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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “meta-overfitting”

Learning Context-aware Task Reasoning for Efficient Meta-reinforcement Learningcs.LG

Novel meta-RL strategy improves efficiency in learning novel tasks.

problem Efficiency in learning novel tasks using deep RL.

method Decomposes meta-RL into task-exploration, task-inference, and task-fulfillment; uses deep networks and a task encoder.

result Improves sample efficiency and mitigates meta-overfitting.

meta-reinforcement learning task reasoning sample efficiency meta-overfitting deep networks

2020-03-03abs ↗pdf ↗

Curriculum in Gradient-Based Meta-Reinforcement Learningcs.LG

Gradient-based meta-RL fails with incorrect task distributions, leading to instability and poor performance.

problem Gradient-based meta-RL's sensitivity to task distributions causes instability and poor performance.

method Proposes meta Active Domain Randomization (meta-ADR) to learn task distributions for gradient-based meta-RL.

result Meta-ADR improves stability and generalization of MAML on simulated locomotion and navigation tasks.

meta-reinforcement learning gradient-based meta-learning task distribution domain randomization meta-overfitting

2020-02-19abs ↗pdf ↗

Overtuning in Hyperparameter Optimizationcs.LG

The paper investigates overfitting in hyperparameter optimization.

problem Overfitting in hyperparameter optimization (overtuning).

method Formal definition, large-scale reanalysis of HPO benchmark data, analysis of factors affecting overtuning.

result Overtuning is more common than previously assumed, leading to worse generalization error in 10% of cases.

hyperparameter optimization overfitting overtuning resampling generalization error

2025-06-24abs ↗pdf ↗

Fast Context Adaptation via Meta-Learningcs.LG

We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable. CAVIA partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and shared param…

2018-10-08abs ↗pdf ↗

Meta-Learning with Network Pruningcs.LG

Meta-learning with network pruning reduces overfitting and improves few-shot learning.

problem Overfitting in meta-learning models with over-parameterized neural networks.

method Network pruning to control capacity and explicitly reduce generalization gap.

result Uniform concentration analysis shows the benefit of network capacity constraint.

meta-learning network pruning few-shot learning overfitting generalization

2020-07-07abs ↗pdf ↗

An Extensive Experimental Evaluation of Automated Machine Learning Methods for Recommending Classification Algorithms (Extended Version)cs.LG

Paper compares AutoML methods for recommending classification algorithms.

problem Finding the best classification algorithm for a dataset.

method Four AutoML methods using Evolutionary Algorithms and CASH approach.

result EA-based methods, especially decision-tree induction, produce interpretable models.

AutoML Classification Algorithms Evolutionary Algorithms Meta-learning Interpretable Models

2020-09-16abs ↗pdf ↗