Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning

• URL: http://arxiv.org/abs/2609.06806v1
• Date: Sun, 06 Sep 2026 19:45:17 GMT
• Title: Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning
• Abstract summary: We show that retraining is most useful in early rounds, while fine-tuning becomes safer once the model trajectory stabilizes.<n>We propose HybridAL, an adaptive training schedule that monitors an online stabilization signal and switches from retraining to fine-tuning after sustained stabilization.
• Score: 1.215621649989295
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training strategy, namely whether to retrain from scratch or fine-tune from the previous checkpoint, is an overlooked decision variable in active learning. We show that this choice has exploitable structure: retraining is most useful in early rounds, when each batch can substantially reshape the labeled distribution, while fine-tuning becomes safer once the model trajectory stabilizes. We propose HybridAL, an adaptive training schedule that monitors an online stabilization signal and switches from retraining to fine-tuning after sustained stabilization. Two complementary signals, spectral exponent change $Δα$ (weight-based) and accuracy change $Δ$Acc (validation-based), span different points on the time-calibration trade-off. Across three encoder backbones and six text-classification tasks (five seeds each), HybridAL keeps endpoint macro-F1 non-inferior to retraining and fine-tuning at a 0.010 margin, saves up to 49% of retraining time, and recovers a substantial fraction of retraining's calibration advantage as measured by negative log-likelihood (NLL). Compared with schedules that switch at a pre-committed round, HybridAL obtains lower NLL at moderate additional cost, showing that trajectory-dependent switching provides a stronger time-calibration trade-off than fixed early switching.

Related papers

• HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning [40.61476978001808]
  We develop HarnessBandit, an online scheduler that selects one harness per step.<n>We train Qwen3.5-2B across six harnesses on ClawGym and evaluate on PinchBench and ClawEval.
  arXiv  Detail & Related papers  (2026-09-12T06:22:45Z)
• From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning [7.33659299625996]
  We introduce Sharpness-Guided Sampling (SGS), which treats the sampling distribution as an active control variable for optimization geometry.<n>On CIFAR-100 with an imbalance ratio of 100, SGS-SAM improves Focal-SAM by 10.85 points in tail accuracy and 3.56 points overall.<n>On ImageNet-LT, it improves ImbSAM by 6.59 points on tail classes and 1.20 points overall.
  arXiv  Detail & Related papers  (2026-07-24T05:56:00Z)
• Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping [56.14767235650558]
  Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length computation tasks.<n>We trace this variance to the spurious correlation in simple algorithmic tasks between sequence length and number of loops.<n>Our work suggests that "when to stop" should be treated as a training design choice, not merely an inference-time-allocation rule.
  arXiv  Detail & Related papers  (2026-06-29T08:58:09Z)
• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning [16.158545640309438]
  We develop a statistical inference framework for gradient-flow training itself.<n>Training time becomes a variance-component parameter governing how variance is reallocated.<n>Deep learning models in fixed gradient regimes provide modern-AI instantiations of the theory.
  arXiv  Detail & Related papers  (2026-05-27T05:32:24Z)
• GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training [21.974153439592317]
  We propose GAC, a noise-aware controller that derives an adaptive mixing weight from online estimates of gradient variance and disagreement between the two training signals.<n>Experiments on math, code, science, and logic benchmarks show that GAC consistently improves hybrid post-training over strong fixed and rule-based baselines.
  arXiv  Detail & Related papers  (2026-05-25T07:52:29Z)
• MARBLE: Multi-Aspect Reward Balance for Diffusion RL [71.6241143519038]
  Reinforcement learning has become the dominant approach for aligning diffusion models with human preferences.<n>Existing practice deal with multiple rewards by training one specialist model per reward.<n>We propose MARBLE, a gradient-space optimization framework that maintains independent advantage estimators for each reward.
  arXiv  Detail & Related papers  (2026-05-07T16:20:42Z)
• Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization [74.91418266859297]
  Implicit process reward models (PRMs) provide fine-grained reward signals along the reasoning process.<n>PRMs suffer from a train-inference mismatch: training only constrains a sequence-level aggregate, whereas inference requires token-level scores to reflect local step quality.<n>We propose a novel Implicit Prefix-Value Reward Model (IPVRM), which directly learns a prefix-conditioned value function estimating the probability of eventual correctness.<n>We also propose Distribution-Level RL (DistRL), which computes TD advantages for both sampled tokens and high-probability candidate tokens.
  arXiv  Detail & Related papers  (2026-04-14T18:19:54Z)
• Optimistic Transfer under Task Shift via Bellman Alignment [5.192817801536311]
  We study online transfer reinforcement learning (RL) in episodic Markov decision processes.<n>We identify one-step Bellman alignment as the correct abstraction for transfer in online RL.<n>We propose re-weighted targeting (RWT), an operator-level correction that retargets continuation values and compensates for transition mismatch.
  arXiv  Detail & Related papers  (2026-01-29T16:16:24Z)
• Reasoning Stabilization Point: A Training-Time Signal for Stable Evidence and Shortcut Reliance [0.0]
  We define explanation drift as the epoch-to-epoch change in normalized token attributions on a fixed probe set.<n>RSP is computed from within-run drift dynamics and requires no tuning on out-of-distribution data.
  arXiv  Detail & Related papers  (2026-01-12T17:48:05Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• SpacTor-T5: Pre-training T5 Models with Span Corruption and Replaced Token Detection [49.43407207482008]
  SpacTor is a new training procedure consisting of a hybrid objective combining span corruption (SC) and token replacement detection (RTD) In our experiments with encoder-decoder architectures (T5) on a variety of NLP tasks, SpacTor-T5 yields the same downstream performance as standard SC pre-training.
  arXiv  Detail & Related papers  (2024-01-24T00:36:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.