paperlist.ai

ICML 2023 Papers

International Conference on Machine Learning

202620252024202320222021202020192018201720162015

Decision breakdown

1,865papers

Counted from the official paper list; may differ slightly from the number the conference announced.

  • Oral
    1558.3%
  • Poster
    1,71091.7%

Top 10 topics (click to filter)

Trends for all 207 research topics

Browse all papers

All1,865Oral155Poster1,710
Fully Dynamic Submodular Maximization over Matroids

Paul Duetting, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Morteza Zadimoghaddam

Expand abstract

Maximizing monotone submodular functions under a matroid constraint is a classic algorithmic problem with multiple applications in data mining and machine learning. We study this classic problem in the fully dynamic setting, where elements can be both inserted and deleted in real-time. Our main result is a randomized algorithm that maintains an efficient data structure with an $\tilde{O}(k^2)$ amortized update time (in the number of additions and deletions) and yields a $4$-approximate solution, where $k$ is the rank of the matroid.

Poster
Deep learning · generative models and autoencodersApplications · chemistry physics and earth sciences
Delay-agnostic Asynchronous Coordinate Update Algorithm

Xuyang Wu, Changxin Liu, Sindri Magnússon, Mikael Johansson

Expand abstract

We propose a delay-agnostic asynchronous coordinate update algorithm (DEGAS) for computing operator fixed points, with applications to asynchronous optimization. DEGAS includes novel asynchronous variants of ADMM and block-coordinate descent as special cases. We prove that DEGAS converges with both bounded and unbounded delays under delay-free parameter conditions. We also validate by theory and experiments that DEGAS adapts well to the actual delays. The effectiveness of DEGAS is demonstrated by numerical experiments on classification problems.

Poster
Applications · chemistry physics and earth sciencesApplications · neuroscience and cognitive science