BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Ery Arias-Castro (UC San Diego)
DTSTART:20200417T150000Z
DTEND:20200417T161200Z
DTSTAMP:20260404T094554Z
UID:sss/1
DESCRIPTION:Title: On using graph distances to estimate Euclidean and related distances\nby Ery Arias-Castro (UC San Diego) as part of Stochastics and Statistic
s Seminar Series\n\n\nAbstract\nGraph distances have proven quite useful i
n machine learning/statistics\, particularly in the estimation of Euclidea
n or geodesic distances. The talk will include a partial review of the lit
erature\, and then present more recent developments on the estimation of c
urvature-constrained distances on a surface\, as well as on the estimation
of Euclidean distances based on an unweighted and noisy neighborhood grap
h.\n
LOCATION:https://stable.researchseminars.org/talk/sss/1/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Sébastien Bubeck (Microsoft Research)
DTSTART:20200424T150000Z
DTEND:20200424T160000Z
DTSTAMP:20260404T094554Z
UID:sss/2
DESCRIPTION:Title: How to Trap a Gradient Flow\nby Sébastien Bubeck (Microsoft Resear
ch) as part of Stochastics and Statistics Seminar Series\n\n\nAbstract\nIn
1993\, Stephen A. Vavasis proved that in any finite dimension\, there exi
sts a faster method than gradient descent to find stationary points of smo
oth non-convex functions. In dimension 2 he proved that 1/eps gradient que
ries are enough\, and that 1/sqrt(eps) queries are necessary. We close thi
s gap by providing an algorithm based on a new local-to-global phenomenon
for smooth non-convex functions. Some higher dimensional results will also
be discussed. I will also present an extension of the 1/sqrt(eps) lower b
ound to randomized algorithms\, mainly as an excuse to discuss some beauti
ful topics such as Aldous’ 1983 paper on local minimization on the cube\
, and Benjamini-Pemantle-Peres’ 1998 construction of unpredictable walks
.\n\nJoint work with Dan Mikulincer\n
LOCATION:https://stable.researchseminars.org/talk/sss/2/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Alexandre d'Aspremont (ENS\, CNRS)
DTSTART:20200501T150000Z
DTEND:20200501T160000Z
DTSTAMP:20260404T094554Z
UID:sss/3
DESCRIPTION:Title: Naive feature selection: Sparsity in naive Bayes\nby Alexandre d'As
premont (ENS\, CNRS) as part of Stochastics and Statistics Seminar Series\
n\n\nAbstract\nDue to its linear complexity\, naive Bayes classification r
emains an attractive supervised learning method\, especially in very large
-scale settings. We propose a sparse version of naive Bayes\, which can be
used for feature selection. This leads to a combinatorial maximum-likelih
ood problem\, for which we provide an exact solution in the case of binary
data\, or a bound in the multinomial case. We prove that our bound become
s tight as the marginal contribution of additional features decreases. Bot
h binary and multinomial sparse models are solvable in time almost linear
in problem size\, representing a very small extra relative cost compared t
o the classical naive Bayes. Numerical experiments on text data show that
the naive Bayes feature selection method is as statistically effective as
state-of-the-art feature selection methods such as recursive feature elimi
nation\, l1-penalized logistic regression and LASSO\, while being orders o
f magnitude faster. For a large data set\, having more than with 1.6 milli
on training points and about 12 million features\, and with a non-optimize
d CPU implementation\, our sparse naive Bayes model can be trained in less
than 15 seconds. Authors: A. Askari\, A. d’Aspremont\, L. El Ghaoui.\n
LOCATION:https://stable.researchseminars.org/talk/sss/3/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Gesine Reinert (University of Oxford)
DTSTART:20200911T150000Z
DTEND:20200911T160000Z
DTSTAMP:20260404T094554Z
UID:sss/4
DESCRIPTION:Title: Stein’s method for multivariate continuous distributions and applicat
ions\nby Gesine Reinert (University of Oxford) as part of Stochastics
and Statistics Seminar Series\n\n\nAbstract\nStein’s method is a key met
hod for assessing distributional distance\, mainly for one-dimensional dis
tributions. In this talk we provide a general approach to Stein’s method
for multivariate continuous distributions. Among the applications we cons
ider is the Wasserstein distance between two continuous probability distri
butions under the assumption of existence of a Poincare constant.\n\nThis
is joint work with Guillaume Mijoule (INRIA Paris) and Yvik Swan (Liege).\
n
LOCATION:https://stable.researchseminars.org/talk/sss/4/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Caroline Uhler (MIT)
DTSTART:20200918T150500Z
DTEND:20200918T160500Z
DTSTAMP:20260404T094554Z
UID:sss/5
DESCRIPTION:Title: Causal Inference and Overparameterized Autoencoders in the Light of Dru
g Repurposing for SARS-CoV-2\nby Caroline Uhler (MIT) as part of Stoch
astics and Statistics Seminar Series\n\n\nAbstract\nMassive data collectio
n holds the promise of a better understanding of complex phenomena and ult
imately\, of better decisions. An exciting opportunity in this regard stem
s from the growing availability of perturbation / intervention data (drugs
\, knockouts\, overexpression\, etc.) in biology. In order to obtain mecha
nistic insights from such data\, a major challenge is the development of a
framework that integrates observational and interventional data and allow
s predicting the effect of yet unseen interventions or transporting the ef
fect of interventions observed in one context to another. I will present a
framework for causal inference based on such data and particularly highli
ght the role of overparameterized autoencoders. We end by demonstrating ho
w these ideas can be applied for drug repurposing in the current SARS-CoV-
2 crisis.\n
LOCATION:https://stable.researchseminars.org/talk/sss/5/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Dylan Foster (MIT)
DTSTART:20200925T150500Z
DTEND:20200925T160500Z
DTSTAMP:20260404T094554Z
UID:sss/6
DESCRIPTION:Title: Separating Estimation from Decision Making in Contextual Bandits\nb
y Dylan Foster (MIT) as part of Stochastics and Statistics Seminar Series\
n\n\nAbstract\nThe contextual bandit is a sequential decision making probl
em in which a learner repeatedly selects an action (e.g.\, a news article
to display) in response to a context (e.g.\, a user’s profile) and recei
ves a reward\, but only for the action they selected. Beyond the classic e
xplore-exploit tradeoff\, a fundamental challenge in contextual bandits is
to develop algorithms that can leverage flexible function approximation t
o model similarity between contexts\, yet have computational requirements
comparable to classical supervised learning tasks such as classification a
nd regression. To this end\, we provide the first universal and optimal re
duction from contextual bandits to online regression. We show how to trans
form any oracle for online regression with a given value function class in
to an algorithm for contextual bandits with the induced policy class\, wit
h no overhead in runtime or memory requirements. Conceptually\, our result
s show that it is possible to provably separate estimation and decision ma
king into separate algorithmic building blocks\, and that this can be effe
ctive both in theory and in practice. Time permitting\, I will discuss ext
ensions of these techniques to more challenging reinforcement learning pro
blems.\n
LOCATION:https://stable.researchseminars.org/talk/sss/6/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Richard Nickl (University of Cambridge)
DTSTART:20201002T150500Z
DTEND:20201002T160500Z
DTSTAMP:20260404T094554Z
UID:sss/7
DESCRIPTION:Title: Bayesian inverse problems\, Gaussian processes\, and partial differenti
al equations\nby Richard Nickl (University of Cambridge) as part of St
ochastics and Statistics Seminar Series\n\nAbstract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/7/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Gábor Lugosi (Pompeu Fabra University)
DTSTART:20201009T150500Z
DTEND:20201009T160500Z
DTSTAMP:20260404T094554Z
UID:sss/8
DESCRIPTION:Title: On Estimating the Mean of a Random Vector\nby Gábor Lugosi (Pompeu
Fabra University) as part of Stochastics and Statistics Seminar Series\n\
nAbstract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/8/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Carola-Bibiane Schönlieb (University of Cambridge)
DTSTART:20201016T150500Z
DTEND:20201016T160500Z
DTSTAMP:20260404T094554Z
UID:sss/9
DESCRIPTION:Title: Data driven variational models for solving inverse problems\nby Car
ola-Bibiane Schönlieb (University of Cambridge) as part of Stochastics an
d Statistics Seminar Series\n\nAbstract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/9/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Jose Blanchet (Stanford University)
DTSTART:20201023T150500Z
DTEND:20201023T160500Z
DTSTAMP:20260404T094554Z
UID:sss/10
DESCRIPTION:Title: Statistical Aspects of Wasserstein Distributionally Robust Optimizatio
n Estimators\nby Jose Blanchet (Stanford University) as part of Stocha
stics and Statistics Seminar Series\n\n\nAbstract\nAbstract: Wasserstein-b
ased distributional robust optimization problems are formulated as min-max
games in which a statistician chooses a parameter to minimize an expected
loss against an adversary (say nature) which wishes to maximize the loss
by choosing an appropriate probability model within a certain non-parametr
ic class. Recently\, these formulations have been studied in the context i
n which the non-parametric class chosen by nature is defined as a Wasserst
ein-distance neighborhood around the empirical measure. It turns out that
by appropriately choosing the loss and the geometry of the Wasserstein dis
tance one can recover a wide range of classical statistical estimators (in
cluding Lasso\, Graphical Lasso\, SVM\, group Lasso\, among many others).
This talk studies a wide range of rich statistical quantities associated w
ith these problems\; for example\, the optimal (in a certain sense) choice
of the adversarial perturbation\, weak convergence of natural confidence
regions associated with these formulations\, and asymptotic normality of t
he DRO estimators. (This talk is based on joint work with Y. Kang\, K. Mur
thy\, and N. Si.)\n
LOCATION:https://stable.researchseminars.org/talk/sss/10/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Daniela Witten (University of Washington)
DTSTART:20201106T160500Z
DTEND:20201106T170500Z
DTSTAMP:20260404T094554Z
UID:sss/12
DESCRIPTION:Title: Valid hypothesis testing after hierarchical clustering\nby Daniela
Witten (University of Washington) as part of Stochastics and Statistics S
eminar Series\n\n\nAbstract\nAs datasets continue to grow in size\, in man
y settings the focus of data collection has shifted away from testing pre-
specified hypotheses\, and towards hypothesis generation. Researchers are
often interested in performing an exploratory data analysis in order to ge
nerate hypotheses\, and then testing those hypotheses on the same data\; I
will refer to this as ‘double dipping’. Unfortunately\, double dippin
g can lead to highly-inflated Type 1 errors. In this talk\, I will conside
r the special case of hierarchical clustering. First\, I will show that sa
mple–splitting does not solve the ‘double dipping’ problem for clust
ering. Then\, I will propose a test for a difference in means between esti
mated clusters that accounts for the cluster estimation process\, using a
selective inference framework. I will also show an application of this app
roach to single-cell RNA-sequencing data. This is joint work with Lucy Gao
(University of Waterloo) and Jacob Bien (University of Southern Californi
a).\n
LOCATION:https://stable.researchseminars.org/talk/sss/12/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Mary Wootters (Stanford University)
DTSTART:20201113T160500Z
DTEND:20201113T170500Z
DTSTAMP:20260404T094554Z
UID:sss/13
DESCRIPTION:Title: Sharp Thresholds for Random Subspaces\, and Applications\nby Mary
Wootters (Stanford University) as part of Stochastics and Statistics Semin
ar Series\n\n\nAbstract\nAbstract: What combinatorial properties are likel
y to be satisfied by a random subspace over a finite field? For example\,
is it likely that not too many points lie in any Hamming ball? What about
any cube? We show that there is a sharp threshold on the dimension of the
subspace at which the answers to these questions change from “extremely
likely” to “extremely unlikely\,” and moreover we give a simple cha
racterization of this threshold for different properties. Our motivation c
omes from error correcting codes\, and we use this characterization to mak
e progress on the questions of list-decoding and list-recovery for random
linear codes\, and also to establish the list-decodability of random Low D
ensity Parity-Check (LDPC) codes.\n\nThis talk is based on the joint works
with Venkatesan Guruswami\, Ray Li\, Jonathan Mosheiff\, Nicolas Resch\,
Noga Ron-Zewi\, and Shashwat Silas.\nEvent Navigation\n
LOCATION:https://stable.researchseminars.org/talk/sss/13/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Arnaud Doucet (University of Oxford)
DTSTART:20201120T160500Z
DTEND:20201120T170500Z
DTSTAMP:20260404T094554Z
UID:sss/14
DESCRIPTION:Title: Perfect Simulation for Feynman-Kac Models using Ensemble Rejection Sam
pling\nby Arnaud Doucet (University of Oxford) as part of Stochastics
and Statistics Seminar Series\n\nAbstract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/14/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Rong Ge (Duke University)
DTSTART:20201204T160500Z
DTEND:20201204T170500Z
DTSTAMP:20260404T094554Z
UID:sss/15
DESCRIPTION:Title: A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neu
ral Net\nby Rong Ge (Duke University) as part of Stochastics and Stati
stics Seminar Series\n\n\nAbstract\nThe training of neural networks optimi
zes complex non-convex objective functions\, yet in practice simple algori
thms achieve great performances. Recent works suggest that over-parametriz
ation could be a key ingredient in explaining this discrepancy. However\,
current theories could not fully explain the role of over-parameterizatio
n. In particular\, they either work in a regime where neurons don't move m
uch\, or require large number of neurons. In this paper we develop a local
convergence theory for mildly over-parameterized two-layer neural net. We
show that as long as the loss is already lower than a threshold (polynomi
al in relevant parameters)\, all student neurons in an over-parametrized t
wo-layer neural network will converge to one of teacher neurons\, and the
loss will go to 0. Our result holds for any number of student neurons as l
ong as it's at least as large as the number of teacher neurons\, and gives
explicit bounds on convergence rates that is independent of the number of
student neurons. Based on joint work with Mo Zhou and Chi Jin.\n
LOCATION:https://stable.researchseminars.org/talk/sss/15/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Jerri Li (Microsoft Research)
DTSTART:20210219T160000Z
DTEND:20210219T171200Z
DTSTAMP:20260404T094554Z
UID:sss/16
DESCRIPTION:Title: Faster and Simpler Algorithms for List Learning\nby Jerri Li (Micr
osoft Research) as part of Stochastics and Statistics Seminar Series\n\n\n
Abstract\nThe goal of list learning is to understand how to learn basic st
atistics of a dataset when it has been corrupted by an overwhelming fracti
on of outliers. More formally\, one is given a set of points $S$\, of whic
h an $\\alpha$-fraction $T$ are promised to be well-behaved. The goal is t
hen to output an $O(1 / \\alpha)$ sized list of candidate means\, so that
one of these candidates is close to the true mean of the points in $T$. In
many ways\, list learning can be thought of as the natural robust general
ization of clustering mixture models. This formulation of the problem was
first proposed in Charikar-Steinhardt-Valiant STOC’17\, which gave the f
irst polynomial-time algorithm which achieved nearly-optimal error guarant
ees. More recently\, exciting work of Cherapanamjeri-Mohanty-Yau FOCS’20
gave an algorithm which ran in time $\\widetilde{O} (n d \\mathrm{poly} (
1 / \\alpha))$. In particular\, this runtime is nearly linear in the input
size for $1/\\alpha = O(1)$\, however\, the runtime quickly becomes impra
ctical for reasonably small $1/\\alpha$. Moreover\, both of these algorith
ms are quite complicated.\n\nIn our work\, we have two main contributions.
First\, we give a polynomial time algorithm for this problem which achiev
es optimal error\, which is considerably simpler than the previously known
algorithms. Second\, we then build off of these insights to develop a mor
e sophisticated algorithm based on lazy mirror descent which runs in time
$\\widetilde{O}(n d / \\alpha + 1/\\alpha^6)$\, and which also achieves op
timal error. Our algorithm improves upon the runtime of previous work for
all $1/\\alpha = O(sqrt(d))$. The goal of this talk is to give a more or l
ess self-contained proof of the first\, and then explain at a high level h
ow to use these ideas to develop our faster algorithm.\n\nJoint work with
Ilias Diakonikolas\, Daniel Kane\, Daniel Kongsgaard\, and Kevin Tian\n
LOCATION:https://stable.researchseminars.org/talk/sss/16/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Yury Polyanskiy (MIT)
DTSTART:20210226T160000Z
DTEND:20210226T171200Z
DTSTAMP:20260404T094554Z
UID:sss/17
DESCRIPTION:Title: Self-regularizing Property of Nonparametric Maximum Likelihood Estimat
or in Mixture Models\nby Yury Polyanskiy (MIT) as part of Stochastics
and Statistics Seminar Series\n\n\nAbstract\nIntroduced by Kiefer and Wolf
owitz 1956\, the nonparametric maximum likelihood estimator (NPMLE) is a w
idely used methodology for learning mixture models and empirical Bayes est
imation. Sidestepping the non-convexity in mixture likelihood\, the NPMLE
estimates the mixing distribution by maximizing the total likelihood over
the space of probability measures\, which can be viewed as an extreme form
of over parameterization.\n\nIn this work we discover a surprising proper
ty of the NPMLE solution. Consider\, for example\, a Gaussian mixture mode
l on the real line with a subgaussian mixing distribution. Leveraging comp
lex-analytic techniques\, we show that with high probability the NPMLE bas
ed on a sample of size n has O(\\log n) atoms (mass points)\, significantl
y improving the deterministic upper bound of n due to Lindsay (1983). Nota
bly\, any such Gaussian mixture is statistically indistinguishable from a
finite one with O(\\log n) components (and this is tight for certain mixtu
res). Thus\, absent any explicit form of model selection\, NPMLE automatic
ally chooses the right model complexity\, a property we term self-regulari
zation. Extensions to other exponential families are given. As a statistic
al application\, we show that this structural property can be harnessed to
bootstrap existing Hellinger risk bound of the (parametric) MLE for finit
e Gaussian mixtures to the NPMLE for general Gaussian mixtures\, recoverin
g a result of Zhang (2009). Time permitting\, we will discuss connections
to approaching the optimal regret in empirical Bayes. This is based on joi
nt work with Yihong Wu (Yale).\n
LOCATION:https://stable.researchseminars.org/talk/sss/17/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Bhaswar B. Bhattacharya (bhaswar@wharton.upenn.edu)
DTSTART:20210305T160000Z
DTEND:20210305T171200Z
DTSTAMP:20260404T094554Z
UID:sss/18
DESCRIPTION:Title: Detection Thresholds for Distribution-Free Non-Parametric Tests: The C
urious Case of Dimension 8\nby Bhaswar B. Bhattacharya (bhaswar@wharto
n.upenn.edu) as part of Stochastics and Statistics Seminar Series\n\nAbstr
act: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/18/
END:VEVENT
BEGIN:VEVENT
SUMMARY:James Robins (Harvard)
DTSTART:20210312T160000Z
DTEND:20210312T171200Z
DTSTAMP:20260404T094554Z
UID:sss/19
DESCRIPTION:Title: On nearly assumption-free tests of nominal confidence interval coverag
e for causal parameters estimated by machine learning\nby James Robins
(Harvard) as part of Stochastics and Statistics Seminar Series\n\nAbstrac
t: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/19/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Daniel Roy (University of Toronto)
DTSTART:20210319T150000Z
DTEND:20210319T161200Z
DTSTAMP:20260404T094554Z
UID:sss/20
DESCRIPTION:Title: Relaxing the I.I.D. Assumption: Adaptively Minimax Optimal Regret via
Root-Entropic Regularization\nby Daniel Roy (University of Toronto) as
part of Stochastics and Statistics Seminar Series\n\nAbstract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/20/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Vladimir Vovk (Royal Holloway\, University of London)
DTSTART:20210326T150000Z
DTEND:20210326T161200Z
DTSTAMP:20260404T094554Z
UID:sss/21
DESCRIPTION:by Vladimir Vovk (Royal Holloway\, University of London) as pa
rt of Stochastics and Statistics Seminar Series\n\nAbstract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/21/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Thibaut Le Gouic (MIT)
DTSTART:20210402T150000Z
DTEND:20210402T161200Z
DTSTAMP:20260404T094554Z
UID:sss/22
DESCRIPTION:Title: Sampler for the Wasserstein barycenter\nby Thibaut Le Gouic (MIT)
as part of Stochastics and Statistics Seminar Series\n\nAbstract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/22/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Suriya Gunasekar (Microsoft Research)
DTSTART:20210409T150000Z
DTEND:20210409T161200Z
DTSTAMP:20260404T094554Z
UID:sss/23
DESCRIPTION:Title: Functions space view of linear multi-channel convolution networks with
bounded weight norm\nby Suriya Gunasekar (Microsoft Research) as part
of Stochastics and Statistics Seminar Series\n\n\nAbstract\nThe magnitude
of the weights of a neural network is a fundamental measure of complexity
that plays a crucial role in the study of implicit and explicit regulariz
ation. For example\, in recent work\, gradient descent updates in overpara
meterized models asymptotically lead to solutions that implicitly minimize
the ell_2 norm of the parameters of the model\, resulting in an inductive
bias that is highly architecture dependent. To investigate the properties
of learned functions\, it is natural to consider a function space view gi
ven by the minimum ell_2 norm of weights required to realize a given funct
ion with a given network. We call this the “induced regularizer” of th
e network. Building on a line of recent work\, we study the induced regula
rizer of linear convolutional neural networks with a focus on the role of
kernel size and the number of channels. We introduce an SDP relaxation of
the induced regularizer\, that we show is tight for networks with a single
input channel. Using this SDP formulation\, we show that the induced regu
larizer is independent of the number of the output channels for single-inp
ut channel networks\, and for multi-input channel networks\, we show indep
endence given sufficiently many output channels. Moreover\, we show that a
s the kernel size increases\, the induced regularizer interpolates between
a basis-invariant norm and a basis-dependent norm that promotes sparse st
ructures in Fourier space.\n\nBased on joint work with Meena Jagadeesan an
d Ilya Razenshteyn.\n
LOCATION:https://stable.researchseminars.org/talk/sss/23/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Eric Laber (Duke University)
DTSTART:20210416T150000Z
DTEND:20210416T161200Z
DTSTAMP:20260404T094554Z
UID:sss/24
DESCRIPTION:Title: Sample size considerations in precision medicine\nby Eric Laber (D
uke University) as part of Stochastics and Statistics Seminar Series\n\nAb
stract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/24/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Hilary Finucane (Broad Institute)
DTSTART:20210423T150000Z
DTEND:20210423T161200Z
DTSTAMP:20260404T094554Z
UID:sss/25
DESCRIPTION:Title: Prioritizing genes from genome-wide association studies\nby Hilary
Finucane (Broad Institute) as part of Stochastics and Statistics Seminar
Series\n\nAbstract: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/25/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Ann Lee (Carnegie Mellon University)
DTSTART:20210514T150000Z
DTEND:20210514T161200Z
DTSTAMP:20260404T094554Z
UID:sss/26
DESCRIPTION:Title: Likelihood-Free Frequentist Inference\nby Ann Lee (Carnegie Mellon
University) as part of Stochastics and Statistics Seminar Series\n\nAbstr
act: TBA\n
LOCATION:https://stable.researchseminars.org/talk/sss/26/
END:VEVENT
END:VCALENDAR