OCLGAug 8, 2022

Optimistic Optimisation of Composite Objective with Exponentiated Update

arXiv:2208.04065v14 citationsh-index: 37
Originality Incremental advance
AI Analysis

This work addresses the problem of efficient online optimization for sparse decision variables, which is incremental as it builds on existing methods to improve performance in specific scenarios.

The paper tackles the online optimization of composite objectives by proposing a new family of algorithms that combine exponentiated gradient and p-norm methods with adaptivity and optimism, achieving a sequence-dependent regret upper bound that matches the best-known bounds for sparse target decision variables.

This paper proposes a new family of algorithms for the online optimisation of composite objectives. The algorithms can be interpreted as the combination of the exponentiated gradient and $p$-norm algorithm. Combined with algorithmic ideas of adaptivity and optimism, the proposed algorithms achieve a sequence-dependent regret upper bound, matching the best-known bounds for sparse target decision variables. Furthermore, the algorithms have efficient implementations for popular composite objectives and constraints and can be converted to stochastic optimisation algorithms with the optimal accelerated rate for smooth objectives.

Code Implementations1 repo
Foundations

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

Your Notes