On the Statistical Benefits of Curriculum Learning

• URL: http://arxiv.org/abs/2111.07126v1
• Date: Sat, 13 Nov 2021 14:51:07 GMT
• Title: On the Statistical Benefits of Curriculum Learning
• Authors: Ziping Xu and Ambuj Tewari
• Abstract summary: We study the benefits of Curriculum learning (CL) in the multitask linear regression problem under both structured and unstructured settings. Our results reveal that adaptive learning can be fundamentally harder than the oracle learning in the unstructured setting.
• Score: 33.94130046391917
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Curriculum learning (CL) is a commonly used machine learning training strategy. However, we still lack a clear theoretical understanding of CL's benefits. In this paper, we study the benefits of CL in the multitask linear regression problem under both structured and unstructured settings. For both settings, we derive the minimax rates for CL with the oracle that provides the optimal curriculum and without the oracle, where the agent has to adaptively learn a good curriculum. Our results reveal that adaptive learning can be fundamentally harder than the oracle learning in the unstructured setting, but it merely introduces a small extra term in the structured setting. To connect theory with practice, we provide justification for a popular empirical method that selects tasks with highest local prediction gain by comparing its guarantees with the minimax rates mentioned above.

Related papers

• Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods [69.36397993451742]
  This work introduces Context-aware Prompt Tuning (CPT), a method inspired by ICL, PT, and adversarial attacks. We modify specific context tokens, considering the unique structure of input and output formats. Inspired by adversarial attacks, we adjust the input based on the labels present in the context, focusing on minimizing, rather than maximizing, the loss.
  arXiv  Detail & Related papers  (2024-10-22T17:45:47Z)
• Is Efficient PAC Learning Possible with an Oracle That Responds 'Yes' or 'No'? [26.334900941196082]
  We investigate whether the ability to perform ERM, which computes a hypothesis minimizing empirical risk on a given dataset, is necessary for efficient learning. We show that in real setting of PAC for binary classification, a concept class can be learned using an oracle which only returns a single bit. Our results extend to the learning setting with a slight strengthening of the oracle, as well as to the partial concept, multiclass and real-valued learning settings.
  arXiv  Detail & Related papers  (2024-06-17T15:50:08Z)
• Is In-Context Learning Sufficient for Instruction Following in LLMs? [38.29072578390376]
  We show that, while effective, ICL alignment withAL still underperforms compared to instruction fine-tuning on the established benchmark MT-Bench. We provide the first, to our knowledge, systematic comparison of ICL and instruction fine-tuning (IFT) for instruction following in the low data regime.
  arXiv  Detail & Related papers  (2024-05-30T09:28:56Z)
• AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning [50.78033979438031]
  We first introduce a unified formulation to analyze CLIP-based few-shot learning methods from a perspective of logit bias. Based on analysis of key components, this paper proposes a novel AMU-Tuning method to learn effective logit bias for CLIP-based few-shot classification.
  arXiv  Detail & Related papers  (2024-04-13T10:46:11Z)
• A Unified and General Framework for Continual Learning [58.72671755989431]
  Continual Learning (CL) focuses on learning from dynamic and changing data distributions while retaining previously acquired knowledge. Various methods have been developed to address the challenge of catastrophic forgetting, including regularization-based, Bayesian-based, and memory-replay-based techniques. This research aims to bridge this gap by introducing a comprehensive and overarching framework that encompasses and reconciles these existing methodologies.
  arXiv  Detail & Related papers  (2024-03-20T02:21:44Z)
• Online Iterative Reinforcement Learning from Human Feedback with General Preference Model [17.900999251247256]
  We study Reinforcement Learning from Human Feedback (RLHF) under a general preference oracle. We consider a standard mathematical formulation, the reverse-KL regularized minimax game between two LLMs for RLHF under general preference oracle. We show that this framework is strictly more general than the reward-based one, and propose sample-efficient algorithms for both the offline learning from a pre-collected preference dataset and online learning.
  arXiv  Detail & Related papers  (2024-02-11T21:44:21Z)
• Density Distribution-based Learning Framework for Addressing Online Continual Learning Challenges [4.715630709185073]
  We introduce a density distribution-based learning framework for online Continual Learning. Our framework achieves superior average accuracy and time-space efficiency. Our method outperforms popular CL approaches by a significant margin.
  arXiv  Detail & Related papers  (2023-11-22T09:21:28Z)
• Multiclass Boosting: Simple and Intuitive Weak Learning Criteria [72.71096438538254]
  We give a simple and efficient boosting algorithm, that does not require realizability assumptions. We present a new result on boosting for list learners, as well as provide a novel proof for the characterization of multiclass PAC learning.
  arXiv  Detail & Related papers  (2023-07-02T19:26:58Z)
• Can Continual Learning Improve Long-Tailed Recognition? Toward a Unified Framework [16.457778420360537]
  Long-Tailed Recognition methods aim to accurately learn a dataset comprising both a larger Head set and a smaller Tail set. We show that Continual Learning (CL) methods can effectively update the weights of the learner to learn the Tail without forgetting the Head. We also assess the applicability of CL techniques on real-world data by exploring CL on the naturally imbalanced256 dataset.
  arXiv  Detail & Related papers  (2023-06-23T03:05:33Z)
• A Study of Continual Learning Methods for Q-Learning [78.6363825307044]
  We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario. Our results show that dedicated CL methods can significantly improve learning when compared to the baseline technique of "experience replay"
  arXiv  Detail & Related papers  (2022-06-08T14:51:52Z)

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.