Neyman Seminar

The Neyman seminar is the statistics seminar in the Department. Historically, it has been focused on applications of Statistics to other fields. Nowadays, it has a very broad scope, with topics ranging from applications of statistics to theory.

The seminar is held on Wednesdays from 4 to 5 in the Jerzy Neyman room, 1011 Evans.

Details of individual seminar events are published in the campus' event system.

You can sign up to the department's seminars@stat mailing list to receive related announcements.

Add this series of events to your calendar: ICAL or XML

Recent & Upcoming Neyman Seminars

Patrick Wolfe, Purdue University (Speaker)
Aug 24, 2017 4:00pm
332 Evans Hall
Abstract:
Understanding how two networks differ, or quantifying the degree to which a single network departs from a given model, is a challenging question in modern mathematical statistics. Here we show how subgraph densities, which for large graphs play a role analogous to moments in the context of random variables, enable a natural means of nonparametric network comparison. Coupled with a partial order...
Xiaodong Li, University of California, Davis (Speaker)
Aug 30, 2017 4:00pm
1011 Evans Hall
Abstract:
Cluster structures might be ubiquitous for large data, and community detection has recently attracted much research attention in applied physics, sociology, computer science and statistics due to its broad applicability in various network datasets. A variety of approaches distinct in essence have thus been proposed, among which convex relaxation had not been extensively explored since its...
Mengdi Wang, Princeton University
Sep 6, 2017 4:00pm
1011 Evans Hall
Abstract:
Stochastic first-order methods provide a basic algorithmic tool for online learning and data analysis. In this talk, we survey several innovative applications including risk-averse optimization, online principal component analysis, dynamic network partition, Markov decision problems and reinforcement learning. We will show that convergence analysis of the stochastic optimization algorithms...
Nike Sun, University of California, Berkeley
Sep 13, 2017 4:00pm
1011 Evans Hall
Abstract:
We will discuss a class of random constraint satisfaction problems (CSPs), including the boolean k-satisfiability (k-SAT) problem. For numerous random CSP models, heuristic methods from statistical physics yield detailed predictions on phase transitions and other phenomena. We will survey some of these predictions and describe some progress in the development of mathematical theory for these...
Adityanand Guntuboyina, University of California, Berkeley
Sep 20, 2017 4:00pm
1011 Evans Hall
Abstract:
We study two convex optimization based procedures for nonparametric function estimation: trend filtering (or higher order total variation denoising) and the Kiefer-Wolfowitz MLE for Gaussian location mixtures. Trend filtering can be seen as a technique for fitting spline-like functions for nonparametric regression with adaptive knot selection. It can also be seen as a special case of LASSO for a...
Stefanie Jegelka, Massachusetts Institute of Technology
Sep 27, 2017 4:00pm
1011 Evans Hall
Abstract:
Discrete Probability distributions with strong negative dependencies (negative association) occur in a wide range of settings in Machine Learning, from probabilistic modeling to randomized algorithms for accelerating a variety of popular ML models. In addition, these distributions enjoy rich theoretical connections and properties. A prominent example are Determinantal Point Processes. In this...
Peter Bühlmann, ETH Zürich
Oct 4, 2017 4:00pm
1011 Evans Hall
Abstract:
Heterogeneity in potentially large-scale data can be beneficially exploited for causal inference and more robust prediction. The key idea relies on invariance and stability across different heterogeneous regimes or sub-populations. What we term as "anchor regression" opens some novel insights and connections between causality and protection (robustness) against worst case interventions in ...
Michael Anderson, University of California, Berkeley
Oct 11, 2017 4:00pm
1011 Evans Hall
Abstract:
Preanalysis plans (PAPs) have become an important tool for limiting false discoveries in field experiments. We evaluate the properties of an alternate approach which splits the data into two samples: An exploratory sample and a confirmation sample. When hypotheses are homogeneous, we describe an improved split-sample approach that achieves 90% of the rejections of the optimal PAP without...
Anca Dragan, University of California, Berkeley
Oct 18, 2017 4:00pm
1011 Evans Hall
Abstract:
Robots are becoming increasingly more capable of optimizing objective functions for physical tasks, from navigation, to dexterous manipulation, to flight. The ultimate goal is to perform these tasks for us, in our environments. We want cars driving on our roads, or personal robots assisting us with activities of daily living as we age in our own homes. Right now, we tend to be merely obstacles to...