Meta-RL learns shared and task-specific information for quick adaptation.
problem Data inefficiency and limited generalization in deep RL.
method Task embedding and shared policy learned via SGD meta-learner.
result 3 to 4 times higher returns on novel tasks compared to baselines.
Meta-learners improve causal effect estimation in small samples.
problem Estimating causal effects using machine learning methods.
method Sample-splitting and cross-fitting to reduce overfitting bias.
result Meta-learners' performance depends on sample size and estimation procedure.
This paper analyzes meta-learners for estimating multi-valued treatment effects.
problem Estimating Conditional Average Treatment Effects (CATE) with multi-valued treatments.
method The paper considers different meta-learners and analyzes their error bounds.
result Meta-learners perform well as the number of treatments increases, improving upon naive extensions.
Study evaluates different meta-learners for multi-view stacking.
problem Choosing the best meta-learner for multi-view stacking.
method Seven different meta-learners were evaluated in simulations and real data.
result Nonnegative lasso, nonnegative adaptive lasso, and nonnegative elastic net are suitable meta-learners.
New meta-learners estimate time-varying treatment effects without model assumptions.
problem Estimating treatment effects over time in personalized medicine.
method Model-agnostic meta-learners for weighted pseudo-outcome regressions.
result Comprehensive theoretical analysis and practical insights for choosing meta-learners.
A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of current meta-learning methods assume that the meta-training set consists of relevant tasks sampled from a single distribution. In practice, …
Meta-learners estimate CATE from multiple environments with partial identification.
problem Estimating CATE from observational data across multiple environments with violations of causal assumptions.
method Adapt IV literature for partial identification, propose model-agnostic meta-learners.
result Meta-learners effectively estimate CATE bounds across various experiments.
New method improves CATE estimation in low overlap regions.
problem Low overlap in CATE estimation leads to poor performance of meta-learners.
method Overlap-Adaptive Regularization (OAR) that regularizes models proportionally to overlap weights.
result OAR significantly improves CATE estimation in low-overlap settings.
New algorithm TURTLE outperforms MAML and meta-learner LSTM.
problem Learning new tasks quickly with limited data and compute power.
method Combining insights from MAML and meta-learner LSTM, TURTLE uses second-order gradients.
result TURTLE outperforms MAML and meta-learner LSTM in few-shot learning tasks.
A new method improves few-shot image classification by updating top layers.
problem Few-shot image classification with limited data.
method Layer-wise adaptive updating (LWAU) for meta-learning.
result LWAU outperforms existing methods with a clear margin and learns more efficiently.
Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning. In this paper, we verify that au…
CosML combines domain-specific meta-learners for cross-domain few-shot classification.
problem Generalizing to unseen domains while meta-learning on multiple seen domains.
method CosML trains domain-specific meta-learners and combines their meta-parameters in the parameter space.
result CosML outperforms state-of-the-art methods and achieves strong cross-domain generalization.
Meta-learning selects best time series forecasting method.
problem Selecting the best time series forecasting method.
method Meta-learning approach using a pool of forecasting algorithms and feature selection.
result Meta-learners outperformed individual forecasters and improved performance with feature selection.
Meta-trained LSTM Meta-Learners learn tasks faster and differently than DL and RL systems.
problem Understanding the learning dynamics of meta-trained LSTM Meta-Learners compared to traditional DL and RL systems.
method Comparative analysis of learning trajectories on three structured tasks.
result Meta-trained LSTM Meta-Learners learn all task structure concurrently, unlike sample-inefficient DL and RL systems.
Deep neural networks excel in regimes with large amounts of data, but tend to struggle when data is scarce or when they need to adapt quickly to changes in the task. In response, recent work in meta-learning proposes training a meta-learner on a distribution of similar tasks, in the hopes of generalization to novel but…
A new meta-learner improves prediction of individualized outcomes in sequential decisions.
problem Predicting individualized outcomes over long horizons in sequential decision-making.
method Developed a novel meta-learner called DRQ-learner with theoretical guarantees of orthogonality and quasi-oracle efficiency.
result DRQ-learner achieves quasi-oracle efficiency, doubly robustness, and Neyman-orthogonality.
Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during …
Stacked conformal prediction simplifies model validation.
problem Validating stacked predictive models efficiently.
method Meta-learner at the top of a stacked ensemble for approximate marginal validity.
result The method achieves approximate marginal validity without a separate calibration sample.
F-PACOH improves meta-learners' reliability in uncertain regions.
problem Overconfident uncertainty estimates in meta-learning.
method Meta-learning priors as stochastic processes in function space, directly steering predictions towards high epistemic uncertainty.
result Significantly outperforms other meta-learners in Bayesian Optimization.
Adaptive-Step Graph Meta-Learner tackles few-shot graph classification with limited labeled data.
problem Few labeled graph data in bioinformatics and other applications.
method A novel framework combining a graph meta-learner and a step controller for robust and generalization.
result State-of-the-art results on several few-shot graph classification tasks.
New method for incremental meta-learning reduces forgetting and improves performance.
problem Incremental meta-learning for few-shot classification tasks.
method Indirect Discriminant Alignment (IDA) with incremental updates.
result Incremental learning reduces forgetting and improves performance.
Meta-learner estimates heterogeneous DiD effects robustly.
problem Estimating heterogeneous treatment effects in panel data with DiD.
method Doubly robust meta-learner for CATT, using convex risk minimization and auxiliary models.
result Superior performance over existing methods in empirical tests.
In unsupervised ensemble learning, one obtains predictions from multiple sources or classifiers, yet without knowing the reliability and expertise of each source, and with no labeled data to assess it. The task is to combine these possibly conflicting predictions into an accurate meta-learner. Most works to date assume…
Data-driven model selection reduces regret in sequential decisions.
problem Optimizing model selection in stochastic environments with bandit feedback.
method Data-driven regret balancing for model selection.
result Meta-learner selects the best base learner based on actual realized regret.
Meta-learning algorithm improves AI efficiency by teaching itself.
problem Overcoming meta-optimization challenges in AI learning.
method Bootstraps a target from the meta-learner and optimizes the meta-learner by minimizing distance under a chosen metric.
result Achieves state-of-the-art performance on Atari ALE benchmark and demonstrates efficiency gains in multi-task learning.
Meta learning can adapt fast but is vulnerable to adversarial attacks.
problem Vulnerability of meta learning to adversarial attacks.
method Formal definition of adversarial attacks unique to meta learning, proposing an attacking algorithm.
result Meta learning is vulnerable to adversarial attacks.
We propose a meta-learning algorithm utilizing a linear transformer that carries out null-space projection of neural network outputs. The main idea is to construct an alternative classification space such that the error signals during few-shot learning are quickly zero-forced on that space so that reliable classificati…
Researchers analyze and compare nonparametric meta-learners for estimating heterogeneous treatment effects.
problem Evaluating treatment effectiveness in empirical science, especially when effects vary among individuals.
method Theoretical analysis of four meta-learning strategies, focusing on plug-in estimation and pseudo-outcome regression.
result Theoretical insights guide algorithm design and reveal relative strengths of different learners under various data-generating processes.
Improves memory efficiency for meta-learning with large images.
problem High memory usage in meta-learning for few-shot classification.
method LITE: episodic training scheme that decomposes task gradients and back-propagates only a random subset of images.
result Achieves state-of-the-art accuracy on real-world and challenging benchmarks.
Meta-learning bound uses conditional mutual information.
problem Bounding generalization performance in meta-learning.
method Extends CMI framework to meta-learning with a meta-supersample.
result Explicit bound involving two CMI terms.
The paper estimates personalized treatment effects in medical settings with competing risks.
problem Estimating treatment effectiveness for specific events in the presence of alternative event types.
method Meta-learners combining Cox regression or random survival forests for risk modeling and elastic net regression or random forests for direct CATE modeling.
result Compared meta-learners in multiple simulation settings, providing practical guidance for model selection.
Paper tackles cold-start problems in online recommendation with few-shot learning and meta learning.
problem Cold-start problems in practical recommendations with limited interaction data.
method Combines scenario-specific learning with sequential meta-learning to create an integrated end-to-end framework.
result Significant gains over state-of-the-arts for cold-start problems in online recommendation.
New method uses SHAP for biomarker identification in CATE models.
problem Identifying predictive biomarkers from observational data.
method Surrogate estimation approach using SHAP values for CATE meta-learners.
result SHAP accurately identifies biomarkers in high-dimensional data.
Meta-learning strategy improves few-shot classification performance.
problem Few-shot classification with deep neural networks struggles when labeled samples are limited.
method Proposes an easy-to-hard expert meta-training strategy to arrange training tasks based on task hardness.
result Meta-learners achieve better results with the proposed expert training strategy.
Two new methods generate probabilistic forecasts of individual treatment effects.
problem Generating probabilistic forecasts of individual treatment effects for risk-aware decision-making.
method Proposes CCT and CMC meta-learners combining conformal predictive systems with analytic convolution or Monte Carlo sampling.
result Achieve probabilistically calibrated predictive distributions and performant continuous ranked probability scores.
Meta-learning system predicts when tuning SVM hyperparameters improves performance.
problem High computational cost of hyperparameter tuning for machine learning models.
method Meta-learning recommender system using meta-features and meta-learners.
result Meta-learning system accurately predicts when tuning improves SVM performance.
The paper proposes a method to assess surrogate heterogeneity in non-randomized data.
problem Lack of methods to evaluate surrogate heterogeneity in non-randomized data.
method Proposes a framework using meta-learners to assess surrogate heterogeneity in real-world data.
result Identifies individuals for whom the surrogate is a valid replacement of the primary outcome.
MTL2L learns to adapt optimisation rules for unseen data.
problem Learners need to adapt to unseen data domains.
method Introduces MTL2L, a context-aware neural optimiser.
result MTL2L can adapt optimisation rules for unseen data.
IE-GP framework learns sequentially arriving data with adaptive kernels.
problem Sequential data adaptation in Gaussian process models.
method Incremental ensemble of Gaussian process learners with adaptive weights.
result IE-GP framework effectively learns and adapts to sequential data.
We develop ensemble Convolutional Neural Networks (CNNs) to classify the transportation mode of trip data collected as part of a large-scale smartphone travel survey in Montreal, Canada. Our proposed ensemble library is composed of a series of CNN models with different hyper-parameter values and CNN architectures. In o…
A computational theory reduces agent evaluation errors and speeds up processes.
problem Efficient evaluation of mini agents at reduced cost.
method Developed a computational theory and a meta-learner to handle heterogeneous agents.
result Reduced evaluation errors by 24.1% to 99.0% across various scenarios.
LLMs learn to recommend models and hyperparameters from dataset metadata.
problem Model and hyperparameter selection in machine learning is challenging and resource-intensive.
method Converted datasets into metadata and prompted LLMs to recommend models and hyperparameters.
result LLMs can recommend competitive models and hyperparameters without search.
Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-learning category, both of which have achieved successes in the simplified "k-shot N-way" image c…
Local SGD outperforms minibatch SGD for quadratic objectives.
problem Theoretical foundations of local SGD are lacking.
method Proved local SGD strictly dominates minibatch SGD for quadratic objectives and accelerated local SGD is minimax optimal.
result Local SGD does not dominate minibatch SGD in general convex objectives.
Meta-learner infers subtask graph to adapt quickly to unknown tasks.
problem Adapting to unknown tasks with unknown subtask dependencies in few-shot RL.
method Meta-learner with Subtask Graph Inference (MSGI) and UCB-inspired intrinsic reward.
result Accurately infers latent task parameters and adapts more efficiently.
Minibatch SGD outperforms Local SGD in heterogeneous distributed learning.
problem Optimizing a combined convex objective with stochastic gradient estimates from different machines.
method Analysis of Minibatch SGD and Local SGD in a heterogeneous distributed setting.
result Minibatch SGD dominates Local SGD in the heterogeneous distributed setting.
PACOH improves meta-learning with theoretical guarantees and practical efficiency.
problem Meta-learning's generalization to unseen tasks is poorly understood, especially with limited meta-training tasks.
method PAC-Bayesian framework for deriving generalization bounds and developing PAC-optimal meta-learning algorithms.
result PACOH yields state-of-the-art performance in predictive accuracy and uncertainty estimation.
Meta-learning improves few-shot learning by propagating knowledge across related classes on a graph.
problem Few-shot learning suffers from insufficient training data.
method Developed a Gated Propagation Network (GPN) that learns to propagate messages between prototypes of different classes on a graph.
result GPN outperforms recent meta-learning methods on benchmark datasets.