Denoising Neural Processes model noisy inputs during meta-learning
On real air-quality sensors, DnNP cuts PM2.5 RMSE by up to 30% and NLL by up to 73% versus standard neural processes.
Stories per day · 30 days
2 RSS
Relatedair-quality1bilevel-optimization1denoising1gpt-21hyperparameter-optimization1neural-processes1newton-methods1uncertainty-quantification1
8 stories, newest first · one card per story
Stories tagged #meta-learning
Newton bilevel methods drop the lower-level strong-convexity assumption
Experiments cover synthetic tasks, data hyper-cleaning, and GPT-2 reweighting, with claimed better complexity than GALET and sl-BAMM.
In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation
A probabilistic Transformer meta-model performs zero-shot system identification on long sequences with calibrated uncertainty.
Optimization Encoders: Rethinking Second-Order Meta-Learning for Neural Fields
MetaLF frames latent optimization as an encoder for second-order meta-learning of conditional neural fields.
Harness Learning Enables Generalizable Test-Time Adaptation
Harness learning trains a proposer to revise an agent's executable harness from execution feedback.
Online Learning via Learned Latent Bayesian Tracking
AURA learns a latent state space so deep models adapt online via Kalman filtering under distribution shift.
ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning
ALPINE is an ultra-lightweight few-shot image classifier that beats Prototypical Networks, Relation Networks, and MAML with 27-53% fewer parameters.
Few-Shot Learning for Network Intrusion Detection: Methods, Datasets, and Performance
A PRISMA-style review of 21 few-shot learning studies for network intrusion detection finds meta-learning and CNNs dominant and evaluation inconsistently reported.