A novel complexity minimization meta-learning framework provably demonstrates that few-shot adaptation error decreases as meta-training data volume increases.
Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with fewer examples, where the choice of meta-learners is crucial. In this paper, we develop Meta-SGD, an SGD-like, easily trainable meta-learner that can initialize and adapt any differentiable learner in just one step, on both supervised learning and reinforcement learning. Compared to the popular meta-learner LSTM, Meta-SGD is conceptually simpler, easier to implement, and can be learned more efficiently. Compared to the latest meta-learner MAML, Meta-SGD has a much higher capacity by learning to learn not just the learner initialization, but also the learner update direction and learning rate, all in a single meta-learning process. Meta-SGD shows highly competitive performance for few-shot learning on regression, classification, and reinforcement learning.
years
2026 6verdicts
UNVERDICTED 6representative citing papers
MetaEvaluator meta-learns an initialization from reference models to enable accurate, label-free performance estimation for unseen models across architectures and modalities.
REINFORCE self-training on competitive programming tasks exhibits robust rise-then-collapse in pass@1; CARE, ES, and GRPO mitigate it in model-size-dependent ways across Qwen-2.5-3B/7B and a Gemma pilot.
AHC applies meta-learned hierarchical compression with dual memory banks to enable continual object detection on MCUs under a 100KB budget, backed by a forgetting bound of O(ε√T + 1/√M) and competitive results on CORe50, TiROD, and PASCAL VOC.
BinomMAML uses a binomial expansion to estimate meta-gradients more accurately than prior approximations, with error bounds that improve on existing methods and decay super-exponentially under mild conditions.
FEDSNet improves few-shot fine-grained image classification by fusing spatial texture and frequency-based structural subspaces to reduce noise overfitting.
citing papers explorer
-
Provable Data Scaling Law for Meta Learning via Complexity Minimization
A novel complexity minimization meta-learning framework provably demonstrates that few-shot adaptation error decreases as meta-training data volume increases.
-
Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning
MetaEvaluator meta-learns an initialization from reference models to enable accurate, label-free performance estimation for unseen models across architectures and modalities.
-
Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training
REINFORCE self-training on competitive programming tasks exhibits robust rise-then-collapse in pass@1; CARE, ES, and GRPO mitigate it in model-size-dependent ways across Qwen-2.5-3B/7B and a Gemma pilot.
-
AHC: Meta-Learned Adaptive Compression for Continual Object Detection on Memory-Constrained Microcontrollers
AHC applies meta-learned hierarchical compression with dual memory banks to enable continual object detection on MCUs under a 100KB budget, backed by a forgetting bound of O(ε√T + 1/√M) and competitive results on CORe50, TiROD, and PASCAL VOC.
-
Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation
BinomMAML uses a binomial expansion to estimate meta-gradients more accurately than prior approximations, with error bounds that improve on existing methods and decay super-exponentially under mild conditions.
-
Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification
FEDSNet improves few-shot fine-grained image classification by fusing spatial texture and frequency-based structural subspaces to reduce noise overfitting.