Adaptive Submodular Meta-Learning
- URL: http://arxiv.org/abs/2012.06070v2
- Date: Thu, 25 Mar 2021 14:31:48 GMT
- Title: Adaptive Submodular Meta-Learning
- Authors: Shaojie Tang, Jing Yuan
- Abstract summary: We introduce and study an adaptive submodular meta-learning problem.
The input of our problem is a set of items, where each item has a random state which is initially unknown.
Our objective is to adaptively select a group of items that achieve the best performance over a set of tasks.
- Score: 28.24164217929491
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Meta-Learning has gained increasing attention in the machine learning and
artificial intelligence communities. In this paper, we introduce and study an
adaptive submodular meta-learning problem. The input of our problem is a set of
items, where each item has a random state which is initially unknown. The only
way to observe an item's state is to select that item. Our objective is to
adaptively select a group of items that achieve the best performance over a set
of tasks, where each task is represented as an adaptive submodular function
that maps sets of items and their states to a real number. To reduce the
computational cost while maintaining a personalized solution for each future
task, we first select an initial solution set based on previously observed
tasks, then adaptively add the remaining items to the initial solution set when
a new task arrives. As compared to the solution where a brand new solution is
computed for each new task, our meta-learning based approach leads to lower
computational overhead at test time since the initial solution set is
pre-computed in the training stage. To solve this problem, we propose a
two-phase greedy policy and show that it achieves a $1/2$ approximation ratio
for the monotone case. For the non-monotone case, we develop a two-phase
randomized greedy policy that achieves a $1/32$ approximation ratio.
Related papers
- Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning [1.2952597101899859]
We study task selection to enhance sample efficiency in model-agnostic meta-reinforcement learning (MAML-RL)
We propose a coreset-based task selection approach that selects a weighted subset of tasks based on how diverse they are in gradient space.
We numerically validate this trend across multiple RL benchmark problems, illustrating the benefits of task selection beyond the LQR baseline.
arXiv Detail & Related papers (2025-02-04T14:09:00Z) - Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach [17.79010397902909]
We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks.
This problem has broad applications in NLP, such as targeted instruction tuning and data selection in chain-of-thought fine-tuning.
We introduce a new algorithm to estimate model fine-tuning performances without repeated training.
arXiv Detail & Related papers (2024-09-28T21:26:50Z) - Meta-learning with an Adaptive Task Scheduler [93.63502984214918]
Existing meta-learning algorithms randomly sample meta-training tasks with a uniform probability.
It is likely that tasks are detrimental with noise or imbalanced given a limited number of meta-training tasks.
We propose an adaptive task scheduler (ATS) for the meta-training process.
arXiv Detail & Related papers (2021-10-26T22:16:35Z) - Meta-Regularization by Enforcing Mutual-Exclusiveness [0.8057006406834467]
We propose a regularization technique for meta-learning models that gives the model designer more control over the information flow during meta-training.
Our proposed regularization function shows an accuracy boost of $sim$ $36%$ on the Omniglot dataset.
arXiv Detail & Related papers (2021-01-24T22:57:19Z) - Variable-Shot Adaptation for Online Meta-Learning [123.47725004094472]
We study the problem of learning new tasks from a small, fixed number of examples, by meta-learning across static data from a set of previous tasks.
We find that meta-learning solves the full task set with fewer overall labels and greater cumulative performance, compared to standard supervised methods.
These results suggest that meta-learning is an important ingredient for building learning systems that continuously learn and improve over a sequence of problems.
arXiv Detail & Related papers (2020-12-14T18:05:24Z) - Improving Generalization in Meta-learning via Task Augmentation [69.83677015207527]
We propose two task augmentation methods, including MetaMix and Channel Shuffle.
Both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets.
arXiv Detail & Related papers (2020-07-26T01:50:42Z) - Adaptive Task Sampling for Meta-Learning [79.61146834134459]
Key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time.
We propose an adaptive task sampling method to improve the generalization performance.
arXiv Detail & Related papers (2020-07-17T03:15:53Z) - Submodular Meta-Learning [43.15332631500541]
We introduce a discrete variant of the meta-learning framework to improve performance on future tasks.
Our approach aims at using prior data, i.e., previously visited tasks, to train a proper initial solution set.
We show that our framework leads to a significant reduction in computational complexity in solving the new tasks while incurring a small performance loss.
arXiv Detail & Related papers (2020-07-11T21:02:48Z) - Sequential Transfer in Reinforcement Learning with a Generative Model [48.40219742217783]
We show how to reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones.
We derive PAC bounds on its sample complexity which clearly demonstrate the benefits of using this kind of prior knowledge.
We empirically verify our theoretical findings in simple simulated domains.
arXiv Detail & Related papers (2020-07-01T19:53:35Z) - Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding
Meta-Amortization Error [50.83356836818667]
We develop a novel meta-regularization objective using it cyclical annealing schedule and it maximum mean discrepancy (MMD) criterion.
The experimental results show that our approach substantially outperforms standard meta-learning algorithms.
arXiv Detail & Related papers (2020-03-04T04:43:16Z)
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.