Tim Kaler bio photo

Tim Kaler

I'm a postdoctoral associate at MIT in the EECS department and a member of the Supertech research group within the Computer Science and Artificial Intelligence Laboratory (CSAIL). You can contact me via email at tfk (at) mit (dot) edu.

Email

Publications

  1. Accelerating training and inference of graph neural networks with fast sampling and pipelining
    Tim Kaler, Nickolas Stathas, Anne Ouyang, Alexandros-Stavros Iliopoulos, Tao Schardl, Charles E. Leiserson & Jie Chen. 2022. Accelerating training and inference of graph neural networks with fast sampling and pipelining. Proceedings of Machine Learning and Systems 4. 172–189.
  2. PARAD: A Work-Efficient Parallel Algorithm for Reverse-Mode Automatic Differentiation
    Tim Kaler, Tao B. Schardl, Brian Xie, Charles E. Leiserson, Jie Chen, Aldo Pareja & Georgios Kollias. 2021. PARAD: A Work-Efficient Parallel Algorithm for Reverse-Mode Automatic Differentiation. In Symposium on Algorithmic Principles of Computer Systems, SIAM.
  3. Evolvegcn: Evolving graph convolutional networks for dynamic graphs
    Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, … Charles Leiserson. 2020. Evolvegcn: Evolving graph convolutional networks for dynamic graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 5363–5370.
  4. High-Throughput Image Alignment for Connectomics using Frugal Snap Judgments Best student paper
    Tim Kaler, Brian Wheatman & Sarah Wooders. 2020. High-Throughput Image Alignment for Connectomics using Frugal Snap Judgments. In 2020 IEEE High Performance Extreme Computing Conference (HPEC), IEEE.
  5. Cilkmem: Algorithms for analyzing the memory high-water mark of fork-join parallel programs Best paper finalist
    Tim Kaler, William Kuszmaul, Tao B. Schardl & Daniele Vettorel. 2020. Cilkmem: Algorithms for analyzing the memory high-water mark of fork-join parallel programs. In Symposium on Algorithmic Principles of Computer Systems, 162–176. SIAM.
  6. High-throughput image alignment for connectomics using frugal snap judgments: poster
    Tim Kaler, Brian Wheatman & Sarah Wooders. 2019. High-throughput image alignment for connectomics using frugal snap judgments: poster. In Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming, 433–434. ACM.
  7. Scalable Graph Learning for Anti-Money Laundering: A First Look
    Mark Weber, Jie Chen, Toyotaro Suzumura, Aldo Pareja, Tengfei Ma, Hiroki Kanezashi, … Tao B. Schardl. 2018. Scalable Graph Learning for Anti-Money Laundering: A First Look. ArXiv Preprint ArXiv:1812.00076.
  8. A multicore path to connectomics-on-demand Best paper finalist
    Alexander Matveev, Yaron Meirovitch, Hayk Saribekyan, Wiktor Jakubiuk, Tim Kaler, Gergely Odor, … Nir Shavit. 2017. A multicore path to connectomics-on-demand. In Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, 267–281. ACM.
  9. Optimal Reissue Policies for Reducing Tail Latency
    Tim Kaler, Yuxiong He & Sameh Elnikety. 2017. Optimal Reissue Policies for Reducing Tail Latency. In Proceedings of the 29th ACM Symposium on Parallelism in Algorithms and Architectures, 195–206. ACM.
  10. Executing dynamic data-graph computations deterministically using chromatic scheduling
    Tim Kaler, William Hasenplaugh, Tao B. Schardl & Charles E. Leiserson. 2016. Executing dynamic data-graph computations deterministically using chromatic scheduling. ACM Transactions on Parallel Computing (TOPC) 3(1). 2.
  11. Polylogarithmic Fully Retroactive Priority Queues via Hierarchical Checkpointing
    Erik D. Demaine, Tim Kaler, Quanquan Liu, Aaron Sidford & Adam Yedidia. 2015. Polylogarithmic Fully Retroactive Priority Queues via Hierarchical Checkpointing. In Workshop on Algorithms and Data Structures, 263–275. Springer.
  12. Ordering heuristics for parallel graph coloring
    William Hasenplaugh, Tim Kaler, Tao B. Schardl & Charles E. Leiserson. 2014. Ordering heuristics for parallel graph coloring. In Proceedings of the 26th ACM symposium on Parallelism in algorithms and architectures, 166–177. ACM.
  13. Executing dynamic data-graph computations deterministically using chromatic scheduling
    Tim Kaler, William Hasenplaugh, Tao B. Schardl & Charles E. Leiserson. 2014. Executing dynamic data-graph computations deterministically using chromatic scheduling. In Proceedings of the 26th ACM symposium on Parallelism in algorithms and architectures, 154–165. ACM.
  14. Chromatic scheduling of dynamic data-graph computations
    Tim Kaler. 2013. Chromatic scheduling of dynamic data-graph computations. Massachusetts Institute of Technology dissertation.
  15. Spatial Data Structures-Performance Comparision
    Tim Kaler & Oscar Moll. 2012. Spatial Data Structures-Performance Comparision. O. Moll (Ed.).
  16. Code in the air: simplifying sensing on smartphones
    Tim Kaler, John Patrick Lynch, Timothy Peng, Lenin Ravindranath, Arvind Thiagarajan, Hari Balakrishnan & Sam Madden. 2010. Code in the air: simplifying sensing on smartphones. In Proceedings of the 8th ACM Conference on Embedded Networked Sensor Systems, 407–408. ACM.
  17. Cache Efficient Bloom Filters for Shared Memory Machines
    Tim Kaler. Cache Efficient Bloom Filters for Shared Memory Machines.

Also available on Google Scholar