Research map / Optimization / Optimizers
Differentiating through inner loops
Optimizes hyperparameters over long horizons using implicit differentiation and truncated inner-loop gradients.
23 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Optimizers, keyword cluster “bilevel · inner · shot”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
4 papers in 2023–24 and 1 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 1.7% to 0.3%.
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 · Hyperparameter optimization with approximate gradient (ICML 2016 · 132 citations)
- 2017 · Forward and Reverse Gradient-Based Hyperparameter Optimization (ICML 2017 · 53 citations)
- 2018 · Learning to Reweight Examples for Robust Deep Learning (ICML 2018 · 841 citations)
- 2019 · Sever: A Robust Meta-Algorithm for Stochastic Optimization (ICML 2019 · 142 citations)
- 2020 · Implicit differentiation of Lasso-type models for hyperparameter optimization (ICML 2020 · 25 citations)
- 2021 · Nonsmooth Implicit Differentiation for Machine-Learning and Optimization (NeurIPS 2021 · 16 citations)
- 2022 · Efficient Riemannian Meta-Optimization by Implicit Differentiation (AAAI 2022 · 5 citations)
- 2023 · NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications (NeurIPS 2023 · 2 citations)
- 2026 · Understanding the Curse of Unrolling (NeurIPS 2026 · 0 citations)
Earliest papers here
- Hyperparameter optimization with approximate gradient (ICML 2016 · 132 citations)
- Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis (NeurIPS 2016 · 1 citation)
- Forward and Reverse Gradient-Based Hyperparameter Optimization (ICML 2017 · 53 citations)
What has been tried
21 papers here report 183 measured changes (a component added, removed or swapped, compared with a baseline): helped 61%, no clear effect 11%, hurt 20%, mixed 8%. Papers mostly publish changes that helped, so "helped" is over-represented.
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 5 papers; from OpenAlex and the papers' affiliations).
- Google · 2 papers
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
- Gradient-based meta-learning theory (40 papers)
- Hypergradient bilevel optimization (35 papers)
Elsewhere in the topic
- Stochastic gradient MCMC (142 papers)
- Surrogate losses and robust solvers (119 papers)
- Differentiating through embedded optimization (117 papers)
- Constrained and non-backprop training (97 papers)
- Memory-efficient LLM optimizers (79 papers)
- Adam convergence and adaptive learning rates (78 papers)
- Natural gradient and Fisher approximations (77 papers)
- Randomized gradient estimation (77 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).