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

9 results for “meta-generalization”

Information-Theoretic Generalization Bounds for Meta-Learning and Applicationscs.LG

This paper bounds meta-generalization gap using information theory.

problem Improving sample efficiency for new tasks in meta-learning.

method Information-theoretic upper bounds on meta-generalization gap for two meta-learning classes.

result Novel ITMI bounds for noisy iterative algorithms.

meta-learning information theory generalization sample efficiency MI

2020-05-09abs ↗pdf ↗

Local Nonparametric Meta-Learningcs.LG

Local nonparametric meta-learning improves meta-generalization across tasks.

problem Meta-learning struggles with global inductive biases and out-of-distribution tasks.

method Proposes a local, nonparametric meta-learning algorithm using meta-trained local learning rules.

result Improved meta-generalization and state-of-the-art results in robotics benchmarks.

meta-learning local learning nonparametric inductive bias meta-generalization

2020-02-09abs ↗pdf ↗

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networkscs.LG

Meta-ticket finds optimal sparse subnetworks for few-shot learning in randomly initialized neural networks.

problem Avoiding overfitting in few-shot learning for over-parameterized neural networks.

method Meta-learning approach to find optimal sparse subnetworks.

result Meta-ticket discovers sparse subnetworks that adapt to each task, achieving superior meta-generalization.

few-shot learning meta-learning sparse subnetworks overfitting neural networks

2022-05-31abs ↗pdf ↗

A General framework for PAC-Bayes Bounds for Meta-Learningcs.LG

This paper improves meta-learning by developing new PAC-Bayes bounds.

problem Meta-learning generalization gap across multiple tasks.

method Upper bounding convex functions linking environment and task-level losses.

result New PAC-Bayes bounds for meta-learning with improved algorithms.

meta-learning PAC-Bayes bounds generalization inductive bias

2022-06-11abs ↗pdf ↗

A Unified Information-Theoretic Framework for Meta-Learning Generalizationstat.ML

Unified framework improves meta-learning generalization bounds.

problem Limited sharpness of existing meta-generalization bounds.

method Unified information-theoretic derivation for single-step bounds.

result Unified bounds exhibit tighter scaling and computational advantages.

meta-learning generalization information-theoretic bounds gradient covariance

2025-01-26abs ↗pdf ↗

Meta-learning autoencoders for few-shot predictioncs.LG

Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task neural networks with a meta-recognition model which learns a succinct model code vi…

2018-07-26abs ↗pdf ↗

LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMscs.LG

LoRA fine-tuning on CPUs without GPUs achieves comparable performance to GPU-based methods.

problem Limited computational resources for fine-tuning LLMs.

method Developed a CPU-efficient method to learn meta-operators for LoRA weights.

result LoRA adapters trained on CPUs outperform base models on downstream tasks.

LoRA LLMs Fine-tuning CPU Meta-operators

2025-07-02abs ↗pdf ↗

General-Purpose In-Context Learning by Meta-Learning Transformerscs.LG

Transformers learn to solve various tasks without explicit design.

problem Training models with minimal inductive bias.

method Meta-learning approach to train general-purpose in-context learning algorithms.

result Transformers can be meta-trained to solve a wide range of tasks.

meta-learning transformers in-context learning general-purpose black-box models

2022-12-08abs ↗pdf ↗

Learning Prototype-oriented Set Representations for Meta-Learningcs.LG

Paper introduces a novel framework for set input tasks in meta-learning.

problem Meta-learning problems with set inputs often require efficient summary networks.

method Prototype-oriented optimal transport (POT) framework to improve summary networks.

result Significantly improves summary statistics from sets in meta-learning.

meta-learning set input prototype optimal transport few-shot classification

2021-10-18abs ↗pdf ↗