|
|
Harsha Vardhan Simhadri
Senior Principal Researcher, Microsoft
Interests
I develop new algorithms with a view towards future platforms and practical systems. A few examples:
- Efficient algorithms for web-scale nearest-neighbor search deployed widely in Microsoft and elsewhere (DiskANN)
- New ML operators and architectures for tiny IoT and edge devices (EdgeML)
- Parallel algorithms and run-times with provable guarantees for multi-core processors (PhD thesis)
I lead the organization of the 2023 Big ANN NeurIPS challenge on Approximate Nearest Neighbor Search.
If you have a strong ANNS algorithm, please submit your idea through this evaluation framework.
Slides on DiskANN from recent seminars and a recording from Northwestern IDEAL workshop.
Publications
-
Scaling Graph-Based ANNS Algorithms to Billion-Size Datasets: A Comparative Analysis
(with Magdalen Dobson, Zheqi Shen, Guy E. Blelloch, Laxman Dhulipala, Yan Gu, Yihan Sun)
-
Filtered-DiskANN: Graph Algorithms for Approximate Nearest Neighbor Search with Filters
WWW'23 (with Siddharth Gollapudi, Neel Karia, Varun Sivashankar, Ravishankar Krishnaswamy,
Nikit Begwani, Swapnil, Raz, Yiyong Lin, Yin Zhang, Neelam Mahapatro, Premkumar Srinivasan,
Amit Singh)
-
Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search
(with George Williams, Martin Aumüller, Matthijs Douze, Artem Babenko,
Dmitry Baranchuk, Qi Chen, Lucas Hosseini, Ravishankar Krishnaswamy, Gopal Srinivasa,
Suhas Jayaram Subramanya, Jingdong Wang)
-
FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Search
(with Aditi Singh, Suhas Jayaram Subramanya and Ravishankar Krishnaswamy)
-
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference (code)
NeurIPS'20 (with Oindrila Saha, Aditya Kusupati, Manik Varma and Prateek Jain)
-
DROCC: Deep Robust One-Class Classification (code)
ICML'20 (with Sachin Goyal, Aditi Raghunathan, Moksh Jain and Prateek Jain)
-
DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node (code)
NeurIPS'19 (with Suhas Jayaram Subramanya, Devvrit, Rohan Kadekodi and Ravishankar Krishnawamy)
-
Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices
NeurIPS'19 (Don Dennis, Durmus Alp, Emre Acar, Vikram Mandikal, Vinu Sankar Sadasivan, Venkatesh Saligrama and Prateek Jain)
-
GesturePod: Programmable Gesture Recognition for Augmenting Assistive Devices
(code)
ACM UIST'19 (with Shishir Patil, Don Kurian Dennis, Chirag Pabbaraju, Rajanikant Deshmukh, Manik Varma, Prateek Jain)
-
Word2Sense : Sparse Interpretable Word Embeddings
ACL'19 (with Abhishek Panigrahi, Chiranjib Bhattacharyya)
-
BLAS-on-flash : An Efficient Alternative for Large Scale ML Training and Inference?
(code)
NSDI'19 (with Suhas Jayaram Subramanya, Srajan Garg, Anil Kag, Venkatesh Balasubramanian)
- Multiple Instance Learning for Efficient Sequential Data Classification on Resource-Constrained Devices
(code)
NeurIPS'18 (with Don Kurian Dennis, Chirag Pabbaraju, Prateek Jain)
- Provably Efficient Scheduling of Dynamically Allocating Programs on Parallel Cache Hierarchies
HiPC '17 (with Guy Blelloch, Phillip Gibbons)
- ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices
(code)
ICML '17
(with Chirag Gupta, Arun Sai Suggala, Ankit Goyal,
Bhargavi Paranjape, Ashish Kumar, Saurabh Goyal, Raghavendra Udupa, Manik Varma, Prateek Jain)
- Extending the Nested Parallel Model to the Nested Dataflow Model with Provably Efficient Schedulers
ACM SPAA'16 (with David Dinh and Yuan Tang)
- Write-Avoiding Algorithms
(poster)
(conference version)
IPDPS '16
(with Erin Carson, James Demmel, Laura Grigori, Nicholas Knight,
Penporn Koanantakool and Oded Schwartz)
- Experimental Analysis of Space-Bounded Schedulers
(conference version)
(code)
ACM SPAA '14 (with Guy E. Blelloch, Jeremy T. Fineman, Phillip B. Gibbons and Aapo Kyrola)
Invited to the ACM Transaction on Parallel Computing best papers issue, 2016, 3(1).
- Program-Centric Cost Models for Locality
ACM MSPC'13 workshop (with Guy E. Blelloch, Jeremy T. Fineman and Phillip B. Gibbons)
- Brief announcement: the problem based benchmark suite
ACM SPAA '12 (with Julian Shun, Guy E. Blelloch, Jeremy T. Fineman, Phillip B. Gibbons, Aapo Kyrola, and Kanat Tangwongsan)
- Parallel and I/O efficient set covering algorithms
ACM SPAA '12 (with Guy E. Blelloch and Kanat Tangwongsan)
- Scheduling Irregular Parallel Computations on Hierarchical Caches
(Tech Report)
ACM SPAA '11 (with Guy E. Blelloch, Jeremy T. Fineman and Phillip B. Gibbons)
Tech Report: CMU-CS-10-154
- Low Depth Cache Oblivious Algorithms
(conference version)
Tech Report: CMU-CS-09-134 (with Guy E. Blelloch and Phillip B. Gibbons)
ACM SPAA '10
- Combinable Memory-Block Transactions
ACM SPAA '08 (with Guy E. Blelloch and Phillip B. Gibbons)
- Towards optimal and efficient perfectly secure message transmission
Theory of Cryptography Conference 2007 (with Mattias Fitzi, Mathew Franklin and Juan Garay)
Thesis
Program-Centric Cost Models for Locality and Parallelism
Students I have worked with
Grace Dinh,
Chirag Gupta,
Srajan Garg,
Don Dennis,
Shishir Patil,
Suhas Jayaram Subramanya,
Abhishek Panigrahi,
Saching Goyal, Moksh Jain, Oindrila Saha, Aditi Singh
Teaching Assistant
- 15-750: Graduate Algorithms (Spring 2011)
- 15-499: Parallel Algorithms (Spring 2009)
Earlier
2013-2016: Postdoctoral Fellow, CS Department, Lawrence Berkeley National Lab.
2007-2013: Ph.D., CS Department, Carnegie Mellon University, Advisor: Guy Blelloch
2003-2007: B.Tech, IIT Madras, Major: CS, Minor: Physics.
|