Unverified50% confidenceBenchmarkExact time
Across six backtesting experiments, applying Ledoit-Wolf shrinkage reduced portfolio turnover by up to 57%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedDistilBERT reduces BERT's parameter count by 40% through distillation, increases inference speed by 60%, and incurs only approximately 3% performance loss65% similarUnverifiedThe compute cost per unit of inference is declining at a rate of 40% to 60% per year.64% similarVerifiedIn long-chain tasks, if each step has an error rate of approximately 5%, the overall success rate may drop to below 36% after 20 steps.64% similarUnverifiedModel inference costs are declining at a rate of approximately 50% per year.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/891765API
curl https://kongchang.com/api/v1/knowledge/claims/891765MCP
get_claim(id=891765)