Adaptive Subgradient Methods for Online Learning and Stochastic Optimization


We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradient-based learning. Metaphorically, the adaptation allows us to find needles in haystacks in the form of very predictive but rarely seen features. Our paradigm stems from recent advances in stochastic optimization and online learning which employ proximal functions to control the gradient steps of the algorithm. We describe and analyze an apparatus for adaptively modifying the proximal function, which significantly simplifies setting a learning rate and results in regret guarantees that are provably as good as the best proximal function that can be chosen in hindsight. We give several efficient algorithms for empirical risk minimization problems with common and important regularization functions and domain constraints. We experimentally study our theoretical analysis and show that adaptive subgradient methods outperform state-of-the-art, yet non-adaptive, subgradient algorithms.

Extracted Key Phrases

11 Figures and Tables

Showing 1-10 of 43 references

Convex Optimization

  • S Boyd, L Vandenberghe
  • 2004
Highly Influential
4 Excerpts

Comments on and complements to Inequalities: Theory of Majorization and Its Applications

  • J V Bondar
  • 1994
Highly Influential
1 Excerpt

Concavity of certain maps on positive definite matrices and applications to Hadamard products

  • T Ando
  • 1979
Highly Influential
1 Excerpt
Showing 1-10 of 1,343 extracted citations
Citations per Year

2,097 Citations

Semantic Scholar estimates that this publication has received between 1,925 and 2,288 citations based on the available data.

See our FAQ for additional information.