Unverified50% confidenceBenchmarkExact time
In experiments where all other conditions were held constant and only the update rule was replaced, Phase-HDC achieved the accuracy of 6-bit momentum Adam while reducing memory to one-third.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPhase-HDC loses approximately 5 accuracy points on average relative to float32 Adam.77% similarUnverifiedAcross eleven datasets spanning images, tabular data, and text, Phase-HDC reduces memory by 16–23× compared to standard float32 Adam and by 4–6× compared to 8-bit Adam.72% similarVerified4-bit quantization reduces model size to 1/8 of the original at the cost of approximately 1–3% accuracy loss.66% similarUnverifiedAfter rebuilding the configuration under the same public identifier on the same day, the model-minus-uniform endpoint value decreased by 0.0429 (H-minus-R comparison 95% CI: [+0.0182, +0.0667]), and with six configuration components changing simultaneously it was impossible to isolate which component caused the difference.65% similarUnverified领域微调后的7B模型在任务准确率上往往超越未经微调的70B通用模型，同时推理成本降低一个数量级64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990626API
curl https://kongchang.com/api/v1/knowledge/claims/990626MCP
get_claim(id=990626)