AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Statistical-Query Lower Bounds via Functional Gradients

Surbhi Goel, Aravind Gollakota, Adam Klivans

NeurIPS 2020 · Learning theory and algorithms › Sample complexity · approach: Robust and surrogate-loss learning bounds · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Reduce agnostic learning of a single activation to learning depth-two networks using functional gradient descent with a surrogate lossReLU regression under Gaussian marginals · Gaussian marginals, ReLU regressionSQ query lower bound: 2^{n^c} \epsilonHurt
Apply the same reduction to sigmoid unitsSigmoid learning · Gaussian marginals, sigmoid learningSQ query lower bound: 2^{n^c} \epsilonHurt
Apply the same reduction to halfspacesHalfspace learning · Gaussian marginals, halfspace learningSQ query lower bound: 2^{n^c} \epsilon^3Hurt
Use the nonstandard surrogate loss and Frank–Wolfe functional gradient descentLearning monotone Lipschitz functions of combinations of an agnostically learnable class · Probabilistic concept modellearning guaranteeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy