A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated program learning and other cases. A novel characterization of the concept of a "good quality feature" for such an optimization problem is pro…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
28 results for “metalearning”
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable function that we parameterize as a deep neural network. Reading from the neural memory function amounts to pushing an input (the key vector) throug…
Metalearning optimizes autoencoder dimensions for efficient data representation.
problem Selecting optimal dimension for autoencoder output to balance accuracy and complexity.
method Metalearning approach using actor-critic algorithm to dynamically adjust dimension.
result Automatic selection of minimum number of bases for optimal reconstruction.
Bayesian metalearning improves performance in linear bandits with misspecified priors.
problem Improper priors lead to suboptimal performance in sequential decision-making.
method Proves performance bounds for metalearning priors in stochastic linear bandits and develops a metalearning algorithm.
result Metalearning can improve performance by learning the prior from multiple tasks.
Metalearned neural circuit performs inference over open classes.
problem Nonparametric Bayesian models' practical barriers in real-world applications.
method Extract inductive bias from nonparametric Bayesian model and transfer to neural network.
result Metalearned neural circuit achieves comparable or better performance than particle filter-based methods.
Study compares methods for treatment assignment, finding A-learner best for playlist generation.
problem Treatment assignment in various applications.
method Three classes of algorithms: O-learner, E-learner, A-learner.
result Optimizing for outcomes or causal effects does not lead to optimal treatment assignments.
Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research. Loss functions are a type of metaknowledge that is crucial to effective training of DNNs, however, their potential role in metalearning has not yet been fully explored. Whereas early work f…
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds representations via slow weights, learned across tasks through SGD, while fast wei…
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework of metalearning, where the aim is to replicate some of the flexibility of human …
As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning. Methods for discovering hyperparameters, topologies, and learning rate schedules have lead to significant increases in performance. This paper shows that loss functions…
Much of the work in metalearning has focused on classifier selection, combined more recently with hyperparameter optimization, with little concern for data preprocessing. Yet, it is generally well accepted that machine learning applications require not only model building, but also data preprocessing. In other words, p…
Neural network tackles continual learning with neuromodulation and local error signals.
problem Catastrophic forgetting in continuous learning.
method Biologically-inspired neural architecture with local learning and neuromodulation, combined with transfer metalearning.
result Superior performance in continual learning tasks compared to other approaches.
Machine Learning (ML) has been successfully applied to a wide range of domains and applications. One of the techniques behind most of these successful applications is Ensemble Learning (EL), the field of ML that gave birth to methods such as Random Forests or Boosting. The complexity of applying these techniques togeth…
Meta-learning framework uses task similarity through nonparametric kernel regression.
problem Limited tasks and outliers/dissimilar tasks hinder meta-learning performance.
method Nonparametric kernel regression to quantify and use task similarity.
result Meta-learning algorithm outperforms existing methods in task-limited settings.
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discover…
MetaTS learns to explore better by meta-learning prior from bandit instances.
problem Efficient exploration in bandit problems.
method MetaThompson Sampling (MetaTS) that meta-learns the prior from bandit instances.
result MetaTS quickly adapts to unknown prior and achieves better exploration.
Meta-learning overfits both model and base learner; meta-augmentation helps.
problem Meta-learning overfits model and base learner.
method Use an information-theoretic framework to describe and demonstrate meta-augmentation.
result Meta-augmentation produces large complementary benefits to meta-regularization.
RCNPs extend equivariant neural processes to higher dimensions, improving performance on tasks with inherent symmetries.
problem Inherently equivariant tasks in spatio-temporal modeling, Bayesian Optimization, and continuous control.
method Relational Conditional Neural Processes (RCNPs) that extend equivariances to higher dimensions.
result Empirically competitive performance on tasks with equivariances.
Method learns equivariances from data without custom architecture design.
problem Learning equivariances for tasks without manually designed architectures.
method Reparameterization to learn equivariant parameter sharing.
result Can learn equivariances for any finite group of transformations.
The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most commonly-used in practice. This paper shows that evolutionary algorithms can discover novel…
A new deep learning benchmark reduces resource needs.
problem Understanding and training deep learning models requires significant resources.
method Introducing MNIST-1D, a minimalist benchmark.
result MNIST-1D enables efficient deep learning research and prototyping.
Auto-PyTorch automates deep learning by optimizing neural architectures and hyperparameters.
problem Automated deep learning for tabular data with robust and efficient optimization.
method Combines multi-fidelity optimization, portfolio construction, and warmstarting with ensembling.
result Achieves state-of-the-art performance on tabular benchmarks.
Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forgetcs.LG
We explore the behavior of a standard convolutional neural net in a continual-learning setting that introduces visual classification tasks sequentially and requires the net to master new tasks while preserving mastery of previously learned tasks. This setting corresponds to that which human learners face as they acquir…
Evolutionary methods improve neural network loss functions, reducing overfitting.
problem Improving neural network performance and preventing overfitting.
method Evolutionary computation to optimize loss functions, balancing error pull and overfitting push.
result Evolved loss functions effectively reduce overfitting, leading to better performance and robustness.
Causal ML methods failed to validate their personalized treatment effects in two large trials.
problem Validating causal machine learning methods for personalized treatment effects in precision medicine.
method Assessed 17 mainstream causal heterogeneity ML methods using two large randomized controlled trials.
result None of the ML methods reliably validated their performance, internal or external, showing significant discrepancies between training and test data.
One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Videocs.LG
Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization to unseen situations difficult without a large number of demonstrations in varyi…
Proposes a new method to optimize treatment allocation with budget constraints.
problem Optimizing treatment allocation with budget constraints in marketing.
method Learning to rank for profit maximization.
result Learning to rank can maximize the area under a policy's incremental profit curve.
To select the best algorithm for a new problem is an expensive and difficult task. However, there are automatic solutions to address this problem: using Metalearning, which takes advantage of problem characteristics (i.e. metafeatures), one is able to predict the relative performance of algorithms. In the Collaborative…