paper-with-me

홈 › Papers

A Lazy Approach to Long-Horizon Gradient-Based Meta-Learning

2021-01-01 · ICCV 2021 10 · Muhammad Abdullah Jamal, Liqiang Wang, Boqing Gong

Gradient-based meta-learning relates task-specific models to a meta-model by gradients. By this design, an algorithm first optimizes the task-specific models by an inner loop and then backpropagates meta-gradients through the loop to update the meta-model. The number of inner-loop optimization steps has to be small (e.g., one step) to avoid high-order derivatives, big memory footprints, and the risk of vanishing or exploding meta-gradients. We propose an intuitive teacher-student scheme to enable the gradient-based meta-learning algorithms to explore long horizons by the inner loop. The key idea is to employ a student network to explore the search space of task-specific models adequately (e.g., by more than ten steps), and a teacher then takes a ``leap'' toward the regions probed by the student. The teacher not only arrives at a high-quality model but also defines a lightweight computation graph for meta-gradients. Our approach is generic, as we verify its effectiveness with four meta-learning algorithms over three tasks: few-shot learning, long-tailed classification, and meta-attack.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningMeta-Learning

Similar Papers 제목 키워드 기반

LAMP: Long-Horizon Adaptive Manipulation Planning for Multi-Robot Collaboration in Cluttered Space

2026-06-28 · Shuai Zhou, Yorai Shaoul, Jiaoyang Li arxiv

Multi-robot manipulation requires jointly reasoning about contact formations, robot motions under coupled dynamics, and collision avoidance. Systematically searching over this large space is difficult and becomes increas…

Reinforcement LearningCollision AvoidanceRobot Manipulation

Non-greedy Gradient-based Hyperparameter Optimization Over Long Horizons

2020-09-28 · Paul Micaelli, Amos Storkey

Gradient-based meta-learning has earned a widespread popularity in few-shot learning, but remains broadly impractical for tasks with long horizons (many gradient steps), due to memory scaling and gradient degradation iss…

Few-Shot LearningHyperparameter OptimizationMeta-Learning

An Investigation of the Bias-Variance Tradeoff in Meta-Gradients

2022-09-22 · Risto Vuorio, Jacob Beck, Shimon Whiteson, Jakob Foerster 외

Meta-gradients provide a general approach for optimizing the meta-parameters of reinforcement learning (RL) algorithms. Estimation of meta-gradients is central to the performance of these meta-algorithms, and has been st…

Meta-LearningReinforcement Learning (RL)

The Lazy Online Subgradient Algorithm is Universal on Strongly Convex Domains

2021-12-01 · NeurIPS 2021 12 · Daron Anderson, Douglas Leith

We study Online Lazy Gradient Descent for optimisation on a strongly convex domain. The algorithm is known to achieve $O(\sqrt N)$ regret against adversarial opponents; here we show it is universal in the sense that it …

Understanding Short-Horizon Bias in Stochastic Meta-Optimization

2018-03-06 · ICLR 2018 1 · Yuhuai Wu, Mengye Ren, Renjie Liao, Roger Grosse

Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training. There has been much recent interest in gradient-based meta-optimization, where one tunes hyperparameters, o…