Hi! I'm Keshav, an aspiring software engineer from Ellicott City, MD.
I enjoy leveraging Machine Learning to tackle the problems I see around me. In my free time, I enjoy attending hackathons, developing websites, and competitive programming.
Feel free to look around the website to see my past experience, projects, and more! Outside of school, I enjoy playing tennis, basketball, and chess, and listening to music.
Below, you can see signifant research projects that I have taken on!
Abstract: Mainstream machine learning conferences have seen a dramatic increase in the number of participants, along with a growing range of perspectives, in recent years. Members of the machine learning community are likely to overhear allegations ranging from randomness of acceptance decisions to institutional bias. In this work, we critically analyze the review process through a comprehensive study of papers submitted to ICLR between 2017 and 2020. We quantify reproducibility and randomness in review scores and acceptance decisions, and examine whether scores correlate with paper impact. Our findings suggest strong institutional bias in accept/reject decisions, even after controlling for paper quality. Furthermore, we find evidence for a gender gap, with female authors receiving lower scores, lower acceptance rates, and fewer citations per paper than their male counterparts. We conclude our work with recommendations for future conference organizers.
Abstract: With neural networks having demonstrated their versatility and benefits, the need for their optimal performance is as prevalent as ever. A defining characteristic, hyperparameters, can greatly affect its performance. Thus engineers go through a process, tuning, to identify and implement optimal hyperparameters. That being said, excess amounts of manual effort are required for tuning network architectures, training configurations, and preprocessing settings such as Byte Pair Encoding (BPE). In this study, we propose an automatic tuning method modeled after Darwin's Survival of the Fittest Theory via a Genetic Algorithm (GA). Research results show that the proposed method, a GA, outperforms a random selection of hyperparameters.
Abstract: Mainstream machine learning conferences have seen a dramatic increase in the number of participants, along with a growing range of perspectives, in recent years. Members of the machine learning community are likely to overhear allegations ranging from randomness of acceptance decisions to institutional bias. In this work, we critically analyze the review process through a comprehensive study of papers submitted to ICLR between 2017 and 2020. We quantify reproducibility and randomness in review scores and acceptance decisions, and examine whether scores correlate with paper impact. Our findings suggest strong institutional bias in accept/reject decisions, even after controlling for paper quality. Furthermore, we find evidence for a gender gap, with female authors receiving lower scores, lower acceptance rates, and fewer citations per paper than their male counterparts. We conclude our work with recommendations for future conference organizers.
Abstract: In everyday tasks, we often depend on sensors and other tools to provide us accurate measurements for a variety of tasks ranging from driving down the street to launching the next rocket to space. Naturally, with these sensors comes slight inaccuracies that will be referred to throughout as noise. Throughout this study, we provide an empirical comparison between two common filtering techniques to remove this noise: a kalman filter and moving average filter.
