Timezone: »

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
Eran Malach · Pritish Kamath · Emmanuel Abbe · Nati Srebro

Thu Jul 22 05:35 AM -- 05:40 AM (PDT) @

We study the relative power of learning with gradient descent on differentiable models, such as neural networks, versus using the corresponding tangent kernels. We show that under certain conditions, gradient descent achieves small error only if a related tangent kernel method achieves a non-trivial advantage over random guessing (a.k.a. weak learning), though this advantage might be very small even when gradient descent can achieve arbitrarily high accuracy. Complementing this, we show that without these conditions, gradient descent can in fact learn with small error even when no kernel method, in particular using the tangent kernel, can achieve a non-trivial advantage over random guessing.

Author Information

Eran Malach (Hebrew University Jerusalem Israel)
Pritish Kamath (Google Research)
Emmanuel Abbe
Nati Srebro (Toyota Technological Institute at Chicago)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors