LGMLMar 12, 2018

Neural Conditional Gradients

arXiv:1803.04300v23 citations
Originality Highly original
AI Analysis

This work addresses the computational and differentiability issues in constrained optimization for machine learning practitioners, offering a novel learning-based approach.

The paper tackles the challenge of constrained optimization by learning projection-free algorithms through Frank-Wolfe Networks, which outperform hand-designed and unconstrained learned optimizers in tasks like training support vector machines and softmax classifiers.

The move from hand-designed to learned optimizers in machine learning has been quite successful for gradient-based and -free optimizers. When facing a constrained problem, however, maintaining feasibility typically requires a projection step, which might be computationally expensive and not differentiable. We show how the design of projection-free convex optimization algorithms can be cast as a learning problem based on Frank-Wolfe Networks: recurrent networks implementing the Frank-Wolfe algorithm aka. conditional gradients. This allows them to learn to exploit structure when, e.g., optimizing over rank-1 matrices. Our LSTM-learned optimizers outperform hand-designed as well learned but unconstrained ones. We demonstrate this for training support vector machines and softmax classifiers.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes