The Curse of Low Task Diversity: On the Failure of Transfer Learning to
Outperform MAML and Their Empirical Equivalence

The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence

2 August 2022

Oluwasanmi Koyejo

Papers citing "The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence"

12 / 12 papers shown

Title
DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks Wei Cui Tongzi Wu Jesse C. Cresswell Yi Sui Keyvan Golestan 55 0 0 12 Mar 2025
Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models Yulei Qin Yuncheng Yang Pengcheng Guo Gang Li Hang Shao Yuchen Shi Zihan Xu Yun Gu Ke Li Xing Sun ALM 85 11 0 31 Dec 2024
A Survey of Multimodal Large Language Model from A Data-centric Perspective Tianyi Bai Hao Liang Binwang Wan Yanran Xu Xi Li ... Ping-Chia Huang Jiulong Shan Conghui He Binhang Yuan Wentao Zhang 47 36 0 26 May 2024
Separating the Wheat from the Chaff with BREAD: An open-source benchmark and metrics to detect redundancy in text Isaac Caswell Lisa Wang Isabel Papadimitriou 18 0 0 11 Nov 2023
Is Pre-training Truly Better Than Meta-Learning? Brando Miranda P. Yu Saumya Goyal Yu-xiong Wang Oluwasanmi Koyejo 26 5 0 24 Jun 2023
Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data Alycia Lee Brando Miranda Sudharsan Sundar Sanmi Koyejo 21 6 0 24 Jun 2023
The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence Brando Miranda Yu-xiong Wang Sanmi Koyejo 8 0 0 24 Dec 2021
Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis Qi Chen Changjian Shui M. Marchand 35 43 0 29 Sep 2021
The Role of Global Labels in Few-Shot Classification and How to Infer Them Ruohan Wang Massimiliano Pontil C. Ciliberto VLM 24 16 0 09 Aug 2021
The Advantage of Conditional Meta-Learning for Biased Regularization and Fine-Tuning Giulia Denevi Massimiliano Pontil C. Ciliberto 32 39 0 25 Aug 2020
Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML Aniruddh Raghu M. Raghu Samy Bengio Oriol Vinyals 170 634 0 19 Sep 2019
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Chelsea Finn Pieter Abbeel Sergey Levine OOD 243 11,568 0 09 Mar 2017