Back to timeline

Research · July 1992

The kernel trick and support vectors

The authors showed that a maximum-margin linear classifier can be applied to nonlinear problems without ever constructing the high-dimensional space explicitly.

Why it matters

A method with proven guarantees appeared that beat networks in practice, and networks were set aside a second time for a decade.

A kernel function computes an inner product in feature space without building the features, so the cost does not depend on that space's dimension. The training problem becomes convex, meaning it has a single optimum, unlike networks where the result depends on initial weights and chance. That reproducibility is what made support vectors the standard of the 1990s.

Event record

Event date
July 1992
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0166

Presented at COLT in July 1992.

Sources

Related events

Records that link to this one