Unverified50% confidenceFactExact time
The exponential decay kernel maps time differences to decayed feature values, giving recent events higher weight and preventing timestamp values from growing unbounded.
1
Sources
50%
Confidence
Long-term
Relevance
10/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWeighted conformal prediction approximates a weakened version of the exchangeability condition by assigning weights to historical samples based on temporal decay or similarity.73% similarUnverifiedA loss spike is a lagging indicator; by the time a prominent spike appears in the loss curve, the underlying numerical deviation may have already accumulated and propagated for a considerable amount of time.72% similarUnverifiedExpressing model capability gaps in terms of time lag is more easily understood and communicated than relying solely on benchmark scores.71% similarUnverifiedVelocity scaling and shifting the model time backward are essentially two equivalent approaches to addressing the population time lag problem.71% similarUnverifiedFor finite step sizes, even if a stationary point is unstable under continuous-time gradient flow, if the step size is too large it may skip over the escape direction and cause numerical divergence, while if the step size is too small the escape time may grow exponentially and appear as stagnation.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1095041API
curl https://kongchang.com/api/v1/knowledge/claims/1095041MCP
get_claim(id=1095041)