Robust distributed orthogonalization based on randomized aggregation

Authors:
Wilfried N. Gansterer;Gerhard Niederbrucker;Hana Straková;Stefan Schulze Grotthoff
Affiliations:
University of Vienna, Vienna, Austria;University of Vienna, Vienna, Austria;University of Vienna, Vienna, Austria;University of Vienna, Vienna, Austria
Venue:
Proceedings of the second workshop on Scalable algorithms for large-scale systems
Year:
2011

Citing 19
Cited 0

Diskless Checkpointing

IEEE Transactions on Parallel and Distributed Systems
Randomized rumor spreading

FOCS '00 Proceedings of the 41st Annual Symposium on Foundations of Computer Science
Improving the performance of coordinated checkpointers on networks of workstations using RAID techniques

SRDS '96 Proceedings of the 15th Symposium on Reliable Distributed Systems
Gossip-Based Computation of Aggregate Information

FOCS '03 Proceedings of the 44th Annual IEEE Symposium on Foundations of Computer Science
Gossip-based aggregation in large dynamic networks

ACM Transactions on Computer Systems (TOCS)
Computing separable functions via gossip

Proceedings of the twenty-fifth annual ACM symposium on Principles of distributed computing
Randomized gossip algorithms

IEEE/ACM Transactions on Networking (TON) - Special issue on networking and information theory
A decentralized algorithm for spectral analysis

Journal of Computer and System Sciences
Algorithm-Based Fault Tolerance for Matrix Operations

IEEE Transactions on Computers
Gossiping in distributed systems

ACM SIGOPS Operating Systems Review - Gossip-based computer networking
Algorithm-Based Fault Tolerance for Fail-Stop Failures

IEEE Transactions on Parallel and Distributed Systems
Fault-Tolerant Aggregation by Flow Updating

DAIS '09 Proceedings of the 9th IFIP WG 6.1 International Conference on Distributed Applications and Interoperable Systems
Gossip Algorithms

Foundations and Trends® in Networking
Broadcast gossip algorithms for consensus

IEEE Transactions on Signal Processing
Convergence Speed in Distributed Consensus and Averaging

SIAM Journal on Control and Optimization
Algorithm-based recovery for iterative methods without checkpointing

Proceedings of the 20th international symposium on High performance distributed computing
Uncoordinated Checkpointing Without Domino Effect for Send-Deterministic MPI Applications

IPDPS '11 Proceedings of the 2011 IEEE International Parallel & Distributed Processing Symposium
Geographic Gossip: Efficient Averaging for Sensor Networks

IEEE Transactions on Signal Processing
Distributed QR factorization based on randomized algorithms

PPAM'11 Proceedings of the 9th international conference on Parallel Processing and Applied Mathematics - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The construction of distributed algorithms for matrix computations built on top of distributed data aggregation algorithms with randomized communication schedules is investigated. For this purpose, a new aggregation algorithm for summing or averaging distributed values, the push-flow algorithm, is developed, which achieves superior resilience properties with respect to node failures compared to existing aggregation methods. On a hypercube topology it asymptotically requires the same number of iterations as the optimal all-to-all reduction operation and it scales well with the number of nodes. Orthogonalization is studied as a prototypical matrix computation task. A new fault tolerant distributed orthogonalization method (rdmGS), which can produce accurate results even in the presence of node failures, is built on top of distributed data aggregation algorithms.