# Seminars and Events

# Machine Learning Seminar Series

## Fall 2019: Fridays at 10:30

**SPECIAL TIME:** Wednesday, Oct. 2, 2019 at 1:30pm in TTIC room 526: Arthur Szlam, Facebook Research

### Language and Interaction in Minecraft

Friday, Oct. 11, 2019 in TTIC room 526: Peter Bartlett, UC-Berkeley

### Optimizing probability distributions for machine learning: sampling meets optimization

Joint work with Yasin Abbasi-Yadkori, Niladri Chatterji, Xiang Cheng, Michael Jordan, Yi-An Ma, Wenlong Mou, and Martin Wainwright.

Bio: Peter Bartlett is a professor in the Computer Science Division and Department of Statistics and Associate Director of the Simons Institute for the Theory of Computing at the University of California at Berkeley. His research interests include machine learning and statistical learning theory. He is the co-author, with Martin Anthony, of the book Neural Network Learning: Theoretical Foundations. He has served as an associate editor of the journals Bernoulli, Mathematics of Operations Research, the Journal of Artificial Intelligence Research, the Journal of Machine Learning Research, and the IEEE Transactions on Information Theory, and as program committee co-chair for COLT and NeurIPS. He was awarded the Malcolm McIntosh Prize for Physical Scientist of the Year in Australia in 2001, and was chosen as an Institute of Mathematical Statistics Medallion Lecturer in 2008, an IMS Fellow and Australian Laureate Fellow in 2011, and a Fellow of the ACM in 2018. He was elected to the Australian Academy of Science in 2015.

Friday, Oct. 18, 2019 in Crerar room 390: Madeleine Udell, Cornell

### Big data is low rank

Friday, Oct. 25, 2019 in TTIC room 526: Shay Moran, Technion

### Convex Set Disjointness, Distributed Learning of Halfspaces, and LP Feasibility

*Convex Set Disjointness*(CSD) problem, where two players have input sets taken from an arbitrary fixed domain U\subset R^d of size | U | = n. Their mutual goal is to decide using minimum communication whether the convex hulls of their sets intersect (equivalently, whether their sets can be separated by a hyperplane).

Friday, Nov. 1, 2019 in Crerar room 390: Ohad Shamir, Weizmann

### Training Neural Networks: The Bigger the Better?

**Special Talk:** Distinguished Lecture at TTIC, Friday, Nov. 8, 2019 in TTIC room 526: Shafi Goldwasser, MIT

Friday, Nov. 15, 2019 in Crerar 390: Greg Ongie, University of Chicago; and Blake Woodworth, TTIC

### Greg Ongie: A function space view of overparameterized neural networks

### Blake Woodworth: The complexity of finding stationary points in convex and non-convex optimization

Friday, Nov. 22, 2019 in TTIC 526: Ramya Vinayak, University of Washington

### Learning from Sparse Data

In this talk, I will present our recent results where we show that the maximum likelihood estimator (MLE) is minimax optimal in the sparse observation regime. While the MLE for this problem was proposed as early as the late 1960’s, how accurately the MLE recovers the true distribution was not known. Our work closes this gap. In the course of our analysis, we provide novel bounds on the coefficients of Bernstein polynomials approximating Lipschitz-1 functions. Furthermore, the MLE is also efficiently computable in this setting and we evaluate the performance of MLE on both synthetic and real datasets.

Joint work with Weihao Kong, Gregory Valiant, and Sham Kakade.

Bio: Ramya Korlakai Vinayak is a postdoctoral researcher at the Paul G. Allen School of Computer Science and Engineering at the University of Washington, working with Sham Kakade. Her research interests broadly span the areas of machine learning, statistical inference, and crowdsourcing. She received a Ph.D. from Caltech where she was advised by Babak Hassibi. She is a recipient of the Schlumberger Foundation Faculty of the Future fellowship from 2013- 15. She obtained her Masters from Caltech and Bachelors from IIT Madras.

Friday, Nov. 29, 2019: Thanksgiving break

Friday, Dec. 6, 2019 in TTIC 526: Zhaoran Wang, Northwestern

### On the Computational and Statistical Efficiency of Policy Optimization in (Deep) Reinforcement Learning

Friday, Dec. 13, 2019: NeurIPS

## Winter 2020: Fridays at 10:30

Friday, Jan. 10, 2020 in TTIC 526: Mina Karzand, UW-Madison

### Focused Learning in Tree-Structured Graphical Models

In particular, in the first half of the talk, I look into learning tree structured Ising models in which the learned model is used subsequently for prediction based on partial observations (given the realization of a subset of variables, predict the value of the remaining ones). The vast majority of previous work on learning graphical models aims to correctly recover the underlying graph structure. In the data-constrained regime, learning the entire graph structure correctly is usually impossible. I show that it is possible to efficiently learn a tree model that gives accurate predictions even when there is insufficient data to learn the correct structure.

The second half of the talk is about speciation rate estimation in phylogenetic trees. This problem is essentially one of inferring features of the model (in this case, the speciation or extinction rate) from partial observations (thesequences at the leaves of the tree) of a latent tree model (phylogeny). I show that to estimate the speciation rate efficiently, it is not necessary to follow the popular approach of reconstructing the complete tree structure as an intermediate step, which requires long DNA sequences. Instead, one can extract precisely the right type of information about the rates by zooming into carefully chosen local structures. My results show that an incomplete and partially incorrect summary of the tree structure is enough to estimate the speciation rate with the minimax optimal dependence on the length of observed DNA sequences.

Joint work with Guy Bresler, Sebastien Roch and Robert Nowak.

Bio: Mina Karzand is a postdoctoral associate in University of Wisconsin-Madison. Before that, she was a postdoctoral research associate in MIT where she received her PhD in Electrical Engineering and Computer Science. Her research interests are on the design and analysis of data driven inference and decision making systems in the intersection of areas of machine learning, probability, and information theory.

Friday, Jan. 17, 2020 in Crerar 390: Rina Foygel Barber, University of Chicago

### Predictive inference with the jackknife+

Bio: Rina Foygel Barber is an Associate Professor in the Department of Statistics at the University of Chicago. Before starting at U of C, she was a NSF postdoctoral fellow during 2012-13 in the Department of Statistics at Stanford University, supervised by Emmanuel Candès. She received her PhD in Statistics at the University of Chicago in 2012, advised by Mathias Drton and Nati Srebro, and a MS in Mathematics at the University of Chicago in 2009. Prior to graduate school, she was a mathematics teacher at the Park School of Baltimore from 2005 to 2007.

Friday, Jan. 24, 2020 in TTIC 526: TBD

Friday, Jan. 31, 2020 in Crerar 390: Tengyu Ma, Stanford

Friday, Feb. 7, 2020 in TTIC 526: Yixin Wang, Columbia

Friday, Feb. 14, 2020 in Crerar 390: TBD

Friday, Feb. 21, 2020 in TTIC 526: TBD

Friday, Feb. 28, 2020 in Crerar 390: TBD

Friday, Mar. 6, 2020 in TTIC 526: TBD

Friday, Mar. 13, 2020 in Crerar 390: TBD

Friday, Mar. 20, 2020: Spring break

## Spring 2020: Fridays at 10:30

Friday, Apr. 3, 2020 in TTIC 526: TBD

Friday, Apr. 10, 2020 in Crerar 390: Ken Goldberg, Berkeley

Friday, Apr. 17, 2020 in TTIC 526: Ben Recht, Berkeley

Friday, Apr. 24, 2020 in Crerar 390: Rose Yu, Northeastern

Friday, May 1, 2020 in TTIC 526: TBD

Friday, May 8, 2020 in Crerar 390: Elad Hazan, Princeton

Friday, May 15, 2020 in TTIC 526: James Sharpnack, UC Davis

Friday, May 22, 2020 in Crerar 390: TBD

Friday, May 29, 2020 in TTIC 526: TBD

Friday, Jun. 5, 2020 in Crerar 390: TBD

## Academic year 2018-2019

#### Wednesdays, 1-2pm in the Harper Center (Booth) Room 219 Pizza provided by UChicago CS Department

###### Sign up for announcement email list at https://lists.uchicago.edu/web/subscribe/ml-announce.

April 3, 2019 **in Crerar room 390**: Lorenzo Orecchia, Boston University

### First-Order Methods Unleashed: Scalable Optimization in the Age of Big Data

April 10, 2019 **in room C25**: Mesrob Ohannessian, TTIC

### From Fair Decisions to Social Benefit

April 17, 2019 **in room C04**: Lin Yang, Princeton University

### Learn Policy Optimally via Efficiently Utilizing Data

April 24, 2019: Avrim Blum, TTIC

### Algorithmic fairness in online decision-making

April 29, 2019: (2:30pm in Crerar 390) Tong Zhang, Hong Kong University of Science and Technology.

### Modern Techniques of Statistical Optimization for Machine Learning

May 1, 2019: Tengyuan Liang, University of Chicago Booth

### New Thoughts on Adaptivity, Generalization and Interpolation Motivated from Neural Networks

May 8, 2019: Rosemary Braun, Northwestern University

### Using Gene Expression to Tell Time

May 15, 2019: Yali Amit, UChicago Statistics

### Optimization of latent variables in deep network applications

May 22, 2019: UChicago Geometric Data Analysis Workshop

May 29, 2019 in **SHFE 203 (Saieh Hall For Economics)**: Dan McDonald

### Trend filtering in exponential families

## Past Quarters:

Jan. 16, 2019: Sumeet Katariya, UW-Madison

### Adaptive Sampling for Ranking and Clustering

### Challenges and Hopes of Unsupervised Learning by Mutual Information Maximization

### Convergence Rates of Variational Posterior Distributions

Feb. 13, 2019: Veronika Rockova, Univeristy of Chicago, Booth

### On Theory for BART

### Analysis of Big Dependent Data

Feb. 27, 2019: No Seminar

March 5, 2019 **(TUESDAY), Harper Center 3B from 12:10 to 1:10 p.m.:** Jorge Nocedal, Northwestern University

### Zero-Order Methods for the Optimization of Noisy Functions

March 6, 2019: Bryan Pardo, Northwestern University

### Audio source separation models that learn without ground truth and are open to user correction

March 13, 2019: Sebastian Stitch, EPFL

### Error Feedback for Communication Efficient SGD

March 20, 2019: Spring Break, No Seminar

March 27, 2019: Spring Break, No Seminar

## Additonal Machine Learning Events