Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization

• URL: http://arxiv.org/abs/2410.06567v1
• Date: Wed, 9 Oct 2024 06:04:52 GMT
• Title: Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization
• Authors: Prateek Varshney, Mert Pilanci,
• Abstract summary: Deployment of large and complex convex networks on resource-constrained devices significant challenges due to their demands. We introduce novel distillation technique that efficiently compresses model via this model via this paper. Our approach enables performance comparable to original model without requiring any post-processing.
• Score: 46.18363767705346
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deploying large and complex deep neural networks on resource-constrained edge devices poses significant challenges due to their computational demands and the complexities of non-convex optimization. Traditional compression methods such as distillation and pruning often retain non-convexity that complicates fine-tuning in real-time on such devices. Moreover, these methods often necessitate extensive end-to-end network fine-tuning after compression to preserve model performance, which is not only time-consuming but also requires fully annotated datasets, thus potentially negating the benefits of efficient network compression. In this paper, we introduce a novel distillation technique that efficiently compresses the model via convex optimization -- eliminating intermediate non-convex activation functions and using only intermediate activations from the original model. Our approach enables distillation in a label-free data setting and achieves performance comparable to the original model without requiring any post-compression fine-tuning. We demonstrate the effectiveness of our method for image classification models on multiple standard datasets, and further show that in the data limited regime, our method can outperform standard non-convex distillation approaches. Our method promises significant advantages for deploying high-efficiency, low-footprint models on edge devices, making it a practical choice for real-world applications. We show that convex neural networks, when provided with rich feature representations from a large pre-trained non-convex model, can achieve performance comparable to their non-convex counterparts, opening up avenues for future research at the intersection of convex optimization and deep learning.

Related papers

• Ultra-Resolution Adaptation with Ease [62.56434979517156]
  We propose a set of key guidelines for ultra-resolution adaptation termed emphURAE. We show that tuning minor components of the weight matrices outperforms widely-used low-rank adapters when synthetic data are unavailable. Experiments validate that URAE achieves comparable 2K-generation performance to state-of-the-art closed-source models like FLUX1.1 [Pro] Ultra with only 3K samples and 2K iterations.
  arXiv  Detail & Related papers  (2025-03-20T16:44:43Z)
• Forget the Data and Fine-Tuning! Just Fold the Network to Compress [13.611551223875194]
  We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers. We show that model folding achieves comparable performance to data-driven compression techniques and outperforms recently proposed data-free methods. This approach is particularly effective for compressing large-scale models, making it suitable for deployment in resource-constrained environments.
  arXiv  Detail & Related papers  (2025-02-14T15:10:43Z)
• Choose Your Model Size: Any Compression by a Single Gradient Descent [9.074689052563878]
  We present Any Compression via Iterative Pruning (ACIP) ACIP is an algorithmic approach to determine a compression-performance trade-off from a single gradient descent run. We show that ACIP seamlessly complements common quantization-based compression techniques.
  arXiv  Detail & Related papers  (2025-02-03T18:40:58Z)
• Dataset Distillation as Pushforward Optimal Quantization [1.039189397779466]
  We propose a simple extension of the state-of-the-art data distillation method D4M, achieving better performance on the ImageNet-1K dataset with trivial additional computation. We demonstrate that when equipped with an encoder-decoder structure, the empirically successful disentangled methods can be reformulated as an optimal quantization problem. In particular, we link existing disentangled dataset distillation methods to the classical optimal quantization and Wasserstein barycenter problems, demonstrating consistency of distilled datasets for diffusion-based generative priors.
  arXiv  Detail & Related papers  (2025-01-13T20:41:52Z)
• Efficient Dataset Distillation via Diffusion-Driven Patch Selection for Improved Generalization [34.53986517177061]
  We propose a novel framework to existing diffusion-based distillation methods, leveraging diffusion models for selection rather than generation. Our method starts by predicting noise generated by the diffusion model based on input images and text prompts, then calculates the corresponding loss for each pair. This streamlined framework enables a single-step distillation process, and extensive experiments demonstrate that our approach outperforms state-of-the-art methods across various metrics.
  arXiv  Detail & Related papers  (2024-12-13T08:34:46Z)
• The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models [75.33431791218302]
  Deep Neural Network Network (DNN) models are used for programming purposes. In this paper we examine the use of convex neural recovery models. We show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program. We also show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program.
  arXiv  Detail & Related papers  (2023-12-19T23:04:56Z)
• Self-Supervised Dataset Distillation for Transfer Learning [77.4714995131992]
  We propose a novel problem of distilling an unlabeled dataset into a set of small synthetic samples for efficient self-supervised learning (SSL) We first prove that a gradient of synthetic samples with respect to a SSL objective in naive bilevel optimization is textitbiased due to randomness originating from data augmentations or masking. We empirically validate the effectiveness of our method on various applications involving transfer learning.
  arXiv  Detail & Related papers  (2023-10-10T10:48:52Z)
• Improved Distribution Matching for Dataset Condensation [91.55972945798531]
  We propose a novel dataset condensation method based on distribution matching. Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources.
  arXiv  Detail & Related papers  (2023-07-19T04:07:33Z)
• Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation [2.741266294612776]
  Low-rank model compression is a widely used technique for reducing the computational load when training machine learning models. Existing compression techniques are not directly applicable to efficient over-the-air (OTA) aggregation in federated learning systems. We propose a novel manifold optimization formulation for low-rank model compression in FL that does not relax the low-rank constraint.
  arXiv  Detail & Related papers  (2023-06-04T18:32:50Z)
• Learning Accurate Performance Predictors for Ultrafast Automated Model Compression [86.22294249097203]
  We propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Our method achieves competitive accuracy-complexity trade-offs with significant reduction of the search cost.
  arXiv  Detail & Related papers  (2023-04-13T10:52:49Z)
• Reducing The Amortization Gap of Entropy Bottleneck In End-to-End Image Compression [2.1485350418225244]
  End-to-end deep trainable models are about to exceed the performance of the traditional handcrafted compression techniques on videos and images. We propose a simple yet efficient instance-based parameterization method to reduce this amortization gap at a minor cost.
  arXiv  Detail & Related papers  (2022-09-02T11:43:45Z)
• Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models [7.6356407698088]
  Pruning unnecessary parameters has emerged as a simple and effective method for compressing large models. We show that optimizing for flat minima consistently leads to greater compressibility of parameters compared to standard Adam optimization.
  arXiv  Detail & Related papers  (2022-05-25T11:54:37Z)
• Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization [1.8579693774597708]
  We propose a model reduction method to compress the pre-trained networks using low-rank tensor decomposition. A new regularization method, called funnel function, is proposed to suppress the unimportant factors during the compression. For ResNet18 with ImageNet2012, our reduced model can reach more than twi times speed up in terms of GMAC with merely 0.7% Top-1 accuracy drop.
  arXiv  Detail & Related papers  (2021-12-07T13:41:51Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)

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.