paper-with-me

Papers

Implicit differentiation for fast hyperparameter selection in non-smooth convex learning

2021-05-04 · Quentin Bertrand, Quentin Klopfenstein, Mathurin Massias, Mathieu Blondel, Samuel Vaiter, Alexandre Gramfort, Joseph Salmon

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 non-smooth. We show that the forward-mode differentiation of proximal gradient descent and proximal coordinate descent yield sequences of Jacobians converging toward the exact Jacobian. Using implicit differentiation, we show it is possible to leverage the non-smoothness of the inner problem to speed up the computation. Finally, we provide a bound on the error made on the hypergradient when the inner optimization problem is solved approximately. Results on regression and classification problems reveal computational benefits for hyperparameter optimization, especially when multiple hyperparameters are required.

📄 PDF Abstract BibTeX arXiv:2105.01637

Code (1)

QB3/sparse-ho 공식 구현

Tasks

Bilevel OptimizationHyperparameter Optimization

Similar Papers 제목 키워드 기반

Nonsmooth Implicit Differentiation for Machine Learning and Optimization

2021-06-08 · NeurIPS 2021 12 · Jérôme Bolte, Tam Le, Edouard Pauwels, Antonio Silveti-Falls

In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e., definable problems) p…

BIG-bench Machine Learning

Nonsmooth Implicit Differentiation for Machine-Learning and Optimization

2021-05-21 · NeurIPS 2021 12 · Jerome Bolte, Tam Le, Edouard Pauwels, Antonio Silveti-Falls

In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e., definable problems) p…

BIG-bench Machine Learning

Implicit differentiation of Lasso-type models for hyperparameter optimization

2020-02-20 · ICML 2020 1 · Quentin Bertrand, Quentin Klopfenstein, Mathieu Blondel, Samuel Vaiter 외

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-…

Hyperparameter OptimizationVocal Bursts Type Prediction

Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates

2024-03-18 · Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo

We study the problem of efficiently computing the derivative of the fixed-point of a parametric nondifferentiable contraction map. This problem has wide applications in machine learning, including hyperparameter optimiza…

Data PoisoningHyperparameter OptimizationMeta-Learning

Hyperparameter selection for Discrete Mumford-Shah

2021-09-28 · Charles-Gérard Lucas, Barbara Pascal, Nelly Pustelnik, Patrice Abry

This work focuses on a parameter-free joint piecewise smooth image denoising and contour detection. Formulated as the minimization of a discrete Mumford-Shah functional and estimated via a theoretically grounded alternat…

Contour DetectionDenoisingImage DenoisingImage Reconstruction