Learning to Learn by Zeroth-Order Oracle

by   Yangjun Ruan, et al.

In the learning to learn (L2L) framework, we cast the design of optimization algorithms as a machine learning problem and use deep neural networks to learn the update rules. In this paper, we extend the L2L framework to zeroth-order (ZO) optimization setting, where no explicit gradient information is available. Our learned optimizer, modeled as recurrent neural network (RNN), first approximates gradient by ZO gradient estimator and then produces parameter update utilizing the knowledge of previous iterations. To reduce high variance effect due to ZO gradient estimator, we further introduce another RNN to learn the Gaussian sampling rule and dynamically guide the query direction sampling. Our learned optimizer outperforms hand-designed algorithms in terms of convergence rate and final solution on both synthetic and practical ZO optimization tasks (in particular, the black-box adversarial attack task, which is one of the most widely used tasks of ZO optimization). We finally conduct extensive analytical experiments to demonstrate the effectiveness of our proposed optimizer.


page 11

page 16


Learning to learn by gradient descent by gradient descent

The move from hand-designed features to learned features in machine lear...

HyperAdam: A Learnable Task-Adaptive Adam for Network Training

Deep neural networks are traditionally trained using human-designed stoc...

Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML

In this paper, we study the problem of constrained robust (min-max) opti...

DRO: Deep Recurrent Optimizer for Structure-from-Motion

There are increasing interests of studying the structure-from-motion (Sf...

Learning to be Global Optimizer

The advancement of artificial intelligence has cast a new light on the d...

Optimizer Amalgamation

Selecting an appropriate optimizer for a given problem is of major inter...

Learning to Optimize in Swarms

Learning to optimize has emerged as a powerful framework for various opt...