Scholar
Benjamin Coleman
Google Scholar ID: fInuVkEAAAAJ
Google DeepMind
Citations & Impact
Citations
1,551
H-index
16
i10-index
21
Publications
20
Co-authors
4
list available
Contact
Publications
Cited
0
Resume (English only)
Academic Achievements
- One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams (ICML22)
- Practical Near Neighbor Search via Group Testing (NeurIPS21, Spotlight Talk - Top 3%)
- A One-Pass Distributed and Private Sketch for Kernel Sums with Applications to Machine Learning at Scale (CCS21)
- Sub-linear RACE Sketches for Approximate Kernel Density Estimation on Streaming Data (WWW20)
- Sub-linear Memory Sketches for Near Neighbor Search on Streaming Data (ICML20)
- Revisiting Consistent Hashing with Bounded Loads (AAAI21)
- Fast processing and querying of 170TB of genomics data via a repeated and merged bloom filter (RAMBO) (SIGMOD21)
Research Experience
- Current work focuses on efficient approximate algorithms for low-level building blocks of machine learning, such as kernel sums and near-neighbor search, as well as fast training and inference.
Background
- Interested in randomized algorithms for scalable machine learning. By replacing expensive exact algorithms with lightweight approximate methods, the resources needed to run a program can be substantially reduced. Particularly interested in simple methods with theoretical guarantees that also work well in a web-scale production environment.
