A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation

Akhilesh Gotmare, Nitish Shirish Keskar, Caiming Xiong, Richard Socher

Abstract: The convergence rate and final performance of common deep learning models have significantly benefited from recently proposed heuristics such as learning rate schedules, knowledge distillation, skip connections and normalization layers. In the absence of theoretical underpinnings, controlled experiments aimed at explaining the efficacy of these strategies can aid our understanding of deep learning landscapes and the training dynamics. Existing approaches for empirical analysis rely on tools of linear interpolation and visualizations with dimensionality reduction, each with their limitations. Instead, we revisit the empirical analysis of heuristics through the lens of recently proposed methods for loss surface and representation analysis, viz. mode connectivity and canonical correlation analysis (CCA), and hypothesize reasons why the heuristics succeed. In particular, we explore knowledge distillation and learning rate heuristics of (cosine) restarts and warmup using mode connectivity and CCA. Our empirical analysis suggests that: (a) the reasons often quoted for the success of cosine annealing are not evidenced in practice; (b) that the effect of learning rate warmup is to prevent the deeper layers from creating training instability; and (c) that the latent knowledge shared by the teacher is primarily disbursed in the deeper layers.

Keywords: deep learning heuristics, learning rate restarts, learning rate warmup, knowledge distillation, mode connectivity, SVCCA

TL;DR: We use empirical tools of mode connectivity and SVCCA to investigate neural network training heuristics of learning rate restarts, warmup and knowledge distillation.