Sven Wang's homepage
  • Research
  • Research
Picture
Welcome! I am a postdoctoral researcher at MIT, where I am affiliated with the Institute for Data, Systems, and Society (IDSS) and the Uncertainty Quantification Group. I obtained my PhD from Cambridge University, where I was advised by Richard Nickl.

In September 2023, I will join the mathematics department at Humboldt University Berlin as Juniorprofessor (assistant professor).

Here's my
 CV.

Email: svenwang [at] mit [dot] edu

My research interests
(i) Much of my research has been dedicated to mathematical statistics. I have worked on theoretical guarantees for many common inference procedures in complex and high-dimensional statistical models, related to:
  • Statistical inference for PDEs and stochastic processes (often used to describe physical,  biological and social phenomena)
  • Bayesian inference in inverse problems
  • Computational guarantees for high-dimensional MCMC algorithms
  • Transport-based statistical methods
(ii) In the past year I have also been working on mathematical questions around democratic processes, mostly with collaborators from the Harvard EconCS group. I am interested in advancing mathematical models of different democratic decision processes, and in reasoning about their potential societal benefits.

Publications / preprints

[10] Infinite-dimensional diffusion models for function spaces (with J. Pidstrigach, Y. Marzouk and S. Reich). Preprint (2023).

​[9] Accounting for stakes in democratic decisions (with B. Flanigan and A. Procaccia). Preprint (2023). Accepted at Foundations of Responsible Computing (FORC 2023, non-archival track).

[8] On free energy barriers in Gaussian priors and failure of MCMC for high-dimensional unimodal distributions (with A.S. Bandeira, A. Maillard and R. Nickl). 
Philosophical Transactions of the Royal Society A 381 (2023).

[7] Distortion under Public-Spirited Voting (with B. Flanigan and A. Procaccia). To appear in Economics and Computation (EC 2023).
​
[6] On minimax density estimation via measure transport (with Y. Marzouk). Preprint (2022).

[5] Wasserstein Distributionally Robust Gaussian Process Regression and Linear Inverse Problems (with X. Zhang, J. Blanchet, Y. Marzouk and V.A. Nguyen). Preprint (2022).

[4] Laplace priors and spatial inhomogeneity in Bayesian inverse problems (with S. Agapiou). To appear in Bernoulli.
​
[3] On polynomial-time computation of high-dimensional posterior measures by Langevin-type algorithms (with R. Nickl). Journal of the European Mathematical Society (2022). Link to EMS online publication.


[2] Convergence rates for Penalised Least Squares estimators in PDE-constrained regression problems (with R. Nickl and S. van de Geer). SIAM/ASA Journal of Uncertainty Quantification 8 (2020) 374-413.
​

[1] The nonparametric LAN expansion for discretely observed diffusions. Electronic Journal of Statistics 13 (2019) 1329-1358.

[A] Statistical inference and computation in PDE models. PhD thesis, University of Cambridge (2021).

Forthcoming articles

[11] Statistical consistency theory for sampling and density estimation via neural differential equations (with R. Ren, Y. Marzouk and J. Zech).

Invited conference talks (upcoming & past):
SIAM Conference on Computational Science and Engineering (2023/02)
​Statistics for Stochastic Processes: SDEs, SPDEs and concentration of measure (2022/09)
ESI Vienna workshop "Statistical estimation and deep learning in UQ for PDEs" (2022/05,
link to program)
AMS Sectional meeting (2022/05, link to program)
BNP workshop Cyprus (2022/04, link to program)
SIAM Conference on Uncertainty Quantification (2022/04)
Oberwolfach "Data Assimilation -- Mathematical Foundation and Applications" (2022/02)
BANFF "Statistical Aspects of Non-Linear Inverse Problems" (link to video)
Oberwolfach "Foundations of Bayesian Inference for Complex Statistical Models"
DPMMS Cambridge workshop "
Mathematical and Statistical challenges in Uncertainty Quantification" (link to video)
​

Selected seminar talks: UMass Amherst (2022/03); WIAS, Berlin (2021/01, 2020/01); ​University of Chicago (2020/10); ETH Zurich YDSSZ seminar (2020/07); Caltech (2020/01); CREST Paris (2019/11); U of Sussex (2019/10)

Music & Miscellanea

I love playing piano, singing and composing music. Some groups I've been lucky to be part of:
  • Munich Bach choir
  • Cambridge's Pembroke lieder scheme, where I studied with Joseph Middleton
  • MIT Chamber Music Society
  • ​Kammermusikkreis Unterwachingen
  • Michael Schopper, my most wonderful mentor and singing teacher
  • Here is me playing some late Schubert in 2019,  recorded in Trinity College Chapel

I also love being outdoors.
  • In 2015, I biked through 22 European countries for 6 months (with my very good friend Niklas from Berlin). We paired our trip with a fundraising project towards medical care for refugees from the war in Syria, which has completely disappeared from the news but is unfortunately still timely.
  • In 2012, my friend Nick came up with the glorious idea of hiking across the alps with a donkey (named Thomas) from our German hometown Aschaffenburg to the Mediterranean Sea in Italy. It was truly life-changing for 16-year-old me. Thomas had a solar panel on his back, and we funded our trip by playing the accordion in the streets. We were (unintentionally) discovered by the Italian media -- they must have had a summer drought of stories to report about.
Powered by Create your own unique website with customizable templates.