pratham16cse
Researcher in Machine Learning focusing on probabilistic models for temporal data analytics. Graduated with a Ph.D. from IIT Bombay.
IIT BombayMumbai
Pinned Repositories
AggForecaster
Code for "Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts", IJCAI 2022
ARU
awesome-time-series
list of papers, code, and other resources
cs725-2020-assign2
Repository for Assignment 2 of the course CS725 Autumn 2020.
deep-learning-time-series
List of papers, code and experiments using deep learning for time series forecasting
DualTPP
Code for "Long Horizon Forecasting With Temporal Point Processes", WSDM 2021
project-website-template
A HTML/CSS Template for Building Projects or Personal Websites
TransNAR
pratham16cse's Repositories
pratham16cse/DualTPP
Code for "Long Horizon Forecasting With Temporal Point Processes", WSDM 2021
pratham16cse/AggForecaster
Code for "Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts", IJCAI 2022
pratham16cse/cs725-2020-assign2
Repository for Assignment 2 of the course CS725 Autumn 2020.
pratham16cse/ARU
pratham16cse/awesome-time-series
list of papers, code, and other resources
pratham16cse/deep-learning-time-series
List of papers, code and experiments using deep learning for time series forecasting
pratham16cse/project-website-template
A HTML/CSS Template for Building Projects or Personal Websites
pratham16cse/TransNAR
pratham16cse/AIML_Scribes_2022
This repository contains scribes of AIML lectures for the 2022 offering.
pratham16cse/basics2apps
A tutorial on deep learning 2019
pratham16cse/bench-vldb20
pratham16cse/cvxpylayers
Differentiable convex optimization layers
pratham16cse/gluon-ts
GluonTS - Probabilistic Time Series Modeling in Python
pratham16cse/json
Output ExpressionEngine data in JSON format.
pratham16cse/multivariate-time-series-data
pratham16cse/pratham16cse
pratham16cse/pratham16cse.github.io
pratham16cse/Taxi_analysis
pratham16cse/tpprl
Code and data for "Deep Reinforcement Learning of Marked Temporal Point Processes", NeurIPS 2018
pratham16cse/Wasserstein-Learning-For-Point-Process
learning point processes by means of optimal transport and wasserstein distance