Pith. sign in

REVIEW 19 cited by

Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1906.03671 v2 pith:2PUF2JX6 submitted 2019-06-09 cs.LG stat.ML

Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

Jordan T. Ash , Chicheng Zhang , Akshay Krishnamurthy , John Langford , Alekh Agarwal This is my paper
classification cs.LG stat.ML
keywords batchactivelearningbadgegradientalgorithmdeepdiverse
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of points that are disparate and high-magnitude when represented in a hallucinated gradient space, a strategy designed to incorporate both predictive uncertainty and sample diversity into every selected batch. Crucially, BADGE trades off between diversity and uncertainty without requiring any hand-tuned hyperparameters. We show that while other approaches sometimes succeed for particular batch sizes or architectures, BADGE consistently performs as well or better, making it a versatile option for practical active learning problems.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

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

  1. MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

    cs.LG 2026-05 unverdicted novelty 7.0

    MASS-DPO derives a Plackett-Luce-specific log-determinant Fisher information objective to select non-redundant negative samples, matching or exceeding multi-negative DPO performance with substantially fewer negatives ...

  2. Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object Tracking

    cs.CV 2026-05 unverdicted novelty 7.0

    CUTAL scores multi-frame clips for uncertainty and enforces temporal diversity to train transformer MOT models to near full-supervision performance with 50% of the labels.

  3. UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval

    cs.IR 2026-04 unverdicted novelty 7.0

    UnIte selects target-domain documents for pseudo-query generation by filtering high aleatoric uncertainty and prioritizing high epistemic uncertainty, yielding +2.45 to +3.49 nDCG@10 gains on BEIR with ~4k samples.

  4. Active Learning with Selective Time-Step Acquisition for PDEs

    cs.LG 2025-11 unverdicted novelty 7.0

    STAP reduces training data costs for PDE surrogates by selectively acquiring key time steps per trajectory instead of full simulations.

  5. Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data

    cs.LG 2025-09 unverdicted novelty 7.0

    Introduces the first active learning framework for unaligned multimodal data that selects alignments using uncertainty and diversity to cut annotation costs by up to 40% on benchmarks while preserving accuracy.

  6. Active Statistical Inference

    stat.ML 2024-03 unverdicted novelty 7.0

    Active inference adapts label collection via ML uncertainty to deliver valid statistical inference with substantially fewer samples than standard non-adaptive methods across any data distribution.

  7. Fine-Tuning Language Models from Human Preferences

    cs.CL 2019-09 unverdicted novelty 7.0

    Language models fine-tuned via RL on 5k-60k human preference comparisons produce stylistically better text continuations and human-preferred summaries that sometimes copy input sentences.

  8. Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning

    cs.AI 2026-07 conditional novelty 6.0

    TTCov curates training data for deployment by building an LLM-generated atomic-proposition atlas of the test distribution and greedily selecting clips that match it.

  9. Finding Needles in the Haystack: Transductive Active Labeling in Ecology

    cs.LG 2026-06 unverdicted novelty 6.0

    Transductive evaluation and a hybrid stopping criterion based on rarefaction curves improve rare-class discovery in long-tailed ecological active learning compared to standard inductive methods.

  10. Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees

    cs.AI 2026-04 unverdicted novelty 6.0

    POES frames prompt evaluation as online adaptive testing and uses a provably submodular objective to pick informative examples, delivering 6.2% higher average accuracy and 35-60% token savings versus naive full-set scoring.

  11. Finding Needles in the Haystack: Transductive Active Labeling in Ecology

    cs.LG 2026-06 unverdicted novelty 5.0

    Active learning evaluation in ecology should be transductive rather than inductive, with a hybrid stopping rule that combines prediction and discovery metrics to better recover long-tail classes.

  12. Are Candidate Models Really Needed for Active Learning?

    cs.CV 2026-05 unverdicted novelty 5.0

    Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.

  13. Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensing

    cs.CV 2026-05 unverdicted novelty 5.0

    UGEL employs deep beta regression to estimate uncertainty in one forward pass, enabling faster convergence in edge learning for remote sensing image regression than active or semi-supervised baselines.

  14. Neural Operator Representation of Granular Micromechanics-based Failure Envelope

    physics.comp-ph 2026-04 unverdicted novelty 5.0

    A differentiable neural operator learns the mapping from granular microstructure configurations to failure envelopes, with physics-informed convexity enforcement and active learning for efficient training.

  15. Labeled TrustSet Guided: Batch Active Learning with Reinforcement Learning

    cs.LG 2026-04 unverdicted novelty 5.0

    BRAL-T uses TrustSet-guided reinforcement learning for batch active learning and reports state-of-the-art results on 10 image classification benchmarks plus 2 fine-tuning tasks.

  16. Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification

    cs.CV 2025-09 conditional novelty 5.0

    DECERN selects annotation samples by combining a fusion-based uncertainty score with a diversity calibration that balances closeness to uncertainty-weighted cluster centers and distance from known class anchors.

  17. Active Learning for Optimal Experimental Design in Machine Learning-Based Building Energy System Identification

    eess.SY 2026-06 unverdicted novelty 4.0

    Active learning for optimal experimental design in ML-based building energy system identification yields up to 54% lower RMSE than passive random sampling on the BOPTEST simulator across neural network and Gaussian pr...

  18. Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance

    cs.LG 2026-05 unverdicted novelty 4.0

    Active learning with foundation model priors achieves over 50% annotation savings on imbalanced noisy datasets across image and text domains while maintaining performance.

  19. ShieldGemma: Generative AI Content Moderation Based on Gemma

    cs.CL 2024-07 unverdicted novelty 4.0

    ShieldGemma delivers a family of Gemma2-based classifiers that outperform Llama Guard and WildCard on public safety benchmarks while introducing a synthetic-data curation pipeline for safety tasks.