Coder Social home page Coder Social logo

About me

I'm a PhD candidate at the Center for Data Science at New York University, advised by Jonathan Niles-Weed. My research interests lie at the intersection of optimal transport, high-dimensional statistics, and optimization theory. This Github page contains the code for some of my research projects during my PhD (among other projects):

Code is available for the following projects:

  • “Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space” with Roger Jiang and Sinho Chewi,
  • "Debiaser Beware: Pitfalls of Centering Regularized Transport Maps" with Marco Cuturi and Jonathan Niles-Weed (ICML 2022),
  • "Entropic estimation of optimal transport maps" with Jonathan Niles-Weed (2021) is also found in the above repo.
  • An implementation of the 1-Nearest-Neighbor estimator for optimal transport maps, as seen in "Plugin Estimators for Smooth Transport Maps" (Manole et al., 2021)

Contact

aram-alexandre[dot]pooladian[at]nyu[dot]edu

AramPooladian's Projects

1nn_mapestimator icon 1nn_mapestimator

Implementation of the 1-Nearest-Neighbor estimator for estimating optimal transport maps, as seen in [Plugin Estimation of Smooth Transport Maps](https://arxiv.org/abs/2107.12364) (Manole et al.; 2021).

debiaserbeware icon debiaserbeware

Repository containing Google Colab code for "Debiaser Beware: Pitfalls of Centering Regularized Transport Maps", which was recently accepted to ICML 2022.

notes icon notes

Collection of personal course notes

ott icon ott

Optimal Transport tools implemented with the JAX framework, to get auto-diff, parallel and jit-able computations.

owl_advattack icon owl_advattack

Adversarial attack with respect to the Ordered Weighted L1 (OWL) norm via the ProxLogBarrier framework

tvprojection icon tvprojection

Batch-wise implementation of TV-ball projection algorithm; coded in PyTorch

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.