FAME learns to route heterogeneous time series to a budgeted subset of forecasting experts using a multidimensional forecastability fingerprint mined from validation performance, achieving 12.4% MSE reduction on a 5,000+ machine industrial dataset while activating 1.92 experts per series on average.
Meta-Learning: A Survey
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible. Not only does this dramatically speed up and improve the design of machine learning pipelines or neural architectures, it also allows us to replace hand-engineered algorithms with novel approaches learned in a data-driven way. In this chapter, we provide an overview of the state of the art in this fascinating and continuously evolving field.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Bayesian PCFG generates synthetic physics-like regression datasets matching eight structural features of the Feynman corpus and enabling equivalent hyperparameter tuning performance to real data.
Diffusion models for in-context meta-learning of robot dynamics outperform deterministic Transformers in robustness to distribution shifts while enabling real-time operation via warm-started sampling.
A proposed imitation learning framework for cable routing robots combines image quality assessment with confidence-weighted training to maintain performance under distorted image inputs.
Proposes Artificial Adaptive Intelligence as the regime between narrow and general AI, defined by elimination of human-specified hyperparameters, and introduces an adaptivity index plus parametric minimality principle grounded in minimum description length.
Two-stage optimization for ML workflows that prioritizes data pipeline search over hyperparameter tuning, with time-allocation policies and a specificity metric for pruning.
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
citing papers explorer
-
FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting
FAME learns to route heterogeneous time series to a budgeted subset of forecasting experts using a multidimensional forecastability fingerprint mined from validation performance, achieving 12.4% MSE reduction on a 5,000+ machine industrial dataset while activating 1.92 experts per series on average.
-
Synthics: Synthetic Physics-like Datasets for Machine Learning
Bayesian PCFG generates synthetic physics-like regression datasets matching eight structural features of the Feynman corpus and enabling equivalent hyperparameter tuning performance to real data.
-
Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics
Diffusion models for in-context meta-learning of robot dynamics outperform deterministic Transformers in robustness to distribution shifts while enabling real-time operation via warm-started sampling.
-
Distortion-Resilient Robotic Imitation Learning for Autonomous Cable Routing
A proposed imitation learning framework for cable routing robots combines image quality assessment with confidence-weighted training to maintain performance under distorted image inputs.
-
Artificial Adaptive Intelligence: The Missing Stage Between Narrow and General Intelligence
Proposes Artificial Adaptive Intelligence as the regime between narrow and general AI, defined by elimination of human-specified hyperparameters, and introduces an adaptivity index plus parametric minimality principle grounded in minimum description length.
-
Two-stage Optimization for Machine Learning Workflow
Two-stage optimization for ML workflows that prioritizes data pipeline search over hyperparameter tuning, with time-allocation policies and a specificity metric for pruning.
-
The Rise and Potential of Large Language Model Based Agents: A Survey
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.