اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدJuvenile state hypothesis: What we can learn from lottery ticket hypothesis researches?
91
0
0.0
(
0
)
تأليف
Di Zhang
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The proposition of lottery ticket hypothesis revealed the relationship between network structure and initialization parameters and the learning potential of neural networks. The original lottery ticket hypothesis performs pruning and weight resetting after training convergence, exposing it to the problem of forgotten learning knowledge and potential high cost of training. Therefore, we propose a strategy that combines the idea of neural network structure search with a pruning algorithm to alleviate this problem. This algorithm searches and extends the network structure on existing winning ticket sub-network to producing new winning ticket recursively. This allows the training and pruning process to continue without compromising performance. A new winning ticket sub-network with deeper network structure, better generalization ability and better test performance can be obtained in this recursive manner. This method can solve: the difficulty of training or performance degradation of the sub-networks after pruning, the forgetting of the weights of the original lottery ticket hypothesis and the difficulty of generating winning ticket sub-network when the final network structure is not given. We validate this strategy on the MNIST and CIFAR-10 datasets. And after relating it to similar biological phenomena and relevant lottery ticket hypothesis studies in recent years, we will further propose a new hypothesis to discuss which factors that can keep a network juvenile, i.e., those possible factors that influence the learning potential or generalization performance of a neural network during training.
قيم البحث
اقرأ أيضاً
We introduce a generalization to the lottery ticket hypothesis in which the notion of sparsity is relaxed by choosing an arbitrary basis in the space of parameters. We present evidence that the original results reported for the canonical basis contin
ue to hold in this broader setting. We describe how structured pruning methods, including pruning units or factorizing fully-connected layers into products of low-rank matrices, can be cast as particular instances of this generalized lottery ticket hypothesis. The investigations reported here are preliminary and are provided to encourage further research along this direction.
Lottery Ticket Hypothesis (LTH) raises keen attention to identifying sparse trainable subnetworks, or winning tickets, of training, which can be trained in isolation to achieve similar or even better performance compared to the full models. Despite m
any efforts being made, the most effective method to identify such winning tickets is still Iterative Magnitude-based Pruning (IMP), which is computationally expensive and has to be run thoroughly for every different network. A natural question that comes in is: can we transform the winning ticket found in one network to another with a different architecture, yielding a winning ticket for the latter at the beginning, without re-doing the expensive IMP? Answering this question is not only practically relevant for efficient once-for-all winning ticket finding, but also theoretically appealing for uncovering inherently scalable sparse patterns in networks. We conduct extensive experiments on CIFAR-10 and ImageNet, and propose a variety of strategies to tweak the winning tickets found from different networks of the same model family (e.g., ResNets). Based on these results, we articulate the Elastic Lottery Ticket Hypothesis (E-LTH): by mindfully replicating (or dropping) and re-ordering layers for one network, its corresponding winning ticket could be stretched (or squeezed) into a subnetwork for another deeper (or shallower) network from the same family, whose performance is nearly the same competitive as the latters winning ticket directly found by IMP. We have also thoroughly compared E-LTH with pruning-at-initialization and dynamic sparse training methods, and discuss the generalizability of E-LTH to different model families, layer types, or across datasets. Code is available at https://github.com/VITA-Group/ElasticLTH.
Recent research has proposed the lottery ticket hypothesis, suggesting that for a deep neural network, there exist trainable sub-networks performing equally or better than the original model with commensurate training steps. While this discovery is i
nsightful, finding proper sub-networks requires iterative training and pruning. The high cost incurred limits the applications of the lottery ticket hypothesis. We show there exists a subset of the aforementioned sub-networks that converge significantly faster during the training process and thus can mitigate the cost issue. We conduct extensive experiments to show such sub-networks consistently exist across various model structures for a restrictive setting of hyperparameters ($e.g.$, carefully selected learning rate, pruning ratio, and model capacity). As a practical application of our findings, we demonstrate that such sub-networks can help in cutting down the total time of adversarial training, a standard approach to improve robustness, by up to 49% on CIFAR-10 to achieve the state-of-the-art robustness.
Recognition tasks, such as object recognition and keypoint estimation, have seen widespread adoption in recent years. Most state-of-the-art methods for these tasks use deep networks that are computationally expensive and have huge memory footprints.
This makes it exceedingly difficult to deploy these systems on low power embedded devices. Hence, the importance of decreasing the storage requirements and the amount of computation in such models is paramount. The recently proposed Lottery Ticket Hypothesis (LTH) states that deep neural networks trained on large datasets contain smaller subnetworks that achieve on par performance as the dense networks. In this work, we perform the first empirical study investigating LTH for model pruning in the context of object detection, instance segmentation, and keypoint estimation. Our studies reveal that lottery tickets obtained from ImageNet pretraining do not transfer well to the downstream tasks. We provide guidance on how to find lottery tickets with up to 80% overall sparsity on different sub-tasks without incurring any drop in the performance. Finally, we analyse the behavior of trained tickets with respect to various task attributes such as object size, frequency, and difficulty of detection.
The lottery ticket hypothesis (Frankle and Carbin, 2018), states that a randomly-initialized network contains a small subnetwork such that, when trained in isolation, can compete with the performance of the original network. We prove an even stronger
hypothesis (as was also conjectured in Ramanujan et al., 2019), showing that for every bounded distribution and every target network with bounded weights, a sufficiently over-parameterized neural network with random weights contains a subnetwork with roughly the same accuracy as the target network, without any further training.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
