Wavelets help compress neural networks efficiently.
problem Efficiently compressing linear layers in neural networks.
method Learnable wavelet transforms to compress RNNs.
result Wavelet compressed RNNs have fewer parameters and perform competitively.
Proposes a new linearity-based neural network compression method.
problem Reduction of neural network model size while maintaining accuracy.
method Integrates linearity-based intuition with ReLU activation functions to merge layers.
result Achieves up to 75% reduction in model size without loss of accuracy.
Study shows LLC correlates with neural network compressibility.
problem Evaluating limits of neural network compression.
method Extended minimum description length principle using singular learning theory.
result Complexity estimates based on LLC are linearly correlated with compressibility.
New method compresses neural networks up to 14x with minimal performance loss.
problem Compressing neural networks for real-time applications.
method Post-training rank-selection method called Rank-Tuning.
result High compression rates with minimal performance degradation.
The success of deep neural networks in many real-world applications is leading to new challenges in building more efficient architectures. One effective way of making networks more efficient is neural network compression. We provide an overview of existing neural network compression methods that can be used to make neu…
Galen algorithm compresses neural networks for specific hardware with reduced latency.
problem Finding optimal compression policies for neural networks on specific hardware.
method Reinforcement learning using pruning and quantization to optimize inference latency.
result Compressed ResNet18 for ARM processor reduced inference latency by 80%.
Proposes a method to train neural networks directly on compressed text data.
problem Training neural networks on compressed text data without decompression.
method Introduces composer modules to encode symbols from grammar compression rules into vector representations.
result Demonstrates that the proposed method can achieve both memory and computational efficiency while maintaining moderate performance.
DP-Net uses dynamic programming for efficient deep neural network compression.
problem Efficiently compressing deep neural networks while maintaining accuracy.
method Dynamic Programming for optimal weight quantization and clustering-friendly training.
result Achieves up to 77X compression ratio on Wide ResNet with minimal accuracy loss.
We compress large neural networks for quick adaptation to specific contexts.
problem How to quickly adapt a pretrained large neural network to specific contexts.
method Propose a Bayesian hypernetwork framework to compress the network and encourage sparsity.
result Generated compressed networks are significantly smaller than baseline methods.
Lossless compression of deep neural networks using NTK and RMT.
problem Compressing large-scale deep neural networks for low-power devices.
method High-dimensional neural tangent kernel approach.
result Asymptotic spectral equivalence between NTK matrices of wide DNNs enables lossless compression.
New study reveals how heavy-tailed SGD dynamics lead to compressible neural networks.
problem Understanding why large neural networks can be compressed effectively.
method Linking SGD dynamics to compressibility properties of neural networks.
result Large step-size/batch-size ratios and overparametrization lead to heavy-tailed SGD dynamics, making networks compressible.
To improve how neural networks function it is crucial to understand their learning process. The information bottleneck theory of deep learning proposes that neural networks achieve good generalization by compressing their representations to disregard information that is not relevant to the task. However, empirical evid…
Theoretical framework for neural network compression using sparsity norms.
problem Understanding and quantifying compressibility and accuracy trade-offs in neural networks.
method Using sparsity-sensitive ℓ_q-norm to characterize compressibility and developing adaptive pruning algorithms.
result Theoretical relationship between network sparsity and compressibility with controlled accuracy degradation.
Layer fusion reduces deep neural network layers with minimal loss in accuracy.
problem Model compression to reduce neural network size and computation.
method Fusion of similar layers to reduce model size with minimal performance loss.
result Deep networks can be compressed up to 3.33x with minimal accuracy loss.
A new framework compresses neural networks using sparse optimization.
problem Efficiently reducing the size of deep neural networks for practical deployment.
method Sparse optimization for model compression, tailored for stochastic learning.
result Up to 7.2 and 2.9 times FLOPs reduction with comparable accuracy.
In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible. At encoder side, we fine-tune a pre-trained artifact removal network on target data by using a compression objective applied on the weight-u…
We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an importance sampling scheme that judiciously defines a sampling distribution over…
Image compression using neural networks have reached or exceeded non-neural methods (such as JPEG, WebP, BPG). While these networks are state of the art in ratedistortion performance, computational feasibility of these models remains a challenge. We apply automatic network optimization techniques to reduce the computat…
We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones. The problem of parameter learning is challenging, as it corresponds to hierarchical nonlinear tensor decomposition. We propose to solve the learning…
This paper offers an overview of neural network compression techniques.
problem Overparameterized neural networks are large and resource-intensive.
method Pruning, quantization, tensor decomposition, knowledge distillation.
result A comprehensive review of compression techniques for deep neural networks.
HOTCAKE compresses CNNs by decomposing kernels into smaller parts.
problem Compressing deep CNNs without significant accuracy loss.
method Input channel decomposition, guided Tucker rank selection, higher order Tucker decomposition, fine-tuning.
result HOTCAKE produces highly compressed CNN models with good accuracy.
We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the entropy of a neural network, which measures its complexity explicitly in terms of its bit-size. Then, we formalize the problem of neural netwo…
New compression theory justifies model pruning for neural networks.
problem Improving neural network performance with reduced model size.
method Information-theoretic rate-distortion theory applied to NN compression.
result Pruning improves model performance on CIFAR-10 and ImageNet datasets.
This paper proposes a new method for efficient data compression using Bayesian neural networks.
problem Efficient compression of data represented as functions mapping coordinates to signal values.
method Overfitting variational Bayesian neural networks to the data and compressing an approximate posterior weight sample using relative entropy coding.
result Our method achieves strong performance on image and audio compression while retaining simplicity.
Deep neural networks generalize well on unseen data though the number of parameters often far exceeds the number of training examples. Recently proposed complexity measures have provided insights to understanding the generalizability in neural networks from perspectives of PAC-Bayes, robustness, overparametrization, co…
This paper investigates compression techniques for deep neural networks to reduce their size without sacrificing performance.
problem Compression of large deep neural networks for resource-limited platforms.
method Weight pruning, quantization, and lossless weight matrix representations based on source coding.
result Achieved up to 165 times compression rate while maintaining or improving model performance.
This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.
problem Inference delays and energy inefficiency in energy-harvesting devices.
method Developed a power trace-aware and exit-guided network compression algorithm for multi-exit neural networks.
result Superior accuracy and reduced latency compared to state-of-the-art techniques.
Bayesian neural networks are compressed using feature and weight pruning based on posterior inclusion probabilities.
problem Efficiently compressing Bayesian neural networks to reduce computation cost and improve generalizability.
method Bayesian model selection principles are applied to obtain posterior inclusion probabilities for pruning and feature selection.
result Pruned models show better generalizability on simulated and real-world data.
This paper studies how to compress neural networks while maintaining accuracy.
problem Compressing a two-layer neural network with fewer nodes without losing accuracy.
method Using tools from high-dimensional probability, the authors minimize the L_2 loss between the target and compressed networks.
result The error rate of the approximation is shown as a function of input dimension and network size in the mean-field limit.
New measure LMN explains neural network grokking.
problem Delayed generalization after memorization in neural networks.
method Defined LMN to measure network complexity, showing LMN correlates with test losses linearly.
result LMN reveals intriguing XOR network behavior and is a promising complexity measure.
Adjoined Networks trains both base and compressed networks together for efficient model compression.
problem Efficiently compressing deep neural networks while maintaining accuracy.
method Adjoined Networks (AN) trains both a base network and a smaller compressed network simultaneously, sharing parameters.
result AN achieves 71.8% top-1 accuracy with 1.8M parameters and 1.6 GFLOPs on ImageNet.
This paper compresses neural networks by permuting and quantizing weights.
problem Efficiently compressing large neural networks for resource-constrained platforms.
method Permuting and quantizing weights, connecting to rate-distortion theory, and using annealed quantization.
result Significant compression with minimal accuracy loss, e.g., 40-70% reduction in gap with uncompressed model.
New SGD variant makes neural networks compressible without assumptions.
problem Improving neural network compressibility without strong assumptions.
method Introducing heavy-tailed noise to SGD iterates.
result Compressible outputs with high probability for any compression rate.
In this paper we apply a compressibility loss that enables learning highly compressible neural network weights. The loss was previously proposed as a measure of negated sparsity of a signal, yet in this paper we show that minimizing this loss also enforces the non-zero parts of the signal to have very low entropy, thus…
Tensor decomposition is an effective approach to compress over-parameterized neural networks and to enable their deployment on resource-constrained hardware platforms. However, directly applying tensor compression in the training process is a challenging task due to the difficulty of choosing a proper tensor rank. In o…
Dirichlet pruning compresses neural networks by removing unimportant units.
problem Compressing large neural network models without sacrificing performance.
method Assigns Dirichlet distribution over network layers' units and uses variational inference to estimate parameters.
result Achieves state-of-the-art compression performance on larger architectures like VGG and ResNet.
New method compresses LSTM networks using MPS tensor trains.
problem Challenges in maintaining performance of compressed RNNs.
method Use of MPS tensor trains for LSTM network compression.
result MPS tensor trains outperform MPOs in storage and inference time.
COIN++ compresses multiple data types efficiently.
problem Handling diverse data modalities in neural compression.
method Implicit neural representations and modulations quantization.
result Significant compression gains with reduced encoding time.
As the industry deploys increasingly large and complex neural networks to mobile devices, more pressure is put on the memory and compute resources of those devices. Deep compression, or compression of deep neural network weight matrices, is a technique to stretch resources for such scenarios. Existing compression metho…
Paper proposes a compression principle for neural networks using Bayesian optimization.
problem Finding methods for making generalizable predictions in machine learning.
method Compression principle and Bayesian optimization approach.
result Optimal predictive models minimize total compressed message length of data and model definition.
Data-independent pruning method reduces neural network size with accuracy guarantees.
problem Limited computational and memory resources for neural networks.
method Structured pruning using coresets.
result First efficient algorithm with worst-case guarantees on compression and accuracy.
Paper compresses deep neural networks by eliminating redundant neurons.
problem Challenges in deploying deep learning models due to high parameter count.
method Exploits non-linear redundancy to compress neural networks without loss.
result Reduces network size by up to 99% with minimal performance loss.
NeuZip compresses neural network weights to save memory during training and inference.
problem Memory constraints in neural network training and inference.
method Entropy-based dynamic weight compression.
result Significant reduction in memory usage without performance loss.
Flexible framework compresses models using LC algorithm.
problem Efficiently compressing neural networks for resource constraints.
method Decouples learning and compression steps with alternating L and C phases.
result Compressed models maintain performance and accuracy.
Paper improves MIRACLE for faster, more robust neural network compression.
problem Efficiently compressing neural networks while maintaining performance.
method Introduces Mean-KL parameterization to constrain compression cost.
result Mean-KL parameterization leads to twice as fast convergence and more robust compression.
The low-rank tensor approximation is very promising for the compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with a smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our…
Paper proposes new Bayesian neural network models for efficient learning.
problem Efficient learning and model compression in deep neural networks.
method Proposes Spike-and-Slab Group Lasso (SS-GL) and Spike-and-Slab Group Horseshoe (SS-GHS) priors for structured sparsity in Bayesian neural networks.
result Establishes competitive performance in prediction accuracy, model compression, and inference latency compared to baseline models.
Study on reducing forgetting in neural networks using compression theory.
problem Catastrophic forgetting in neural networks.
method Defined forgetting as increased description lengths, compared variational posterior approaches to prequential coding methods.
result Proposed a new continual learning method combining ML plug-in and Bayesian mixture codes.