paper-with-me

Papers

How to warm-start your unfolding network

2025-02-03 · Vicky Kouni

We present a new ensemble framework for boosting the performance of overparameterized unfolding networks solving the compressed sensing problem. We combine a state-of-the-art overparameterized unfolding network with a continuation technique, to warm-start a crucial quantity of the said network's architecture; we coin the resulting continued network C-DEC. Moreover, for training and evaluating C-DEC, we incorporate the log-cosh loss function, which enjoys both linear and quadratic behavior. Finally, we numerically assess C-DEC's performance on real-world images. Results showcase that the combination of continuation with the overparameterized unfolded architecture, trained and evaluated with the chosen loss function, yields smoother loss landscapes and improved reconstruction and generalization performance of C-DEC, consistently for all datasets.

📄 PDF Abstract BibTeX arXiv:2502.01854

Code (0)

등록된 구현이 없습니다.

Tasks

compressed sensing

Similar Papers 제목 키워드 기반

Continual Pre-Training of Large Language Models: How to (re)warm your model?

2023-08-08 · Kshitij Gupta, Benjamin Thérien, Adam Ibrahim, Mats L. Richter 외

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to restart the process over again once new data becomes available. A much cheaper and more efficient solution would be to enable the cont…

Language Modelling

Graph Neural Patching for Cold-Start Recommendations

2024-10-18 · Hao Chen, Yu Yang, Yuanchen Bei, Zefan Wang 외

The cold start problem in recommender systems remains a critical challenge. Current solutions often train hybrid models on auxiliary data for both cold and warm users/items, potentially degrading the experience for the l…

Recommendation Systems

Learning to Warm-Start Fixed-Point Optimization Algorithms

2023-09-14 · Rajiv Sambharya, Georgina Hall, Brandon Amos, Bartolomeo Stellato

We introduce a machine-learning framework to warm-start fixed-point optimization algorithms. Our architecture consists of a neural network mapping problem parameters to warm starts, followed by a predefined number of fix…

Generalization Bounds

Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap

2023-06-20 · Hang Wang, Sen Lin, Junshan Zhang

Warm-Start reinforcement learning (RL), aided by a prior policy obtained from offline training, is emerging as a promising RL approach for practical applications. Recent empirical studies have demonstrated that the perfo…

Offline RLReinforcement Learning (RL)

Heuristic algorithm for 1D and 2D unfolding

2014-10-17 · Yordan Karadzhov

A very simple heuristic approach to the unfolding problem will be described. An iterative algorithm starts with an empty histogram and every iteration aims to add one entry to this histogram. The entry to be added is sel…