From Local Pseudorandom Generators to Hardness of Learning

Abstract

We prove hardness-of-learning results under a well-studied assumption on the existence of local pseudorandom generators. As we show, this assumption allows us to surpass the current state of the art, and prove hardness of various basic problems, with no hardness results to date. Our results include: hardness of learning shallow ReLU neural networks under the Gaussian distribution and other distributions; hardness of learning intersections of $\omega (1)$ halfspaces, DNF formulas with $\omega (1)$ terms, and ReLU networks with $\omega (1)$ hidden neurons; hardness of weakly learning deterministic finite automata under the uniform distribution; hardness of weakly learning depth-$3$ Boolean circuits under the uniform distribution, as well as distribution-specific hardness results for learning DNF formulas and intersections of halfspaces. We also establish lower bounds on the complexity of learning intersections of a constant number of halfspaces, and ReLU networks with a constant number of hidden neurons. Moreover, our results imply the hardness of virtually all improper PAC-learning problems (both distribution-free and distribution-specific) that were previously shown hard under other assumptions.

References in corpus (14)

• Provable Bounds for Learning Some Deep Representations
• Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods
• Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
• An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis
• Learning One Convolutional Layer with Overlapping Patches
• Learning Neural Networks with Two Nonlinear Layers in Polynomial Time
• On the Complexity of Learning Neural Networks
• Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals
• Statistical-Query Lower Bounds via Functional Gradients
• Algorithms and SQ Lower Bounds for PAC Learning One-Hidden-Layer ReLU Networks
• Hardness of Learning Neural Networks with Natural Weights
• On the Learnability of Deep Random Networks
• Improved Learning of One-hidden-layer Convolutional Neural Networks with Overlaps
• A Deep Conditioning Treatment of Neural Networks