Conference
Proteus: agile ML elasticity through tiered reliability in dynamic resource markets
Provably Efficient Scheduling of Dynamically Allocating Programs on Parallel Cache Hierarchies
Buddy-RAM: Improving the Performance and Efficiency of Bulk Bitwise Operations Using DRAM
GeePS: Scalable deep learning on distributed GPUs with a GPU-specialized parameter server
Bandwidth-Efficient Distributed <i>k</i>-Nearest-Neighbor Search with Dynamic Time Warping