Autoencoder dimensionality reduction, EMD-Manhattan metrics comparison and classifier based clustering on MNIST dataset.

Autoencoder dimensionality reduction, EMD-Manhattan metrics comparison and classifier based clustering on MNIST dataset

Comparison of multiple methods for calculating MNIST hand-written digits similarity.

3 part project: A. bottleneck autoencoder, B. manhattan distance, C. earth mover's distance

PyTorch Wrapper for Earth-Mover-Distance (EMD) for 3D point cloud regression

Reducing MNIST image data dimensionality by extracting the latent space representations of an Autoencoder model. Comparing these latent space representations to the default MNIST representation

Pillars is a library that contains fast algorithms for Python implemented in Rust.

Calculating Pairwise Similarity of Polymer Ensembles via Earth Mover’s Distance

Jupyter notebook for my research in Document Similarity.

Earth-movers distance based graph distance metric for financial statements.

Dot Lib

PyTorch code for ACL 2022 paper: RoMe: A Robust Metric for Evaluating Natural Language Generation https://aclanthology.org/2022.acl-long.387/

An implementation of Squared Earth-Mover's Distance loss for Neural Networks.

Play, learn, solve, and analyze No-Limit Texas Hold Em. Implementation follows from Monte Carlo counter-factual regret minimization over with hierarchical K-means imperfect recall abstractions.

A materials discovery algorithm geared towards exploring high-performance candidates in new chemical spaces.

Compact Matlab code for the computation of the 1- and 2-Wasserstein distances in 1D

Measure the distance between two spectra/signals using optimal transport and related metrics

Code for CVPR 2022 https://arxiv.org/abs/2112.04016 DeepFace-EMD Re-ranking Using Patch-wise Earth Movers Distance Improves Out-Of-Distribution Face Identification

Morphing and Sampling Network for Dense Point Cloud Completion (AAAI2020)