Research map / Optimization / Nonconvex and smooth optimization
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the non-oblivious function F and its sampled stochastic gradient instead of the original objective gradient | Gradient ascent for weakly DR-submodular maximization · Offline stochastic continuous DR-submodular maximization | approximation guarantee: $(\frac{\gamma^2}{1+\gamma^2})$ to $(1-e^{-\gamma}-\epsilon^{2})$ | Helped |
| Use the non-oblivious function F in online gradient ascent | Online stochastic continuous DR-submodular maximization · No-delay online setting | approximation ratio: $1/2$ to $1-1/e$ | Helped |
| Use delayed online boosting gradient ascent with F | Online stochastic continuous DR-submodular maximization · Adversarial delayed feedback | approximation-regret: $O(\sqrt{D})$ | Helped |
| Replace deterministic Frank-Wolfe updates with stochastic projected gradient updates using F | Offline continuous DR-submodular maximization · Monotone stochastic continuous DR-submodular functions | gradient oracle complexity: $O(1/\epsilon^3)$ to $O(1/\epsilon^2)$ | Helped |
Closest papers by meaning
- Gradient Methods for Submodular Maximization (NeurIPS 2017 · similarity 0.93)
- Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints (NeurIPS 2024 · similarity 0.92)
- Online Two-Stage Submodular Maximization (NeurIPS 2025 · similarity 0.90)
- Online Submodular Maximization via Online Convex Optimization (AAAI 2024 · similarity 0.89)
- Nearly Minimax Optimal Submodular Maximization with Bandit Feedback (NeurIPS 2024 · similarity 0.88)
- From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.