PANOM: Automatic Hyper-parameter Tuning for Inverse Problems
Automated hyper-parameter tuning for unsupervised learning, including inverse problems, remains a long-standing open problem due to the lack of validation data. In this work, we design an automatic tuning criterion for inverse problems and formulate it as a bilevel optimization task. We demonstrate the efficiency of our tuning scheme on various inverse problems and different test and out-of-distribution image samples at no expense of performance drops.
Code (0)
등록된 구현이 없습니다.
Tasks
Bilevel OptimizationSimilar Papers 제목 키워드 기반
A hyperparameter-tuning approach to automated inverse planning
Radiotherapy inverse planning often requires planners to modify parameters in the treatment planning system's objective function to produce clinically acceptable plans. Due to the manual steps in this process, plan quali…
Bayesian OptimizationDimensionality ReductionPanoMixSwap Panorama Mixing via Structural Swapping for Indoor Scene Understanding
The volume and diversity of training data are critical for modern deep learningbased methods. Compared to the massive amount of labeled perspective images, 360 panoramic images fall short in both volume and diversity. In…
Data AugmentationDiversityScene UnderstandingSemantic SegmentationPrincipled Design of Diffusion-based Optimizers for Inverse Problems
Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference times and cumbersome hyperparameter tuning. While pretrained diffusion …
Image ReconstructionAutomatic Tuning of Federated Learning Hyper-Parameters from System Perspective
Federated Learning (FL) is a distributed model training paradigm that preserves clients' data privacy. FL hyper-parameters significantly affect the training overheads in terms of time, computation, and communication. H…
Federated LearningBilevel optimization for learning hyperparameters: Application to solving PDEs and inverse problems with Gaussian processes
Methods for solving scientific computing and inference problems, such as kernel- and neural network-based approaches for partial differential equations (PDEs), inverse problems, and supervised learning tasks, depend cruc…
Hyperparameter OptimizationBilevel OptimizationGaussian Processes