Pradeep Dogga

Research Lab 486
404 Westwood Plaza
Los Angeles, California 90095
dogga@cs.ucla.edu

I am a final year Ph.D. candidate at the Computer Science Department at UCLA. My research interests are broadly in using ML and NLP techniques to improve networks and systems. My PhD thesis focus is on assisting end-to-end debugging workflows in production distributed systems. I am advised by George Varghese and Ravi Netravali. Prior to joining UCLA, I received my B.Tech.(Hons.) from the Computer Science and Engineering Department at Indian Institute of Technology, Kharagpur where I was advised by Sandip Chakraborty and Subrata Mitra.


Industrial Research

AWS: Reasoning Performance Degradations In AWS Redshift
Applied Scientist Intern, Summer'23, AWS Redshift.

Microsoft: Automated Root-Cause Labelling of Incidents in Microsoft Azure
Research Intern, Summer'22, MSR Redmond.

Google: Root-cause Analysis of Global Network Bad-Minutes
Research Intern, Summer'21, CoreInfra Group.
Student Researcher, Fall'21, CoreInfra Group.

Adobe: Optimizing Containing Performance in the Cloud
Research Intern, Summer'18, BigData Experience Lab.

Adobe: (Best Overall Project Award) Personalized E-learning Curricula using Knowledge Tracing and Hint-Taking Propensity
Research Intern, Summer'17, BigData Experience Lab.


Publications

AutoARTS: Taxonomy, Insights and Tools for Root Cause Labelling of Incidents in Microsoft Azure
Dogga, P., Bansal, C., Costleigh, R., Jayagopal, G., Nath, S., and Zhang, X.
(USENIX ATC 23) Proceedings of 2023 USENIX Annual Technical Conference

Revelio: ML-Generated Debugging Queries for Distributed Systems
Dogga, P., Narasimhan, K., Sivaraman, A., Saini, S.K., Varghese, G., and Netravali, R.
(MLSys 22) Proceedings of Machine Learning and Systems

A System-Wide Debugging Assistant Powered by Natural Language Processing
Dogga, P., Narasimhan, K., Sivaraman, A., and Netravali, R.
(SoCC 19) ACM Symposium of Cloud Computing

Edge-based Transcoding for Adaptive Live Video Streaming
Dogga, P., Chakraborty, S., Mitra, S. and Netravali, R.
(HotEdge 19) 2nd USENIX Workshop on Hot Topics in Edge Computing

CL Scholar: The ACL Anthology Knowledge Graph Miner
Singh, M., Dogga, P., Patro, S., Barnwal, D., Dutt, R., Haldar, R., Goyal, P. and Mukherjee, A.
(NAACL-HLT 18) North American Chapter of the Association for Computational Linguistics: Demonstrations

Modeling Hint-Taking Behavior and Knowledge State of Students with Multi-Task Learning
Chaudhry, R., Singh, H., Dogga, P. and Saini, S.K.
(EDM 18) International Educational Data Mining Society


Research


A System-Wide Debugging Assistant Powered by Natural Language Processing

Despite advances in debugging tools, systems debugging today remains largely manual. A developer typically follows an iterative and time-consuming process to move from a reported bug to a bug fix. This is because developers are still responsible for making sense of system-wide semantics, bridging together outputs and features from existing debugging tools, and extracting information from many diverse data sources (e.g., bug reports, source code, comments, documentation, and execution traces). We believe that the latest statistical natural language processing (NLP) techniques can help automatically analyze these data sources and significantly improve the systems debugging experience. We present early results to highlight the promise of NLP-powered debugging, and discuss systems and learning challenges that must be overcome to realize this vision.

Overview of the proposed NLP-Powered debugging assistant



Edge-based Transcoding for Adaptive Live Video Streaming

User-generated video content is imposing an increasing burden on live video service architectures such as Facebook Live. These services are responsible for ingesting large amounts of video, transcoding that video into different quality levels (i.e., bitrates), and adaptively streaming it to viewers. These tasks are expensive, both computationally and network-wise, often forcing service providers to sacrifice the ``liveness'' of delivered video. Given the steady increases in smartphone bandwidth and energy resources, coupled with the fact that commodity smartphones now include hardware-accelerated codecs, we propose that live video services augment their existing infrastructure with edge support for transcoding and transmission. We present measurements to motivate the feasibility of incorporating such edge-support into the live video ecosystem, present the design of a peer-to-peer adaptive live video streaming system, and discuss directions for future work to realize this vision in practice.

Existing Live Video Streaming Infrastructure



Proposed Edge-based Live Video Streaming Infrastructure using Hardware Accelerated Codecs and P2P Streaming



Awards

2018-2019 UCLA Graduate Division Fellowship
2017 Best Overall Project Award, Adobe Research-India
2016 Best Intern, Smartron-India
2014 Inspire Fellowship Awardee, Govt of India
2012 Rank 6 in South Indian Chemistry Olympiad (SIChO)
2012 Rank 9 in South Indian Mathematics Olympiad (SIMO)