Universal Algorithm-Implicit Learning

• URL: http://arxiv.org/abs/2602.14761v1
• Date: Mon, 16 Feb 2026 14:05:07 GMT
• Title: Universal Algorithm-Implicit Learning
• Abstract summary: We introduce a theoretical framework for meta-learning which formally defines practical universality and introduces a distinction between algorithm-explicit and algorithm-implicit learning.<n>We present TAIL, a transformer-based algorithm-implicit meta-learner that functions across tasks with varying domains, modalities, and label configurations.<n>TAIL achieves state-of-the-art performance on standard few-shot benchmarks while generalizing to unseen domains.
• Score: 19.712439620866945
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literature uses key terms like "universal" and "general-purpose" inconsistently and lacks precise definitions, hindering comparability. We introduce a theoretical framework for meta-learning which formally defines practical universality and introduces a distinction between algorithm-explicit and algorithm-implicit learning, providing a principled vocabulary for reasoning about universal meta-learning methods. Guided by this framework, we present TAIL, a transformer-based algorithm-implicit meta-learner that functions across tasks with varying domains, modalities, and label configurations. TAIL features three innovations over prior transformer-based meta-learners: random projections for cross-modal feature encoding, random injection label embeddings that extrapolate to larger label spaces, and efficient inline query processing. TAIL achieves state-of-the-art performance on standard few-shot benchmarks while generalizing to unseen domains. Unlike other meta-learning methods, it also generalizes to unseen modalities, solving text classification tasks despite training exclusively on images, handles tasks with up to 20$\times$ more classes than seen during training, and provides orders-of-magnitude computational savings over prior transformer-based approaches.

Related papers

• Towards Generalizable Representations of Mathematical Strategies [0.0]
  We present a novel approach for learning problem-invariant representations of entire algebraic solution pathways.<n>We first construct transition embeddings by computing vector differences between consecutive algebraic states encoded by high-capacity pretrained models.<n> Sequence-level embeddings are then learned via SimCSE, using contrastive objectives to position semantically similar solution pathways close in embedding space.
  arXiv  Detail & Related papers  (2026-04-09T18:26:13Z)
• Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers [22.72866404096086]
  Amortized learning is the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems.<n>Current approaches struggle to scale to large datasets because their capacity to process task data at inference is often limited.<n>We propose iterative amortized inference, a class of models that refine solutions step-by-step over mini-batches.
  arXiv  Detail & Related papers  (2025-10-13T14:40:47Z)
• General-Purpose In-Context Learning by Meta-Learning Transformers [45.63069059498147]
  We show that Transformers and other black-box models can be meta-trained to act as general-purpose in-context learners. We characterize transitions between algorithms that generalize, algorithms that memorize, and algorithms that fail to meta-train at all. We propose practical interventions such as biasing the training distribution that improve the meta-training and meta-generalization of general-purpose in-context learning algorithms.
  arXiv  Detail & Related papers  (2022-12-08T18:30:22Z)
• Set-based Meta-Interpolation for Few-Task Meta-Learning [79.4236527774689]
  We propose a novel domain-agnostic task augmentation method, Meta-Interpolation, to densify the meta-training task distribution. We empirically validate the efficacy of Meta-Interpolation on eight datasets spanning across various domains.
  arXiv  Detail & Related papers  (2022-05-20T06:53:03Z)
• Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks [62.63852372239708]
  Meta learning aims to learn the learning methodology for machine learning from observed tasks, so as to generalize to new query tasks. We interpret such learning methodology as learning an explicit hyper- parameter prediction function shared by all training tasks. Such setting guarantees that the meta-learned learning methodology is able to flexibly fit diverse query tasks.
  arXiv  Detail & Related papers  (2021-07-06T04:05:08Z)
• Meta-Learning with Fewer Tasks through Task Interpolation [67.03769747726666]
  Current meta-learning algorithms require a large number of meta-training tasks, which may not be accessible in real-world scenarios. By meta-learning with task gradient (MLTI), our approach effectively generates additional tasks by randomly sampling a pair of tasks and interpolating the corresponding features and labels. Empirically, in our experiments on eight datasets from diverse domains, we find that the proposed general MLTI framework is compatible with representative meta-learning algorithms and consistently outperforms other state-of-the-art strategies.
  arXiv  Detail & Related papers  (2021-06-04T20:15:34Z)
• Improving Generalization in Meta-learning via Task Augmentation [69.83677015207527]
  We propose two task augmentation methods, including MetaMix and Channel Shuffle. Both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets.
  arXiv  Detail & Related papers  (2020-07-26T01:50:42Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)
• MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures [61.73533544385352]
  We propose a transferable perturbation, MetaPerturb, which is meta-learned to improve generalization performance on unseen data. As MetaPerturb is a set-function trained over diverse distributions across layers and tasks, it can generalize heterogeneous tasks and architectures.
  arXiv  Detail & Related papers  (2020-06-13T02:54:59Z)
• Information-Theoretic Generalization Bounds for Meta-Learning and Applications [42.275148861039895]
  Key performance measure for meta-learning is the meta-generalization gap. This paper presents novel information-theoretic upper bounds on the meta-generalization gap.
  arXiv  Detail & Related papers  (2020-05-09T05:48:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.