Estimating hyperparameters has been a long-standing problem in machine learning. We consider the case where the task at hand is modeled as the solution to an optimization problem. Here the exact gradient with respect to the hyperparameters cannot be feasibly computed and approximate strategies are required. We introduce a unified framework for computing hypergradients that generalizes existing methods based on the implicit function theorem and automatic differentiation/backpropagation, showing that these two seemingly disparate approaches are actually tightly connected. Our framework is extremely flexible, allowing its subproblems to be solved with any suitable method, to any degree of accuracy. We derive a priori and computable a posteriori error bounds for all our methods, and numerically show that our a posteriori bounds are usually more accurate. Our numerical results also show that, surprisingly, for efficient bilevel optimization, the choice of hypergradient algorithm is at least as important as the choice of lower-level solver.
Bilevel Learning with Inexact Stochastic Gradients
Department of Mathematical Sciences, University of Bath（巴斯大学数学科学系）；Department of Electronics & Electrical Communication Engineering, Indian Institute of Technology (IIT) Kharagpur（印度理工学院Kharagpur电子与电气通信工程系）；School of Mathematics and Statistics, University of Sydney（悉尼大学数学与统计学学院）
The Ohio State University（俄亥俄州立大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via Jacobian- or/and Hessian-vector computations, which can be costly and unscalable in practice. Recently, Hessian-free bilevel schemes have been proposed to resolve this issue, where the general idea is to use zeroth- or first-order methods to approximate the full hypergradient of the bilevel problem. However, we empirically observe that such approximation can lead to large varia…
An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning
EPSRC Centre for Doctoral Training in Statistical Applied Mathematics at Bath (SAMBa)（EPSRC统计应用数学博士培训中心（SAMBa））；Department of Mathematical Sciences, University of Bath（巴斯大学数学科学系）；Department of Electronics & Electrical Communication Engineering, Indian Institute of Technology (IIT), Kharagpur（印度理工学院（Kharagpur）电子与电气通信工程系）；School of Mathematics and Statistics, University of Sydney（悉尼大学数学与统计学学院）
Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation
Southern University of Science and Technology（南方科技大学）；National Center for Applied Mathematics Shenzhen（深圳应用数学国家研究中心）；City University of Hong Kong（香港城市大学）
University of Michigan（密歇根大学）；University of California, Riverside（加州大学河滨分校）；University of British Columbia（不列颠哥伦比亚大学）
Standard federated optimization methods successfully apply to stochastic problems with single-level structure. However, many contemporary ML problems -- including adversarial robustness, hyperparameter tuning, and actor-critic -- fall under nested bilevel programming that subsumes minimax and compositional optimization. In this work, we propose \fedblo: A federated alternating stochastic gradient method to address general nested problems. We establish provable convergence rates for \fedblo in the presence of heterogeneous data and introduce variations for bilevel, minimax, and compositional op…
Bilevel Learning via Inexact Stochastic Gradient Descent
EPSRC Centre for Doctoral Training in Statistical Applied Mathematics at Bath（巴斯大学统计应用数学博士培训中心）；Australian Research Council（澳大利亚研究理事会）；Indian Institute of Technology (IIT), Kharagpur（印度理工学院（Kharagpur分校））；University of Melbourne（墨尔本大学）；Department of Electronics & Electrical Communication Engineering（电子与电气通信工程系）；School of Mathematics and Statistics（数学与统计学学院）
Solving a bilevel optimization problem is at the core of several machine learning problems such as hyperparameter tuning, data denoising, meta- and few-shot learning, and training-data poisoning. Different from simultaneous or multi-objective optimization, the steepest descent direction for minimizing the upper-level cost in a bilevel problem requires the inverse of the Hessian of the lower-level cost. In this work, we propose a novel algorithm for solving bilevel optimization problems based on the classical penalty function approach. Our method avoids computing the Hessian inverse and can han…
University of Bath（巴斯大学）；Australian National University（澳大利亚国立大学）
Variational regularization techniques are dominant in the field of mathematical imaging. A drawback of these techniques is that they are dependent on a number of parameters which have to be set by the user. A by now common strategy to resolve this issue is to learn these parameters from data. While mathematically appealing this strategy leads to a nested optimization problem (known as bilevel optimization) which is computationally very difficult to handle. It is common when solving the upper-level problem to assume access to exact solutions of the lower-level problem, which is practically infe…
Derivative-Free Bilevel Optimization with Inexact Lower-Level Solutions
Dipartimento di Ingegneria Informatica, Automatica e Gestionale “A. Ruberti”, “Sapienza” Università di Roma（罗马大学信息与自动化与管理工程学院）；Istituto di Analisi dei Sistemi ed Informatica “A. Ruberti”, Consiglio Nazionale delle Ricerche（意大利国家研究委员会系统与信息技术分析研究所）
Bilevel optimization has arisen as a powerful tool for many machine learning problems such as meta-learning, hyperparameter optimization, and reinforcement learning. In this paper, we investigate the nonconvex-strongly-convex bilevel optimization problem. For deterministic bilevel optimization, we provide a comprehensive convergence rate analysis for two popular algorithms respectively based on approximate implicit differentiation (AID) and iterative differentiation (ITD). For the AID-based method, we orderwisely improve the previous convergence rate analysis due to a more practical parameter …
Meta；The Ohio State University（俄亥俄州立大学）；University at Buffalo（布法罗大学）
Federated bilevel optimization has received increasing attention in various emerging machine learning and communication applications. Recently, several Hessian-vector-based algorithms have been proposed to solve the federated bilevel optimization problem. However, several important properties in federated learning such as the partial client participation and the linear speedup for convergence (i.e., the convergence rate and complexity are improved linearly with respect to the number of sampled clients) in the presence of non-i.i.d.~datasets, still remain open. In this paper, we fill these gaps…
University of Waterloo（滑铁卢大学）；University of Victoria（维多利亚大学）；Southern University of Science and Technology（南方科技大学）；National Center for Applied Mathematics Shenzhen（深圳国家应用数学中心）
Gradient-based optimization methods for hyperparameter tuning guarantee theoretical convergence to stationary solutions when for fixed upper-level variable values, the lower level of the bilevel program is strongly convex (LLSC) and smooth (LLS). This condition is not satisfied for bilevel programs arising from tuning hyperparameters in many machine learning algorithms. In this work, we develop a sequentially convergent Value Function based Difference-of-Convex Algorithm with inexactness (VF-iDCA). We show that this algorithm achieves stationary solutions without LLSC and LLS assumptions for b…
We study a class of algorithms for solving bilevel optimization problems in both stochastic and deterministic settings when the inner-level objective is strongly convex. Specifically, we consider algorithms based on inexact implicit differentiation and we exploit a warm-start strategy to amortize the estimation of the exact gradient. We then introduce a unified theoretical framework inspired by the study of singularly perturbed systems (Habets, 1974) to analyze such amortized algorithms. By using this framework, our analysis shows these algorithms to match the computational complexity of oracl…
Bilevel optimization has become a powerful framework in various machine learning applications including meta-learning, hyperparameter optimization, and network architecture search. There are generally two classes of bilevel optimization formulations for machine learning: 1) problem-based bilevel optimization, whose inner-level problem is formulated as finding a minimizer of a given loss function; and 2) algorithm-based bilevel optimization, whose inner-level solution is an output of a fixed algorithm. For the first class, two popular types of gradient-based algorithms have been proposed for hy…
In this work, the demand Adjustment Problem (DAP) associated to urban traffic planning is studied. The framework for the formulation of the DAP is mathematical programming with equilibrium constraints. In particular, if the optimization program associated to the equilibrium constraints is considered, the DAP results in a bilevel optimization problem. In this approach the DAP via the Inexact Restoration method is treated.
DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
Department of Electrical and Computer Engineering, The Ohio State University（俄亥俄州立大学电气与计算机工程系）；Department of Computer Science and Engineering, University of North Texas（北卡罗来纳州立大学计算机科学与工程系）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）
Hessian-Free Distributed Bilevel Optimization via Penalization with Time-Scale Separation
State Key Laboratory of Industrial Control Technology and the College of Control Science and Engineering, Zhejiang University（浙江大学工业控制技术国家重点实验室与控制科学与工程学院）；School of Electrical Engineering and Computer Science, Pennsylvania State University（宾夕法尼亚州立大学电气与计算机工程学院）
Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
Amirkabir University of Technology（阿姆斯泰尔大学）；University of Pennsylvania（宾夕法尼亚大学）；Samsung SDS Research America（三星SDS美国研究部）；University of California, Los Angeles（加州大学洛杉矶分校）
Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs
University of British Columbia（不列颠哥伦比亚大学）；University of Victoria（维多利亚大学）；Southern University of Science and Technology（南方科技大学）；National Center for Applied Mathematics Shenzhen（深圳国家应用数学中心）；Peng Cheng Laboratory（鹏城实验室）
Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong（香港中文大学先进工程学院）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）
