Pith. sign in

REVIEW 1 cited by

Training-Free Neural Active Learning with Initialization-Robustness Guarantees

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.04454 v1 pith:27SWTQYW submitted 2023-06-07 cs.LG cs.AI

classification cs.LGcs.AI
keywords dataneuralactivecriterionev-gplearningperformancepredictive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Existing neural active learning algorithms have aimed to optimize the predictive performance of neural networks (NNs) by selecting data for labelling. However, other than a good predictive performance, being robust against random parameter initializations is also a crucial requirement in safety-critical applications. To this end, we introduce our expected variance with Gaussian processes (EV-GP) criterion for neural active learning, which is theoretically guaranteed to select data points which lead to trained NNs with both (a) good predictive performances and (b) initialization robustness. Importantly, our EV-GP criterion is training-free, i.e., it does not require any training of the NN during data selection, which makes it computationally efficient. We empirically demonstrate that our EV-GP criterion is highly correlated with both initialization robustness and generalization performance, and show that it consistently outperforms baseline methods in terms of both desiderata, especially in situations with limited initial data or large batch sizes.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Uncovering Scaling Laws for Large Language Models via Inverse Problems

    cs.LG 2025-09 conditional novelty 4.0 of 10

    Proposes using inverse problems to discover LLM scaling laws, but provides no empirical evidence or new results.

Pith tools