2025

  1. EuroSys FLEX: Fast, Accurate DNN Inference on Low-Cost Edges Using Heterogeneous Accelerator Execution
    Tanmoy Sen, Haiying Shen, and Anand Padmanabha Iyer
    In Proceedings of the 20th European Conference on Computer Systems (EuroSys), Mar 2025
    Paper
  2. Preprint ReInc: Scaling Training of Dynamic Graph Neural Networks
    Mingyu Guan, Saumia Singhal, Taesoo Kim, and Anand Padmanabha Iyer
    In arXiv (Preprint), Jan 2025
    Paper
  3. Preprint OMEGA: A Low-Latency GNN Serving System for Large Graphs
    Geon-Woo Kim, Donghyun Kim, Jeongyoon Moon, Henry Liu, Tarannum Khan, Anand Padmanabha Iyer, Daehyeok Kim, and Aditya Akella
    In arXiv (Preprint), Jan 2025
    Paper

2024

  1. CoNEXT PACER: Accelerating Distributed GNN Training Using Communication-Efficient Partition Refinement and Caching
    Shohaib Mahmud, Haiying Shen, and Anand Padmanabha Iyer
    In Proceedings of the International Conference on emerging Networking EXperiments and Technologies (CoNEXT), Dec 2024
  2. Preprint Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection
    Vima Gupta, Kartik Sinha, Ada Gavrilovska, and Anand Padmanabha Iyer
    In arXiv (Preprint), Nov 2024
    Paper
  3. SOSP Improving DNN Inference Throughput Using Practical, Per-Input Compute Adaptation
    Anand Padmanabha Iyer, Mingyu Guan, Yinwei Dai, Rui Pan, Swapnil Gandhi, and Ravi Netravali
    In Proceedings of the 30th Symposium on Operating Systems Principles (SOSP), Nov 2024
    Paper
  4. SOSP Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving
    Yinwei Dai, Rui Pan Pan, Anand Padmanabha Iyer, Kai Li, and Ravi Netravali
    In Proceedings of the 30th Symposium on Operating Systems Principles (SOSP), Nov 2024
    Paper
  5. OSDI USHER: Holistic Interference Avoidance for Resource Optimized ML Inference
    Sudipta Saha Shubha, Haiying Shen, and Anand Padmanabha Iyer
    In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI), Jul 2024
    Paper Slides Talk
  6. IPDPS Proactive, Accuracy-aware Straggler Mitigation in Machine Learning Clusters
    Suraiya Tairin, Haiying Shen, and Anand Padmanabha Iyer
    In Proceedings of the 38th IEEE International Parallel & Distributed Processing Symposium (IPDPS), May 2024
  7. NSDI Vulcan: Automatic Query Planning for Live ML Analytics
    Yiwen Zhang, Xumiao Zhang, Ganesh Ananthanarayanan, Anand Padmanabha Iyer, Yuanchao Shu, Victor Bahl, Z. Morley Mao, and Mosharaf Chowdhury
    In Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI), Apr 2024
    Paper Slides Talk

2023

  1. NSDI Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge
    Arthi Padmanabhan, Neil Agarwal, Anand Padmanabha Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing Harry Xu, and Ravi Netravali
    In Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI), Apr 2023
    Paper Slides Talk

2022

  1. GRADES-NDA DynaGraph: Dynamic Graph Neural Networks at Scale
    Mingyu Guan, Anand Padmanabha Iyer, and Taesoo Kim
    In Proceedings of the 5th ACM SIGMOD Joint International Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA) (GRADES-NDA), 2022
    Paper Slides

2021

  1. HotEdgeVideo Towards Memory-Efficient Inference in Edge Video Analytics
    Arthi Padmanabhan, Anand Padmanabha Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing Harry Xu, and Ravi Netravali
    In Proceedings of the 3rd ACM Workshop on Hot Topics in Video Analytics and Intelligent Edges (HotEdgeVideo), 2021
    Paper
  2. OSDI P3: Distributed Deep Graph Learning at Scale
    Swapnil Gandhi, and Anand Padmanabha Iyer
    In Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI), Jul 2021
    Paper Slides Talk
  3. NSDI TEGRA: Efficient Ad-Hoc Analytics on Evolving Graphs
    Anand Padmanabha Iyer, Qifan Pu, Kishan Patel, Joseph E. Gonzalez, and Ion Stoica
    In Proceedings of the 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI), Apr 2021
    Paper Slides Talk

2019

  1. Thesis Scalable Systems for Large Scale Dynamic Connected Data Processing
    Anand Padmanabha Iyer
    PhD Thesis, University of California at Berkeley (Thesis), 2019
    Paper
  2. Preprint Enriching Driving Experience with Cloud Assistance
    Anand Padmanabha Iyer, Srikanth Kandula, Paramvir Bahl, and Ion Stoica
    (Preprint) 2019
    Paper

2018

  1. MobiCom Mitigating the Latency-Accuracy Trade-off in Mobile Data Analytics Systems
    Anand Padmanabha Iyer, Li Erran Li, Mosharaf Chowdhury, and Ion Stoica
    In Proceedings of the 24th Annual International Conference on Mobile Computing and Networking (MobiCom), 2018
    Paper Slides Talk
  2. OSDI ASAP: Fast, Approximate Graph Pattern Mining at Scale
    Anand Padmanabha Iyer, Zaoxing Liu, Xin Jin, Shivaram Venkataraman, Vladimir Braverman, and Ion Stoica
    In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation (OSDI), Oct 2018
    Paper Slides Talk Press
  3. HotCloud Monarch: Gaining Command on Geo-Distributed Graph Analytics
    Anand Padmanabha Iyer, Aurojit Panda, Mosharaf Chowdhury, Aditya Akella, Scott Shenker, and Ion Stoica
    In Proceedings of the 10th USENIX Conference on Hot Topics in Cloud Computing (HotCloud), 2018
    Paper Slides
  4. HotCloud Towards Fast and Scalable Graph Pattern Mining
    Anand Padmanabha Iyer, Zaoxing Liu, Xin Jin, Shivaram Venkataraman, Vladimir Braverman, and Ion Stoica
    In Proceedings of the 10th USENIX Conference on Hot Topics in Cloud Computing (HotCloud), 2018
    Paper Slides
  5. GRADES-NDA Bridging the GAP: Towards Approximate Graph Analytics
    Anand Padmanabha Iyer, Aurojit Panda, Shivaram Venkataraman, Mosharaf Chowdhury, Aditya Akella, Scott Shenker, and Ion Stoica
    In Proceedings of the 1st ACM SIGMOD Joint International Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA) (GRADES-NDA), 2018
    Paper Slides

2017

  1. SOSP-SRC Time-evolving Graph Processing on Commodity Clusters
    Anand Padmanabha Iyer
    ACM SOSP Student Research Competition (SRC) (SOSP-SRC), 2017
    Paper
  2. MobiCom Automating Diagnosis of Cellular Radio Access Network Problems
    Anand Padmanabha Iyer, Li Erran Li, and Ion Stoica
    In Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking (MobiCom), 2017
    Paper Slides
  3. SoCC A Scalable Distributed Spatial Index for the Internet-of-Things
    Anand Padmanabha Iyer, and Ion Stoica
    In Proceedings of the 2017 Symposium on Cloud Computing (SoCC), 2017
    Paper Slides

2016

  1. GRADES-NDA Time-Evolving Graph Processing at Scale
    Anand Padmanabha Iyer, Li Erran Li, Tathagata Das, and Ion Stoica
    In Proceedings of the Fourth International Workshop on Graph Data Management Experiences and Systems (GRADES-NDA), 2016
    Paper Slides Press
  2. Fast and Accurate Performance Analysis of LTE Radio Access Networks
    Anand Padmanabha Iyer, Ion Stoica, Mosharaf Chowdhury, and Li Erran Li
    2016
    arXiv

2015

  1. SoCC FastLane: Making Short Flows Shorter with Agile Drop Notification
    David Zats, Anand Padmanabha Iyer, Ganesh Ananthanarayanan, Rachit Agarwal, Randy Katz, Ion Stoica, and Amin Vahdat
    In Proceedings of the Sixth ACM Symposium on Cloud Computing (SoCC), 2015
    Paper
  2. NSDI CellIQ: Real-Time Cellular Network Analytics at Scale
    Anand Padmanabha Iyer, Li Erran Li, and Ion Stoica
    In Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI), May 2015
    Paper Slides

2013

  1. SenSys Carat: Collaborative Energy Diagnosis for Mobile Devices
    Adam J. Oliner, Anand Padmanabha Iyer, Ion Stoica, Eemil Lagerspetz, and Sasu Tarkoma
    In Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems (SenSys), 2013
    Paper Code Press

2012

  1. HotDep Collaborative Energy Debugging for Mobile Devices
    Adam J. Oliner, Anand Padmanabha Iyer, Eemil Lagerspetz, Sasu Tarkoma, and Ion Stoica
    In Proceedings of the Eighth USENIX Conference on Hot Topics in System Dependability (HotDep), 2012
    Paper Code
  2. VLDB Blink and It’s Done: Interactive Queries on Very Large Data
    Sameer Agarwal, Anand Padmanabha Iyer, Aurojit Panda, Samuel Madden, Barzan Mozafari, and Ion Stoica
    Proc. VLDB Endow. (VLDB), Aug 2012
    Paper

2011

  1. NSDI SpecNet: Spectrum Sensing Sans Frontieres
    Anand Padmanabha Iyer, Krishna Chintalapudi, Vishu Navda, Ramachandran Ramjee, Venkata N. Padmanabhan, and Chandra R. Murthy
    In Proceedings of the Eighth USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2011
    Paper Slides Talk

2010

  1. MobiCom Indoor Localization without the Pain
    Krishna Chintalapudi, Anand Padmanabha Iyer, and Venkata N. Padmanabhan
    In Proceedings of the Sixteenth Annual International Conference on Mobile Computing and Networking (MobiCom), 2010
    Paper
  2. GLOBECOM Cyclostationary-Based Architectures for Spectrum Sensing in IEEE 802.22 WRAN
    Deepa B., Anand Padmanabha Iyer, and Chandra R. Murthy
    In 2010 IEEE Global Telecommunications Conference GLOBECOM 2010 (GLOBECOM), 2010

2009

  1. IWQoS Fast Resilient Jumbo frames in wireless LANs
    Anand Padmanabha Iyer, Gaurav Deshpande, Eric Rozner, Apurv Bhartia, and Lili Qiu
    In 17th International Workshop on Quality of Service (IWQoS), 2009
    Paper Slides
  2. IWCMC Handling Mobility across WiFi and WiMAX
    Anand Padmanabha Iyer, and Jayaraman Iyer
    In Proceedings of the 2009 International Conference on Wireless Communications and Mobile Computing: Connecting the World Wirelessly (IWCMC), 2009
    Paper

2008

  1. Thesis Efficient Transmissions & Recovery in Wireless LAN
    Anand Padmanabha Iyer
    Masters Thesis, The University of Texas at Austin (Thesis), May 2008
    Paper

2007

  1. CoNEXT ER: Efficient Retransmission Scheme for Wireless LANs
    Eric Rozner, Anand Padmanabha Iyer, Yogita Mehta, Lili Qiu, and Mansoor Jafry
    In Proceedings of the 2007 ACM CoNEXT Conference (CoNEXT), 2007
    Paper