{"work":{"id":"cfd46fb8-7c98-41ac-8499-e11236b08f18","openalex_id":null,"doi":null,"arxiv_id":"1803.02999","raw_key":null,"title":"On First-Order Meta-Learning Algorithms","authors":null,"authors_text":"A","year":2018,"venue":"cs.LG","abstract":"This paper considers meta-learning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i.e., learns quickly) when presented with a previously unseen task sampled from this distribution. We analyze a family of algorithms for learning a parameter initialization that can be fine-tuned quickly on a new task, using only first-order derivatives for the meta-learning updates. This family includes and generalizes first-order MAML, an approximation to MAML obtained by ignoring second-order derivatives. It also includes Reptile, a new algorithm that we introduce here, which works by repeatedly sampling a task, training on it, and moving the initialization towards the trained weights on that task. We expand on the results from Finn et al. showing that first-order meta-learning algorithms perform well on some well-established benchmarks for few-shot classification, and we provide theoretical analysis aimed at understanding why these algorithms work.","external_url":"https://arxiv.org/abs/1803.02999","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-24T23:25:03.861266+00:00","pith_arxiv_id":"1803.02999","created_at":"2026-05-09T23:29:43.753069+00:00","updated_at":"2026-05-24T23:25:03.861266+00:00","title_quality_ok":true,"display_title":"Reptile: a scalable metalearning algorithm","render_title":"Reptile: a scalable metalearning algorithm"},"hub":{"state":{"work_id":"cfd46fb8-7c98-41ac-8499-e11236b08f18","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":25,"external_cited_by_count":null,"distinct_field_count":7,"first_pith_cited_at":"2019-07-11T06:47:30+00:00","last_pith_cited_at":"2026-05-21T05:38:47+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-25T04:05:29.505814+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":1},{"context_polarity":"unclear","n":1},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}