Divyansh Singhvi

I am a Quantitative Researcher working in the financial industry using statistical and machine learning methods to develop predictive signals. I completed my B.Tech in Computer Science and Engineering from Indian Institute of Technology, Kanpur.

I enjoy reading Kaggle notebooks and occasionally do take part in competitive competitions. I was recently ranked 7th on Kaggle : Jane Street Market Prediction Challenge. I hate recurring manual tasks in my work and prefer automating as much as possible.

In my spare time, I enjoy playing sports and video games with friends. I am always up for hearing better ways of automation and doing some brainstorming on a research topic unrelated to my everyday work.

news

Oct 25, 2021	Short Paper Accepted in IEEE HPCC-2021
Sep 1, 2021	Joining Millennium Management as Quantitative Researcher.
Aug 30, 2021	Ranked 7^th in Jane Street Market Prediction kaggle challenge among 4245 teams.

selected publications

Active Learning-based Automatic Tuning and Prediction of Parallel I/O Performance

Agarwal, Megha, Singhvi, Divyansh, Malakar, Preeti, and Byna, Suren

In 2019 IEEE/ACM Fourth International Parallel Data Systems Workshop (PDSW) Nov 2019

Abs HTML

Parallel I/O is an indispensable part of scientific applications. The current stack of parallel I/O contains many tunable parameters. While changing these parameters can increase I/O performance many-fold, the application developers usually resort to default values because tuning is a cumbersome process and requires expertise. We propose two auto-tuning models, based on active learning that recommend a good set of parameter values (currently tested with Lustre parameters and MPI-IO hints) for an application on a given system. These models use Bayesian optimization to find the values of parameters by minimizing an objective function. The first model runs the application to determine these values, whereas, the second model uses an I/O prediction model for the same. Thus the training time is significantly reduced in comparison to the first model (e.g., from 800 seconds to 18 seconds). Also both the models provide flexibility to focus on improvement of either read or write performance. To keep the tuning process generic, we have focused on both read and write performance. We have validated our models using an I/O benchmark (IOR) and 3 scientific application I/O kernels (S3D-IO, BT-IO and GenericIO) on two supercomputers (HPC2010 and Cori). Using the two models, we achieve an increase in I/O bandwidth of up to 11× over the default parameters. We got up to 3× improvements for 37 TB writes, corresponding to 1 billion particles in GenericIO. We also achieved up to 3.2× higher bandwidth for 4.8 TB of noncontiguous I/O in BT-IO benchmark.