Skip to main content.
Advanced search >
Print

<< November 2017 >>

Wednesday, November 1, 2017

On Gaussian-width gradient complexity and mean-field behavior of interacting particle systems and random graphs

Seminar: Probability Seminar | November 1 | 3:10-4 p.m. | 1011 Evans Hall


Ronen Eldan, Weizmann Institute of Science

Department of Statistics


The motivating question for this talk is: What does a sparse Erd\"os-R\'enyi random graph, conditioned to have twice the number of triangles than the expected number, typically look like? Motivated by this question, In 2014, Chatterjee and Dembo introduced a framework for obtaining Large Deviation Principles (LDP) for nonlinear functions of Bernoulli random variables (this followed an earlier...   More >



Leave out estimation of variance components

Seminar: Neyman Seminar | November 1 | 4-5 p.m. | 1011 Evans Hall


Patrick Kline, University of California, Berkeley

Department of Statistics


We propose a general framework for unbiased estimation of quadratic forms of regression coefficients in linear models with unrestricted heteroscedasticity. Economic applications include variance component estimation in multi-way fixed effects and random coefficient models. The large sample distribution of our estimator is studied in an asymptotic framework where the number of regressors grows in...   More >



Tuesday, November 7, 2017

Seminar 217, Risk Management: Rough Heston model: Pricing, hedging and microstructural foundations

Seminar: Risk Seminar | November 7 | 11 a.m.-1 p.m. | 639 Evans Hall


Speaker: Mathieu Rosenbaum, École Polytechnique

Center for Risk Management Research


It has been recently shown that rough volatility models, where the volatility is driven by a fractional  Brownian motion with small Hurst parameter, provide very relevant dynamics in order to reproduce the  behavior of both historical and implied volatilities. However, due to the non-Markovian nature of the fractional Brownian motion, they raise new issues when it comes to the risk management of...   More >

Wednesday, November 8, 2017

Self-avoiding polygons and walks: counting, joining and closing.

Seminar | November 8 | 3:10-4 p.m. | 1011 Evans Hall


Alan Hammond, U.C. Berkeley

Department of Statistics


Self-avoiding walk of length n on the integer lattice Z^d is the uniform measure on nearest-neighbour walks in Z^d that begin at the origin and are of length n. If such a walk closes, which is to say that the walk's endpoint neighbours the origin, it is natural to complete the missing edge connecting this endpoint and the origin. The result of doing so is a self-avoiding polygon. We investigate...   More >



Causal inference with interfering units for cluster and population level intervention programs

Seminar: Neyman Seminar | November 8 | 4-5 p.m. | 1011 Evans Hall


Fabrizia Mealli, University of Florence

Department of Statistics


Interference arises when an individual's potential outcome
depends on the individual treatment and also on the treatment
of others. A common assumption in the causal inference literature in the
presence of interference is partial interference, implying that the
population can be partitioned in clusters of units whose potential
outcomes only depend on the treatment of other units within the...   More >

Monday, November 13, 2017

Loeve Prize ceremony

Special Event: Other Related Seminars | November 13 | 4-5 p.m. | 1011 Evans Hall


David Aldous and Vladas Sidoravicius.

Department of Statistics


Presentation of prize to Hugo Duminil-Copin, and short non-technical talk by Vladas Sidoravicius. Followed by reception 5.00 - 5.45 in Womens Faculty Club.

Tuesday, November 14, 2017

Seminar 217, Risk Management: Investor Behavior and Market Dynamics

Seminar: Risk Seminar | November 14 | 11 a.m.-1 p.m. | 639 Evans Hall


Speaker: John Arabadjis, State Street

Center for Risk Management Research


The Market is a consensual hallucination that commands attention by wielding its Invisible Hand. In this talk we will examine the ways that Adam Smith’s 250-year-old appendage makes itself felt – positioning, trading, and hurting herding – and their implications for the investment process.

Wednesday, November 15, 2017

Probing neural circuits with shaped light

Seminar: Neyman Seminar | November 15 | 4-5 p.m. | 1011 Evans Hall


Na Ji, University of California, Berkeley

Department of Statistics


To understand computation in the brain, one needs to understand the input-output relationships for neural circuits and the anatomical and functional relationships between individual neurons therein. Optical microscopy has emerged as an ideal tool in this quest, as it is capable of recording the activity of neurons distributed over millimeter dimensions with sub-micron spatial resolution. I will...   More >

Tuesday, November 28, 2017

Seminar 217, Risk Management: The Futures Financing Rate

Seminar: Risk Seminar | November 28 | 11 a.m.-1 p.m. | 639 Evans Hall


Speaker: Nicholas Gunther, UC Berkeley

Center for Risk Management Research


We estimate the financing rate implicit in equity index futures (“FIR”) by comparing the prices of the near and next contracts and adjusting for expected dividends and convexity. We provide a direct estimate of the FIR volatility, along with the correlation of the FIR and the underlying stock index, which are required for the convexity adjustment and the specification of confidence intervals. Our...   More >

Wednesday, November 29, 2017

Regularity and strict positivity of densities for the nonlinear stochastic heat equation

Seminar: Probability Seminar | November 29 | 3:10-4 p.m. | 1011 Evans Hall


Le Chen, University of Nevada, Las Vegas

Department of Statistics


In this talk, I will present some recent progress in understanding the existence, regularity and strict positivity of the (joint-) density of the solution to a semilinear stochastic heat equation. The talk will consists two parts. In the first part, I will show that under a mild cone condition for the diffusion coefficient, one can establish the smooth joint density at multiple points. The tool...   More >



Causal Inference in the Presence of Interference

Seminar: Neyman Seminar | November 29 | 4-5 p.m. | 1011 Evans Hall


Michael Hudgens, UNC-Chapel Hill

Department of Statistics


A fundamental assumption usually made in causal inference is that of no interference between individuals (or units), i.e., the potential outcomes of one individual are assumed to be unaffected by the treatment assignment of other individuals. However, in many settings, this assumption obviously does not hold. For example, in infectious diseases, whether one person becomes infected depends on who...   More >

Thursday, November 30, 2017

GraphXD Seminar: Data-Driven Methods for Learning Sparse Graphical Models

Seminar: Other Related Seminars | November 30 | 5:30-7 p.m. | 1011 Evans Hall


Somayeh Sojoudi, EECS, Mechanical Engineering

Berkeley Institute for Data Science


Learning models from data has a significant impact on many disciplines, including computer vision, medical imaging, social networks, neuroscience and signal processing. In the network inference problem, one may model the relationships between the network components through an underlying inverse covariance matrix. Learning this graphical model is often challenged by the fact that only a small...   More >