Related papers: Lottery Tickets on a Data Diet: Finding Initializa…
We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random data order and augmentation). We find that standard vision models become stable to SGD noise in this way…
The search for efficient, sparse deep neural network models is most prominently performed by pruning: training a dense, overparameterized network and removing parameters, usually via following a manually-crafted heuristic. Additionally, the…
Post-training dropout based approaches achieve high sparsity and are well established means of deciphering problems relating to computational cost and overfitting in Neural Network architectures. Contrastingly, pruning at initialization is…
With the rise in interest of sparse neural networks, we study how neural network pruning with synthetic data leads to sparse networks with unique training properties. We find that distilled data, a synthetic summarization of the real data,…
The recently proposed Lottery Ticket Hypothesis of Frankle and Carbin (2019) suggests that the performance of over-parameterized deep networks is due to the random initialization seeding the network with a small fraction of favorable…
Many Neural Network Pruning approaches consist of several iterative training and pruning steps, seemingly losing a significant amount of their performance after pruning and then recovering it in the subsequent retraining phase. Recent works…
Since its use in the Lottery Ticket Hypothesis, iterative magnitude pruning (IMP) has become a popular method for extracting sparse subnetworks that can be trained to high performance. Despite its success, the mechanism that drives the…
Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. (2020) empirically showed that only pruning the weights can achieve remarkable performance…
The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy. However, the initialization and…
Modern-day neural networks are famously large, yet also highly redundant and compressible; there exist numerous pruning strategies in the deep learning literature that yield over 90% sparser sub-networks of fully-trained, dense…
Is the lottery ticket phenomenon an idiosyncrasy of gradient-based training or does it generalize to evolutionary optimization? In this paper we establish the existence of highly sparse trainable initializations for evolution strategies…
Recently, Frankle & Carbin (2019) demonstrated that randomly-initialized dense networks contain subnetworks that once found can be trained to reach test accuracy comparable to the trained dense network. However, finding these high…
In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i.e., a properly pruned sub-network together with original weight initialization)…
Random masks define surprisingly effective sparse neural network models, as has been shown empirically. The resulting sparse networks can often compete with dense architectures and state-of-the-art lottery ticket pruning algorithms, even…
Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization). The…
Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks.…
Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training. We focus on this framework and propose a new pruning at initialization…
Neural network pruning is useful for discovering efficient, high-performing subnetworks within pre-trained, dense network architectures. More often than not, it involves a three-step process -- pre-training, pruning, and re-training -- that…
Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to…
This thesis delves into the intricate world of Deep Neural Networks (DNNs), focusing on the exciting concept of the Lottery Ticket Hypothesis (LTH). The LTH posits that within extensive DNNs, smaller, trainable subnetworks termed "winning…