# A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum

arXiv: https://arxiv.org/abs/2102.07367 · HTML: https://mlsanity.com/paper/2102.07367/

## Key facts

- Cited by 106 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 15 Feb 2021.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Meta-Learning with Implicit Gradients](https://mlsanity.com/paper/1909.04630/) (2019)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Bilevel Programming for Hyperparameter Optimization and Meta-Learning](https://mlsanity.com/paper/1806.04910/) (2018)
- [Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML](https://mlsanity.com/paper/1909.09157/) (2019)
- [Momentum-Based Variance Reduction in Non-Convex SGD](https://mlsanity.com/paper/1905.10018/) (2019)
- [SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator](https://mlsanity.com/paper/1807.01695/) (2018)
- [Approximation Methods for Bilevel Programming](https://mlsanity.com/paper/1802.02246/) (2018)
- [Forward and Reverse Gradient-Based Hyperparameter Optimization](https://mlsanity.com/paper/1703.01785/) (2017)
- [Hyperparameter optimization with approximate gradient](https://mlsanity.com/paper/1602.02355/) (2016)
- [Truncated Back-propagation for Bilevel Optimization](https://mlsanity.com/paper/1810.10667/) (2018)
- [On the Iteration Complexity of Hypergradient Computation](https://mlsanity.com/paper/2006.16218/) (2020)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton](https://mlsanity.com/paper/2006.04045/) (2020)
- [learn2learn: A Library for Meta-Learning Research](https://mlsanity.com/paper/2008.12284/) (2020)
- [A First Order Method for Solving Convex Bi-Level Optimization Problems](https://mlsanity.com/paper/1702.03999/) (2017)
- [Stochastic Nested Variance Reduction for Nonconvex Optimization](https://mlsanity.com/paper/1806.07811/) (2018)
- [Hybrid Stochastic Gradient Descent Algorithms for Stochastic Nonconvex Optimization](https://mlsanity.com/paper/1905.05920/) (2019)
- [Improved Bilevel Model: Fast and Optimal Algorithm with Theoretical Guarantee](https://mlsanity.com/paper/2009.00690/) (2020)
- [Convergence Properties of Stochastic Hypergradients](https://mlsanity.com/paper/2011.07122/) (2020)

## Built on by (most cited first, 30 of 106)

- [Provably Faster Algorithms for Bilevel Optimization](https://mlsanity.com/paper/2106.04692/) (2021)
- [BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach](https://mlsanity.com/paper/2209.08709/) (2022)
- [A Fully First-Order Method for Stochastic Bilevel Optimization](https://mlsanity.com/paper/2301.10945/) (2023)
- [A framework for bilevel optimization that enables stochastic and global variance reduction algorithms](https://mlsanity.com/paper/2201.13409/) (2022)
- [On Penalty-based Bilevel Gradient Descent Method](https://mlsanity.com/paper/2302.05185/) (2023)
- [Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization](https://mlsanity.com/paper/2112.12376/) (2021)
- [SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection](https://mlsanity.com/paper/2410.07471/) (2024)
- [FedNest: Federated Bilevel, Minimax, and Compositional Optimization](https://mlsanity.com/paper/2205.02215/) (2022)
- [A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse](https://mlsanity.com/paper/2112.04660/) (2021)
- [On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation](https://mlsanity.com/paper/2309.01753/) (2023)
- [Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees](https://mlsanity.com/paper/2210.01808/) (2022)
- [First-order penalty methods for bilevel optimization](https://mlsanity.com/paper/2301.01716/) (2023)
- [An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning](https://mlsanity.com/paper/2308.00788/) (2023)
- [Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF](https://mlsanity.com/paper/2402.06886/) (2024)
- [PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2308.02585/) (2023)
- [ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting](https://mlsanity.com/paper/2406.19976/) (2024)
- [Will Bilevel Optimizers Benefit from Loops](https://mlsanity.com/paper/2205.14224/) (2022)
- [On the Convergence Theory for Hessian-Free Bilevel Algorithms](https://mlsanity.com/paper/2110.07004/) (2021)
- [BiAdam: Fast Adaptive Bilevel Optimization Methods](https://mlsanity.com/paper/2106.11396/) (2021)
- [Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks](https://mlsanity.com/paper/2206.10870/) (2022)
- [Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions](https://mlsanity.com/paper/2306.12067/) (2023)
- [Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning](https://mlsanity.com/paper/2509.06948/) (2025)
- [Enhanced Bilevel Optimization via Bregman Distance](https://mlsanity.com/paper/2107.12301/) (2021)
- [Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity](https://mlsanity.com/paper/2302.03407/) (2023)
- [Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity](https://mlsanity.com/paper/2210.12839/) (2022)
- [Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction](https://mlsanity.com/paper/2205.01608/) (2022)
- [Efficiently Escaping Saddle Points in Bilevel Optimization](https://mlsanity.com/paper/2202.03684/) (2022)
- [Achieving Linear Speedup in Non-IID Federated Bilevel Learning](https://mlsanity.com/paper/2302.05412/) (2023)
- [Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start](https://mlsanity.com/paper/2202.03397/) (2022)
- [Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles](https://mlsanity.com/paper/2306.14853/) (2023)

## Abstract (arXiv)

This paper proposes a new algorithm -- the underlineSingle-timescale Dounderlineuble-momentum underlineStochastic underlineApproxunderlineimatiounderlinen (SUSTAIN) -- for tackling stochastic unconstrained bilevel optimization problems. We focus on bilevel problems where the lower level subproblem is strongly-convex and the upper level objective function is smooth. Unlike prior works which rely on two-timescale or double loop techniques, we design a stochastic momentum-assisted gradient estimator for both the upper and lower level updates. The latter allows us to control the error in the stochastic gradient updates due to inaccurate solution to both subproblems. If the upper objective function is smooth but possibly non-convex, we show that aname~requires O(ε-3/2) iterations (each using cal O(1) samples) to find an ε-stationary solution. The ε-stationary solution is defined as the point whose squared norm of the gradient of the outer function is less than or equal to ε. The total number of stochastic gradient samples required for the upper and lower level objective functions matches the best-known complexity for single-level stochastic gradient algorithms. We also analyze the case when the upper level objective function is strongly-convex.