paper-with-me

홈 › Papers

Task Weighting in Meta-learning with Trajectory Optimisation

2023-01-04 · Cuong Nguyen, Thanh-Toan Do, Gustavo Carneiro

Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal solutions. In this paper, we introduce a new principled and fully-automated task-weighting algorithm for meta-learning methods. By considering the weights of tasks within the same mini-batch as an action, and the meta-parameter of interest as the system state, we cast the task-weighting meta-learning problem to a trajectory optimisation and employ the iterative linear quadratic regulator to determine the optimal action or weights of tasks. We theoretically show that the proposed algorithm converges to an $\epsilon_{0}$-stationary point, and empirically demonstrate that the proposed approach out-performs common hand-engineering weighting methods in two few-shot learning benchmarks.

📄 PDF Abstract BibTeX arXiv:2301.01400

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningMeta-Learning

Similar Papers 제목 키워드 기반

End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes

2023-05-25 · NeurIPS 2023 11 · Alexandre Maraval, Matthieu Zimmer, Antoine Grosnit, Haitham Bou Ammar

Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acq…

Bayesian OptimisationInductive BiasReinforcement Learning (RL)valid

Trajectory-Aware Flow Matching for Topology Optimisation

2026-07-16 · Shusheng Xiao, Jinshuai Bai, Hyogu Jeong, Yunfei Xi 외 arxiv

Topology optimisation (TO) often requires repeated finite element analysis and sensitivity-based material updates, which can be costly when multiple candidate designs are needed under varying physical and design conditio…

Learning Cardiac Motion Priors for Implicit Neural Representations

2026-07-01 · Andrew Bell, George Webber, Andrew P King, Steffen E Petersen 외 arxiv

Implicit neural representations (INRs) are well suited to cardiac motion estimation, providing continuous, compact representations of motion fields. However, fitting an INR to each image sequence is time-consuming and se…

Auto-Lambda: Disentangling Dynamic Task Relationships

2022-02-07 · Shikun Liu, Stephen James, Andrew J. Davison, Edward Johns

Understanding the structure of multiple related tasks allows for multi-task learning to improve the generalisation ability of one or all of them. However, it usually requires training each pairwise combination of tasks t…

Auxiliary LearningMeta-LearningMulti-Task LearningRobot Manipulation

Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees

2025-10-14 · Yiming Zhang, Chester Holtz, Gal Mishne, Alex Cloninger arxiv

Learning with noisy labels remains challenging because over-parameterized networks memorize corrupted supervision. Meta-learning-based sample reweighting mitigates this by using a small clean subset to guide training, ye…

Learning with noisy labels