Deep Active Learning by Leveraging Training Dynamics
- URL: http://arxiv.org/abs/2110.08611v1
- Date: Sat, 16 Oct 2021 16:51:05 GMT
- Title: Deep Active Learning by Leveraging Training Dynamics
- Authors: Haonan Wang, Wei Huang, Andrew Margenot, Hanghang Tong, Jingrui He
- Abstract summary: We propose a theory-driven deep active learning method (dynamicAL) which selects samples to maximize training dynamics.
We show that dynamicAL not only outperforms other baselines consistently but also scales well on large deep learning models.
- Score: 57.95155565319465
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Active learning theories and methods have been extensively studied in
classical statistical learning settings. However, deep active learning, i.e.,
active learning with deep learning models, is usually based on empirical
criteria without solid theoretical justification, thus suffering from heavy
doubts when some of those fail to provide benefits in applications. In this
paper, by exploring the connection between the generalization performance and
the training dynamics, we propose a theory-driven deep active learning method
(dynamicAL) which selects samples to maximize training dynamics. In particular,
we prove that convergence speed of training and the generalization performance
is positively correlated under the ultra-wide condition and show that
maximizing the training dynamics leads to a better generalization performance.
Further on, to scale up to large deep neural networks and data sets, we
introduce two relaxations for the subset selection problem and reduce the time
complexity from polynomial to constant. Empirical results show that dynamicAL
not only outperforms the other baselines consistently but also scales well on
large deep learning models. We hope our work inspires more attempts in bridging
the theoretical findings of deep networks and practical impacts in deep active
learning applications.
Related papers
- Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network.
Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
arXiv Detail & Related papers (2024-10-31T22:54:34Z) - Advancing Deep Active Learning & Data Subset Selection: Unifying
Principles with Information-Theory Intuitions [3.0539022029583953]
This thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models.
We investigate data subset selection techniques, specifically active learning and active sampling, grounded in information-theoretic principles.
arXiv Detail & Related papers (2024-01-09T01:41:36Z) - An Expert's Guide to Training Physics-informed Neural Networks [5.198985210238479]
Physics-informed neural networks (PINNs) have been popularized as a deep learning framework.
PINNs can seamlessly synthesize observational data and partial differential equation (PDE) constraints.
We present a series of best practices that can significantly improve the training efficiency and overall accuracy of PINNs.
arXiv Detail & Related papers (2023-08-16T16:19:25Z) - Loss Dynamics of Temporal Difference Reinforcement Learning [36.772501199987076]
We study the case learning curves for temporal difference learning of a value function with linear function approximators.
We study how learning dynamics and plateaus depend on feature structure, learning rate, discount factor, and reward function.
arXiv Detail & Related papers (2023-07-10T18:17:50Z) - Exploring Adversarial Examples for Efficient Active Learning in Machine
Learning Classifiers [17.90617023533039]
We first add particular perturbation to original training examples using adversarial attack methods.
We then investigate the connections between active learning and these particular training examples.
Results show that the established theoretical foundation will guide better active learning strategies based on adversarial examples.
arXiv Detail & Related papers (2021-09-22T14:51:26Z) - Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
There is an increasing need for active learning algorithms that are compatible with deep neural networks.
This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
arXiv Detail & Related papers (2021-06-17T17:26:31Z) - What can linearized neural networks actually say about generalization? [67.83999394554621]
In certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization.
We show that the linear approximations can indeed rank the learning complexity of certain tasks for neural networks.
Our work provides concrete examples of novel deep learning phenomena which can inspire future theoretical research.
arXiv Detail & Related papers (2021-06-12T13:05:11Z) - Trajectory-wise Multiple Choice Learning for Dynamics Generalization in
Reinforcement Learning [137.39196753245105]
We present a new model-based reinforcement learning algorithm that learns a multi-headed dynamics model for dynamics generalization.
We incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector.
Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods.
arXiv Detail & Related papers (2020-10-26T03:20:42Z) - The large learning rate phase of deep learning: the catapult mechanism [50.23041928811575]
We present a class of neural networks with solvable training dynamics.
We find good agreement between our model's predictions and training dynamics in realistic deep learning settings.
We believe our results shed light on characteristics of models trained at different learning rates.
arXiv Detail & Related papers (2020-03-04T17:52:48Z)
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.