TensorFlow 2.0

Tags:
Seminars

### Recent Advances in Non-Convex Distributed Optimization and Learning

Mon, Nov 18, 2019, 4:30 pm

We consider a class of distributed non-convex optimization problems, in which a number of agents are connected by a communication network, and they collectively optimize a sum of (possibly non-convex and non-smooth) local objective functions. This type of problem has gained some recent popularities, especially in the application of distributed...

Location:
B205 Engineering Quadrangle

Speaker(s):

Mingyi Hong

University of Minnesota

Tags:
Seminars

## Events Archive

### Machine Learning for the Sciences

*Taking place every other Friday. Lunch will be provided.*

Location:
26 Prospect Ave, Auditorium 103

Tags:
Seminars

### TensorFlow & PyTorch User Group Talks [Two 20-minute talks]

**TensorFlow & PyTorch User Group Talks **[*Two 20-minute talks*]

Location:
138 Lewis Science Library

Speaker(s):

Alex Beatson

Computer Science

Accelerating automated modeling and design with stochastic optimization and neural networks

Mark Ho

Computational Cognitive Science Lab, Department of Psychology

Modeling Human Sequential Decision-Making

Tags:
Seminars

### Meisam Razaviyayn

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...

Location:
Equad B205

Speaker(s):

Meisam Razaviyayn

University of Southern California

Tags:
Seminars

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

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...

Location:
Sherrerd 101

Speaker(s):

Max H. Farrell, Associate Professor of Econometrics and Statistics

University of Chicago

Tags:
Seminars

### Control with Learning On the Fly: First Toy Problems

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...

Location:
Sherrerd 101

Speaker(s):

Charles Fefferman

Math Department, Princeton University

Tags:
Seminars

### Provable Reinforcement Learning From Small Data

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...

Location:
B205 Engineering Quadrangle

Speaker(s):

Mengdi Wang

Operations Research and Financial Engineering at Princeton University

Tags:
Seminars

### Beyond Supervised Learning for Biomedical Imaging

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...

Location:
B205 Engineering Quadrangle

Speaker(s):

Mert R. Sabuncu

Cornell University’s School of Electrical and Computer Engineering, and Meinig School of Biomedical Engineering

Tags:
Seminars

### Prediction with Confidence – General Framework for Predictive Inference

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...

Location:
Corwin Hall, Room 127

Speaker(s):

Regina Y. Liu

Rutgers, Department of Statistics

Tags:
Seminars

### AI Journey with Intel Workshop

### TensorFlow and PyTorch User Group

**TensorFlow and PyTorch User Group**

**JAX: Accelerated machine-learning research via composable function transformations in Python
Thursday, September 12, 4:30-5:30 pm, 120 Lewis Science Library
Peter Hawkins, Google AI Princeton**

Location:
120 Lewis Science Library

Speaker(s):

Peter Hawkins

Google AI Princeton

JAX: Accelerated machine-learning research via composable function transformations in Python

Tags:
Seminars