A review on bilevel optimization: From classical to evolutionary approaches and applications

A Sinha, P Malo, K Deb - IEEE transactions on evolutionary …, 2017‏ - ieeexplore.ieee.org
Bilevel optimization is defined as a mathematical program, where an optimization problem
contains another optimization problem as a constraint. These problems have received …

[HTML][HTML] A survey on mixed-integer programming techniques in bilevel optimization

T Kleinert, M Labbé, I Ljubić, M Schmidt - EURO Journal on Computational …, 2021‏ - Elsevier
Bilevel optimization is a field of mathematical programming in which some variables are
constrained to be the solution of another optimization problem. As a consequence, bilevel …

A fully first-order method for stochastic bilevel optimization

J Kwon, D Kwon, S Wright… - … Conference on Machine …, 2023‏ - proceedings.mlr.press
We consider stochastic unconstrained bilevel optimization problems when only the first-
order gradient oracles are available. While numerous optimization methods have been …

A two-timescale stochastic algorithm framework for bilevel optimization: Complexity analysis and application to actor-critic

M Hong, HT Wai, Z Wang, Z Yang - SIAM Journal on Optimization, 2023‏ - SIAM
This paper analyzes a two-timescale stochastic algorithm framework for bilevel optimization.
Bilevel optimization is a class of problems which exhibits a two-level structure, and its goal is …

Data distillation: A survey

N Sachdeva, J McAuley - arxiv preprint arxiv:2301.04272, 2023‏ - arxiv.org
The popularity of deep learning has led to the curation of a vast number of massive and
multifarious datasets. Despite having close-to-human performance on individual tasks …

Investigating bi-level optimization for learning and vision from a unified perspective: A survey and beyond

R Liu, J Gao, J Zhang, D Meng… - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then
introduced into the optimization community. BLO is able to handle problems with a …

On penalty-based bilevel gradient descent method

H Shen, T Chen - International Conference on Machine …, 2023‏ - proceedings.mlr.press
Bilevel optimization enjoys a wide range of applications in hyper-parameter optimization,
meta-learning and reinforcement learning. However, bilevel problems are difficult to solve …

Advancing model pruning via bi-level optimization

Y Zhang, Y Yao, P Ram, P Zhao… - Advances in …, 2022‏ - proceedings.neurips.cc
The deployment constraints in practical applications necessitate the pruning of large-scale
deep learning models, ie, promoting their weight sparsity. As illustrated by the Lottery Ticket …

Revisiting and advancing fast adversarial training through the lens of bi-level optimization

Y Zhang, G Zhang, P Khanduri… - International …, 2022‏ - proceedings.mlr.press
Adversarial training (AT) is a widely recognized defense mechanism to gain the robustness
of deep neural networks against adversarial attacks. It is built on min-max optimization …

A near-optimal algorithm for stochastic bilevel optimization via double-momentum

P Khanduri, S Zeng, M Hong, HT Wai… - Advances in neural …, 2021‏ - proceedings.neurips.cc
This paper proposes a new algorithm--the\underline {S} ingle-timescale Do\underline {u} ble-
momentum\underline {St} ochastic\underline {A} pprox\underline {i} matio\underline …