Training Throughput
Cross-source consensus on Training Throughput from 1 sources and 4 claims.
1 sources · 4 claims
How it works
Benefits
Highlighted claims
- DriftXpress preserved sample quality close to standard drifting while substantially increasing throughput. — DriftXpress: Faster Drifting Models via Projected RKHS Fields
- Profiling on CIFAR10 found large reductions in field-estimation time for sharded and unsharded DriftXpress. — DriftXpress: Faster Drifting Models via Projected RKHS Fields
- Wall-clock convergence improved on SVHN, CIFAR10, and CIFAR100. — DriftXpress: Faster Drifting Models via Projected RKHS Fields
- Projected attraction is described as smoother and more stable because it uses a cached summary of the full positive support rather than mini-batch positives. — DriftXpress: Faster Drifting Models via Projected RKHS Fields