mlsanityData to 7 Oct 2026

Optimistic Optimisation of Composite Objective with Exponentiated Update

arXiv 2208.04065 ↗First posted 8 Aug 2022math.OC cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 8 Aug 2022.

Builds on

22 of 45 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  5. 2013Optimal rates for zero-order convex optimization: the power of two function evaluationscited by 190
  6. 2018On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizescited by 155
  7. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  8. 2016Scale-Free Online Learningcited by 83
  9. 2019ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimizationcited by 75
  10. 2014Linear Coupling: An Ultimate Unification of Gradient and Mirror Descentcited by 58
  11. 2019UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimizationcited by 56
  12. 2018Online Adaptive Methods, Universality and Accelerationcited by 51
10 more
  1. 2017Online Learning Without Prior Informationcited by 36
  2. 2020A new regret analysis for Adam-type algorithmscited by 35
  3. 2013Online Learning for Time Series Predictioncited by 33
  4. 2019Exponentiated Gradient Meets Gradient Descentcited by 32
  5. 2017A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Boundscited by 23
  6. 2019Adaptive scale-invariant online algorithms for learning linear modelscited by 19
  7. 2013A Generalized Online Mirror Descent with Applications to Classification and Regressioncited by 18
  8. 2017Online Convex Optimization with Unconstrained Domains and Lossescited by 14
  9. 2014Smoothed Low Rank and Sparse Matrix Recovery by Iteratively Reweighted Least Squares Minimizationcited by 3
  10. 2016NonSTOP: A NonSTationary Online Prediction Method for Time Seriescited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1.

3 papers.

  1. 2022Adaptive Stochastic Optimisation of Nonconvex Composite Objectivescited by 0
  2. 2023Joining Forces for Pathology Diagnostics with AI Assistance: The EMPAIA Initiativecited by 0
  3. 2025Structured Universal Adversarial Attacks on Object Detection for Video Sequencescited by 0