English
Related papers

Related papers: Implicit Differentiation for Hyperparameter Tuning…

200 papers

Finding the optimal hyperparameters of a model can be cast as a bilevel optimization problem, typically solved using zero-order techniques. In this work we study first-order methods when the inner optimization problem is convex but…

Hyperparameter optimization can be formulated as a bilevel optimization problem, where the optimal parameters on the training set depend on the hyperparameters. We aim to adapt regularization hyperparameters for neural networks by fitting…

Machine Learning · Computer Science 2019-03-08 Matthew MacKay , Paul Vicol , Jon Lorraine , David Duvenaud , Roger Grosse

In this paper, we develop zeroth-order algorithms with provably (nearly) optimal sample complexity for stochastic bilevel optimization, where only noisy function evaluations are available. We propose two distinct algorithms: the first is…

Optimization and Control · Mathematics 2025-10-07 Alireza Aghasi , Jeongyeol Kwon , Saeed Ghadimi

Many Machine Learning algorithms are formulated as regularized optimization problems, but their performance hinges on a regularization parameter that needs to be calibrated to each application at hand. In this paper, we propose a general…

Machine Learning · Statistics 2021-03-31 Mike Laszkiewicz , Asja Fischer , Johannes Lederer

We develop a new method for equality constrained optimization problems based on a sequential cubic programming framework. Each iteration utilizes a step decomposition based on the Jacobian of the constraints into a normal and a tangential…

Optimization and Control · Mathematics 2026-04-06 Nikos Dimou , Michael J. O'Neill

We propose a scalable, efficient and statistically motivated computational framework for Graphical Lasso (Friedman et al., 2007b) - a covariance regularization framework that has received significant attention in the statistics community…

Machine Learning · Statistics 2011-10-26 Rahul Mazumder , Deepak K. Agarwal

This paper considers the hyperparameter optimization problem of mathematical techniques that arise in the numerical solution of differential and integral equations. The well-known approaches grid and random search, in a parallel algorithm…

Numerical Analysis · Mathematics 2023-04-28 Alireza Afzal Aghaei , Kourosh Parand

Hyperparameter tuning is an active area of research in machine learning, where the aim is to identify the optimal hyperparameters that provide the best performance on the validation set. Hyperparameter tuning is often achieved using naive…

Machine Learning · Computer Science 2020-07-23 Ankur Sinha , Tanmay Khandait , Raja Mohanty

We study bilevel optimization problems where the lower-level problems are strongly convex and have coupled linear constraints. To overcome the potential non-smoothness of the hyper-objective and the computational challenges associated with…

Optimization and Control · Mathematics 2026-02-06 Wei Shen , Jiawei Zhang , Minhui Huang , Cong Shen

We design and analyze a novel accelerated gradient-based algorithm for a class of bilevel optimization problems. These problems have various applications arising from machine learning and image processing, where optimal solutions of the two…

Optimization and Control · Mathematics 2023-11-20 Sepideh Samadi , Daniel Burbano , Farzad Yousefian

In this work we derive a second-order approach to bilevel optimization, a type of mathematical programming in which the solution to a parameterized optimization problem (the "lower" problem) is itself to be optimized (in the "upper"…

Optimization and Control · Mathematics 2022-05-06 Robert Dyro , Edward Schmerling , Nikos Arechiga , Marco Pavone

Hyperparameter optimization of neural networks can be elegantly formulated as a bilevel optimization problem. While research on bilevel optimization of neural networks has been dominated by implicit differentiation and unrolling,…

Machine Learning · Computer Science 2020-10-27 Juhan Bae , Roger Grosse

Inpainting based image compression approaches, especially linear and non-linear diffusion models, are an active research topic for lossy image compression. The major challenge in these compression models is to find a small set of…

Computer Vision and Pattern Recognition · Computer Science 2014-05-12 Yunjin Chen , René Ranftl , Thomas Pock

The Newton, Gauss--Newton and Levenberg--Marquardt methods all use the first derivative of a vector function (the Jacobian) to minimise its sum of squares. When the Jacobian matrix is ill-conditioned, the function varies much faster in some…

Numerical Analysis · Mathematics 2025-08-01 S. J. Brooks

In Gaussian graphical models, the likelihood equations must typically be solved iteratively. We investigate two algorithms: A version of iterative proportional scaling which avoids inversion of large matrices, and an algorithm based on…

Computation · Statistics 2023-12-12 Søren Højsgaard , Steffen Lauritzen

Setting regularization parameters for Lasso-type estimators is notoriously difficult, though crucial in practice. The most popular hyperparameter optimization approach is grid-search using held-out validation data. Grid-search however…

This study proposes a Newton based multiple objective optimization algorithm for hyperparameter search. The first order differential (gradient) is calculated using finite difference method and a gradient matrix with vectorization is formed…

Optimization and Control · Mathematics 2024-01-09 Qinwu Xu

Algorithms for bilevel optimization often encounter Hessian computations, which are prohibitive in high dimensions. While recent works offer first-order methods for unconstrained bilevel problems, the constrained setting remains relatively…

Optimization and Control · Mathematics 2025-04-22 Guy Kornowski , Swati Padmanabhan , Kai Wang , Zhe Zhang , Suvrit Sra

The graphical lasso \citep{FHT2007a} is an algorithm for learning the structure in an undirected Gaussian graphical model, using $\ell_1$ regularization to control the number of zeros in the precision matrix ${\B\Theta}={\B\Sigma}^{-1}$…

Machine Learning · Statistics 2012-08-09 Rahul Mazumder , Trevor Hastie

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…

Machine Learning · Computer Science 2022-06-07 Daouda Sow , Kaiyi Ji , Yingbin Liang
‹ Prev 1 2 3 10 Next ›