Research map / Optimization / Nonconvex and smooth optimization
Projection-free conditional gradient
Designs conditional gradient variants that avoid projections for constrained convex and online optimization.
23 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Nonconvex and smooth optimization, keyword cluster “frank · wolfe · conditional”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
2 papers in 2023–24 and 3 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 0.6% to 0.9%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Faster Projection-free Convex Optimization over the Spectrahedron (NeurIPS 2016 · 17 citations)
- 2017 · Conditional Accelerated Lazy Stochastic Gradient Descent (ICML 2017 · 19 citations)
- 2018 · A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming (ICML 2018 · 21 citations)
- 2019 · Blended Conditonal Gradients (ICML 2019 · 12 citations)
- 2020 · Conditional gradient methods for stochastically constrained convex minimization (ICML 2020 · 3 citations)
- 2021 · Parameter-free Locally Accelerated Conditional Gradients (ICML 2021 · 2 citations)
- 2022 · Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding (ICML 2022 · 0 citations)
- 2023 · Projection-Free Online Convex Optimization via Efficient Newton Iterations (NeurIPS 2023 · 0 citations)
- 2024 · Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization (ICML 2024 · 0 citations)
- 2025 · Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness (NeurIPS 2025 · 0 citations)
- 2026 · On Densest $k$-Subgraph Mining and Diagonal Loading: Optimization Landscape and Finite-Step Exact Convergence Analysis (ICML 2026 · 0 citations)
Earliest papers here
- Faster Projection-free Convex Optimization over the Spectrahedron (NeurIPS 2016 · 17 citations)
- Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity (ICML 2016 · 6 citations)
- Conditional Accelerated Lazy Stochastic Gradient Descent (ICML 2017 · 19 citations)
What has been tried
19 papers here report 134 measured changes (a component added, removed or swapped, compared with a baseline): helped 79%, no clear effect 7%, hurt 9%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 21 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Stochastic Frank-Wolfe methods (43 papers)
Elsewhere in the topic
- Adaptive first-order convex methods (190 papers)
- Coordinate and Adam convergence analysis (188 papers)
- Stochastic gradient last-iterate analysis (178 papers)
- Nonconvex minimax and constrained methods (100 papers)
- Stochastic convex optimization complexity (94 papers)
- Acceleration and Nesterov dynamics (91 papers)
- Equilibrium learning in zero-sum games (88 papers)
- Stochastic variance reduction (86 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).