Hedging on the Frontier: Learning New Tasks with Few Samples

• URL: http://arxiv.org/abs/2605.30997v1
• Date: Fri, 29 May 2026 08:30:27 GMT
• Title: Hedging on the Frontier: Learning New Tasks with Few Samples
• Abstract summary: Empirically, we observe that weak monotonicity is often approximately satisfied.<n>We show that not only can we prune the model class based on monotonicity, but we can also further adapt to the geometry of the available trade-offs by hedging on the frontier.
• Score: 11.745953914883769
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When a learner faces a new task with few samples, it must leverage any available side information. In practice, this often comes in the form of model evaluations on related tasks in public benchmarks. A key question then is how to model task relatedness such that it is both realistic and the benchmark evaluations lead to provable gains. Empirically, we observe that weak monotonicity is often approximately satisfied: if a model dominates another on many benchmarks, it also tends to outperform on the new task. We explore the statistical complexity of learning under (approximate) weak monotonicity, leveraging it within two learning paradigms: transfer learning and model selection aggregation. We show that not only can we prune the model class based on monotonicity, but we can also further adapt to the geometry of the available trade-offs by hedging on the frontier.

Related papers

• Reasoning with Sampling: Your Base Model is Smarter Than You Think [52.639108524651846]
  We propose a simple iterative sampling algorithm leveraging the base models' own likelihoods.<n>We show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL.<n>Our method does not require training, curated datasets, or a verifier.
  arXiv  Detail & Related papers  (2025-10-16T17:18:11Z)
• Self-Improving LLM Agents at Test-Time [49.9396634315896]
  One paradigm of language model (LM) fine-tuning relies on creating large training datasets.<n>In practice, gathering large sets of data is inefficient, and training on them is prohibitively expensive.<n>We study two variants of this approach: Test-Time Self-Improvement (TT-SI) and Test-Time Distillation (TT-D)
  arXiv  Detail & Related papers  (2025-10-09T06:37:35Z)
• Small Models, Smarter Learning: The Power of Joint Task Training [23.91574901740084]
  Our study focuses on the ListOps dataset, which consists of nested mathematical operations.<n>We observe that sum modulo n is the hardest to learn.<n>We show that joint training not only improves performance but also leads to qualitatively different model behavior.
  arXiv  Detail & Related papers  (2025-05-23T20:56:37Z)
• Multi-Level Collaboration in Model Merging [56.31088116526825]
  This paper explores the intrinsic connections between model merging and model ensembling.<n>We find that even when previous restrictions are not met, there is still a way for model merging to attain a near-identical and superior performance similar to that of ensembling.
  arXiv  Detail & Related papers  (2025-03-03T07:45:04Z)
• Temporal Test-Time Adaptation with State-Space Models [4.248760709042802]
  Adapting a model on test samples can help mitigate this drop in performance. Most test-time adaptation methods have focused on synthetic corruption shifts. We propose STAD, a probabilistic state-space model that adapts a deployed model to temporal distribution shifts.
  arXiv  Detail & Related papers  (2024-07-17T11:18:49Z)
• OLMES: A Standard for Language Model Evaluations [64.85905119836818]
  OLMES is a documented, practical, open standard for reproducible language model evaluations.<n>It supports meaningful comparisons between smaller base models that require the unnatural "cloze" formulation of multiple-choice questions.<n> OLMES includes well-considered, documented recommendations guided by results from existing literature as well as new experiments resolving open questions.
  arXiv  Detail & Related papers  (2024-06-12T17:37:09Z)
• Negotiated Representations to Prevent Overfitting in Machine Learning Applications [0.0]
  Overfitting is a phenomenon that occurs when a machine learning model is trained for too long and focused too much on the exact fitness of the training samples to the provided training labels.<n>We present an approach that increases the classification accuracy of machine learning models by allowing the model to negotiate output representations of the samples with previously determined class labels.
  arXiv  Detail & Related papers  (2023-11-19T19:53:49Z)
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
  We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other. We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
  arXiv  Detail & Related papers  (2023-10-26T17:59:46Z)
• Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks [55.431048995662714]
  We create a small model for a new task from the pruned models of similar tasks. We show that a few fine-tuning steps on this model suffice to produce a promising pruned-model for the new task. We develop a simple but effective ''Meta-Vote Pruning (MVP)'' method that significantly reduces the pruning iterations for a new task.
  arXiv  Detail & Related papers  (2023-01-27T06:49:47Z)
• Hardness of Samples Need to be Quantified for a Reliable Evaluation System: Exploring Potential Opportunities with a New Task [24.6240575061124]
  Evaluation of models on benchmarks is unreliable without knowing the degree of sample hardness. We propose a Data Scoring task that requires assignment of each unannotated sample in a benchmark a score between 0 to 1.
  arXiv  Detail & Related papers  (2022-10-14T08:26:32Z)
• Probing Representation Forgetting in Supervised and Unsupervised Continual Learning [14.462797749666992]
  Catastrophic forgetting is associated with an abrupt loss of knowledge previously learned by a model. We show that representation forgetting can lead to new insights on the effect of model capacity and loss function used in continual learning.
  arXiv  Detail & Related papers  (2022-03-24T23:06:08Z)
• Mixture of basis for interpretable continual learning with distribution shifts [1.6114012813668934]
  Continual learning in environments with shifting data distributions is a challenging problem with several real-world applications. We propose a novel approach called mixture of Basismodels (MoB) for addressing this problem setting.
  arXiv  Detail & Related papers  (2022-01-05T22:53:15Z)
• Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models [62.28551903638434]
  We measure the impact of three different adaptation methods on the generalization and accuracy of models. Experiments with two models show that fine-tuning performs best, by learning both the content and the structure of the task, but suffers from overfitting and limited generalization to novel answers. We observe that alternative adaptation methods like prefix-tuning have comparable accuracy, but generalize better to unseen answers and are more robust to adversarial splits.
  arXiv  Detail & Related papers  (2021-09-07T03:13:06Z)

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.