1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness

• URL: http://arxiv.org/abs/2311.16833v1
• Date: Tue, 28 Nov 2023 14:50:50 GMT
• Title: 1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness
• Authors: Bernd Prach, Fabio Brau, Giorgio Buttazzo, Christoph H. Lampert
• Abstract summary: robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems. Recently, the scientific community has focused on enhancing certifiable robustness guarantees by crafting 1-Lipschitz neural networks that leverage Lipschitz bounded dense and convolutional layers. This paper provides a theoretical and empirical comparison between methods by evaluating them in terms of memory usage, speed, and certifiable robust accuracy.
• Score: 22.09354138194545
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems. Recently, the scientific community has focused on enhancing certifiable robustness guarantees by crafting 1-Lipschitz neural networks that leverage Lipschitz bounded dense and convolutional layers. Although different methods have been proposed in the literature to achieve this goal, understanding the performance of such methods is not straightforward, since different metrics can be relevant (e.g., training time, memory usage, accuracy, certifiable robustness) for different applications. For this reason, this work provides a thorough theoretical and empirical comparison between methods by evaluating them in terms of memory usage, speed, and certifiable robust accuracy. The paper also provides some guidelines and recommendations to support the user in selecting the methods that work best depending on the available resources. We provide code at https://github.com/berndprach/1LipschitzLayersCompared.

Related papers

• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Smooth-Reduce: Leveraging Patches for Improved Certified Robustness [100.28947222215463]
  We propose a training-free, modified smoothing approach, Smooth-Reduce. Our algorithm classifies overlapping patches extracted from an input image, and aggregates the predicted logits to certify a larger radius around the input. We provide theoretical guarantees for such certificates, and empirically show significant improvements over other randomized smoothing methods.
  arXiv  Detail & Related papers  (2022-05-12T15:26:20Z)
• Compare learning: bi-attention network for few-shot learning [6.559037166322981]
  One of the Few-shot learning methods called metric learning addresses this challenge by first learning a deep distance metric to determine whether a pair of images belong to the same category. In this paper, we propose a novel approach named Bi-attention network to compare the instances, which can measure the similarity between embeddings of instances precisely, globally and efficiently.
  arXiv  Detail & Related papers  (2022-03-25T07:39:10Z)
• A Framework and Benchmark for Deep Batch Active Learning for Regression [2.093287944284448]
  We study active learning methods that adaptively select batches of unlabeled data for labeling. We present a framework for constructing such methods out of (network-dependent) base kernels, kernel transformations, and selection methods. Our proposed method outperforms the state-of-the-art on our benchmark, scales to large data sets, and works out-of-the-box without adjusting the network architecture or training code.
  arXiv  Detail & Related papers  (2022-03-17T16:11:36Z)
• Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds [99.23098204458336]
  Certified robustness is a desirable property for deep neural networks in safety-critical applications. We show that our method consistently outperforms state-of-the-art methods on MNIST and TinyNet datasets.
  arXiv  Detail & Related papers  (2021-11-02T06:44:10Z)
• Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms [1.2183405753834562]
  Backpropagation is the default algorithm for training deep neural networks due to its simplicity, efficiency and high convergence rate. In recent years, more biologically plausible learning methods have been proposed. BioTorch is a software framework to create, train, and benchmark biologically motivated neural networks.
  arXiv  Detail & Related papers  (2021-08-30T18:02:55Z)
• Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning [66.59455427102152]
  We introduce Uncertainty Baselines: high-quality implementations of standard and state-of-the-art deep learning methods on a variety of tasks. Each baseline is a self-contained experiment pipeline with easily reusable and extendable components. We provide model checkpoints, experiment outputs as Python notebooks, and leaderboards for comparing results.
  arXiv  Detail & Related papers  (2021-06-07T23:57:32Z)
• AdaS: Adaptive Scheduling of Stochastic Gradients [50.80697760166045]
  We introduce the notions of textit"knowledge gain" and textit"mapping condition" and propose a new algorithm called Adaptive Scheduling (AdaS) Experimentation reveals that, using the derived metrics, AdaS exhibits: (a) faster convergence and superior generalization over existing adaptive learning methods; and (b) lack of dependence on a validation set to determine when to stop training.
  arXiv  Detail & Related papers  (2020-06-11T16:36:31Z)
• A Closer Look at Accuracy vs. Robustness [94.2226357646813]
  Current methods for training robust networks lead to a drop in test accuracy. We show that real image datasets are actually separated. We conclude that achieving robustness and accuracy in practice may require using methods that impose local Lipschitzness.
  arXiv  Detail & Related papers  (2020-03-05T07:09:32Z)

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.