Proposes new terms for neural image compression to improve quality and efficiency.
problem Improving the quality and efficiency of neural image compression.
method Introduces a compression objective and a cycle loss term, applied to autoencoder encoder outputs, combined with reconstruction losses.
result Different autoencoders trained with varying losses produce images with distinct perceptual qualities and image-domain distortions.
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…
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…
Paper introduces adversarial lossy compression for video artifacts reduction.
problem Unpleasant reconstruction artifacts in standard video coding schemes at low bit-rates.
method Adversarial lossy video compression model minimizing an adversarial distortion objective.
result Reduction of perceptual artifacts and detail reconstruction under extreme compression.
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…
Object detection in still images has drawn a lot of attention over past few years, and with the advent of Deep Learning impressive performances have been achieved with numerous industrial applications. Most of these deep learning models rely on RGB images to localize and identify objects in the image. However in some a…
A new method for optimizing hierarchical multi-objective problems.
problem Symmetry and neglect of objective hierarchy in existing multi-objective methods.
method Priority-Constrained Descent (PCD) framework exploiting hierarchical objective structures.
result Pareto dominance and better per-objective performance with secondary progress guarantees.
Paper designs a lossy compression method for lossless prediction.
problem Ensuring high performance on predictive tasks with minimal data.
method Characterizes bit-rate requirements for invariant transformations, designs unsupervised objectives for neural compressors.
result Achieves substantial rate savings on ImageNet compared to JPEG without compromising classification performance.
Multiple gossip steps improve decentralized optimization convergence.
problem Efficiently optimizing large-scale machine learning models with limited communication.
method Integrates multiple gossip steps between gradient descent iterations in compressed decentralized optimization.
result Convergence to within ε of the optimal value for smooth non-convex objectives.
Compressive Transformer learns long-range sequences by compressing past memories.
problem Learning long-range sequences in language and speech models.
method Compressive Transformer compresses past memories for efficient long-range sequence learning.
result State-of-the-art performance on language and speech benchmarks.
Condensa programmatically optimizes neural network compression.
problem Finding optimal compression strategies for neural networks.
method Bayesian optimization-based algorithm for automatic sparsity inference.
result Significant memory and runtime improvements for real-world DNNs.
This work proves that large models can be compressed significantly without losing performance.
problem Achieving comparable performance with smaller models and less data.
method Developed a universal compression theory for neural networks and datasets.
result Proved that a generic permutation-invariant function can be compressed into a function of polylogarithmic size with vanishing error.
Video analytics requires operating with large amounts of data. Compressive sensing allows to reduce the number of measurements required to represent the video using the prior knowledge of sparsity of the original signal, but it imposes certain conditions on the design matrix. The Bayesian compressive sensing approach r…
If M is a manifold with compressible boundary, we analyze essential disks in M, as well as incompressible, but not necessarily boundary incompressible, surfaces in M. We are most interested in the case where M is a handlebody or compression body. The analysis depends on a new normal surface theory. We hope the normal s…
Adaptive step-size method improves compressed SGD performance in machine learning.
problem Communication bottleneck in distributed and decentralized optimization.
method Developed an adaptive step-size method for compressed SGD.
result Order-optimal convergence rates for various objective functions.
Compressing neural nets is an active research problem, given the large size of state-of-the-art nets for tasks such as object recognition, and the computational limits imposed by mobile devices. We give a general formulation of model compression as constrained optimization. This includes many types of compression: quan…
Paper tackles optimal network compression for financial systems.
problem Optimal network compression for financial systems under shocks.
method Formulated as an NP-hard problem, studied systemic risk measures, and analyzed specific networks.
result Systemic fragility results no longer hold generally under shocks and heterogeneous networks.
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.
Paper presents a new video compression method using autoencoders.
problem Efficient video compression with reduced quality loss.
method 3D autoencoder with discrete latent space and autoregressive prior trained jointly.
result Method outperforms state-of-the-art learned video compression networks.
Paper proposes a framework and algorithm for model compression in neural networks.
problem Training neural networks with model compression techniques suffers from accuracy loss and convergence issues.
method Holistic framework based on nonconvex optimization, using NN-BCD algorithm with closed-form iteration scheme.
result The proposed algorithm globally converges to a critical point at a rate of O(1/k).
Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised representation learning inspired by compressed sensing. We treat the low-dimensional …
We consider decentralized stochastic optimization with the objective function (e.g. data samples for machine learning task) being distributed over n machines that can only communicate to their neighbors on a fixed communication graph. To reduce the communication bottleneck, the nodes compress (e.g. quantize or sparsi…
The enormous size of modern deep neural networks makes it challenging to deploy those models in memory and communication limited scenarios. Thus, compressing a trained model without a significant loss in performance has become an increasingly important task. Tremendous advances has been made recently, where the main te…
Unified framework compresses GANs up to 47x with minimal quality loss.
problem High parameter complexity of GANs for resource-constrained devices.
method Unified optimization framework combining model distillation, channel pruning, and quantization.
result 47x compression of CartoonGAN with minimal quality degradation.
Improves compression of neural networks for embedded systems.
problem High computational cost and data labeling issues in DNNs.
method Domain Adaptation Regularization for Spectral Pruning.
result Our method outperforms existing methods by a large margin for high compression rates.
New hierarchical VQ-VAE scheme improves image compression quality and features at low bitrates.
problem Low bitrate image compression maintaining quality and features.
method Hierarchical VQ-VAE with stochastic quantization and Markovian latent variables.
result High perceptual quality and semantic features at low bitrates.
Deep neural networks have become commonplace in the domain of reinforcement learning, but are often expensive in terms of the number of parameters needed. While compressing deep neural networks has of late assumed great importance to overcome this drawback, little work has been done to address this problem in the conte…
New method improves generalization of VAEs by reducing overfitting.
problem Generalization issues in VAEs overfitting to training data.
method Proposed a new training objective to improve amortized inference.
result Improved performance in image modeling and lossless compression.
New method estimates robust mean in high dimensions with minimized outliers.
problem Estimating the mean in high dimensions when a fraction of data is corrupted.
method Formulating the problem as ℓ0-norm minimization under second moment constraints, and using ℓ1 and ℓp minimization techniques. result The proposed method achieves order optimal robust mean estimation and significantly outperforms existing methods.
We consider the problem of robust compressed sensing whose objective is to recover a high-dimensional sparse signal from compressed measurements corrupted by outliers. A new sparse Bayesian learning method is developed for robust compressed sensing. The basic idea of the proposed method is to identify and remove the ou…
C2G-Net improves image classification of similar objects like cells.
problem Classifying images with many similar objects efficiently and interpretably.
method Combines image compression and a CNN with reduced parameters.
result C2G-Net achieves similar accuracy to conventional CNNs but with reduced training time and improved interpretability.
The paper proposes a bio-inspired framework for better compression and adversarial robustness in machine learning models.
problem Machine learning models are vulnerable to adversarial examples.
method The paper introduces a bio-inspired classification framework that conditions model inference on label hypothesis and uses an information bottleneck regularizer.
result The framework enables better compression and adversarial robustness without loss of natural accuracy.
Unified SVD compression fails in practical tasks, highlighting the importance of per layer activation reconstruction.
problem The failure of a unified SVD compression method in practical tasks like perplexity and accuracy.
method Unified optimization problem for SVD based compression methods, focusing on cross-layer coupling.
result Downstream metrics like perplexity and accuracy degrade severely compared to standard per layer SVD LLM.
We present a filter correlation based model compression approach for deep convolutional neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise correlations and drops one of the filters from each such pair. However, instead of discarding one of the filters from each such pair naï…
Decentralized deep learning improves efficiency with arbitrary compression.
problem Limited network bandwidth hinders decentralized deep learning.
method Proposed Choco-SGD with arbitrary compression for non-convex functions.
result Choco-SGD achieves linear speedup and higher compression than previous methods.
Recent breakthrough results in compressed sensing (CS) have established that many high dimensional objects can be accurately recovered from a relatively small number of non- adaptive linear projection observations, provided that the objects possess a sparse representation in some basis. Subsequent efforts have shown th…
New compression technique reduces RNN size by 2-4x without sacrificing accuracy.
problem Large and compute-intensive RNNs on edge devices with run-time constraints.
method Hybrid Matrix Decomposition (HMD) splits weight matrix into unconstrained and rank-1 blocks.
result HMD achieves 2-4x compression with faster run-time and similar accuracy.
A new deep learning framework for efficient IoT data compression and inference.
problem Limited bandwidth and power resources in IoT sensors.
method Co-designed deep learning framework that maximizes sensing goal accuracy.
result Superior performance compared to benchmark models.
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.
Flexible framework improves communication efficiency across various systems.
problem Reducing communication between nodes in machine learning tasks.
method Adapts compression level to true gradient at each iteration, optimizing per-bit improvement.
result Automatic tuning strategies significantly increase communication efficiency.
Unified analysis of federated learning with compression for various data distributions.
problem Communication overhead in federated learning with unreliable or limited communication.
method Periodic compressed communication and local gradient tracking schemes.
result Sharp convergence rates for various objective functions and data distributions.
Draft proposes adapting neural networks to match naive Bayes classifiers.
problem Bridge between neural networks and naive Bayes classifiers.
method Class-conditional compression and disentanglement using variational bounds.
result Latent representations enable naive Bayes classifier performance.
New method preserves privacy while improving machine learning accuracy.
problem Privacy-preserving machine learning for daily data.
method Compressive Privacy and multi-kernel method.
result Improved utility classification accuracy with privacy preservation.
New method compares community detection algorithms without ground truth.
problem Comparing community detection algorithms without ground truth.
method Integrates any objective with its implicit generative model.
result More expressive methods consistently outperform others.
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.
ARDMs are a new model class for autoregressive diffusion that generalize existing models and can compress data efficiently.
problem Efficient data compression and generation.
method Autoregressive Diffusion Models (ARDMs) that generalize existing autoregressive models and discrete diffusion models.
result ARDMs require significantly fewer steps for compression compared to discrete diffusion models.
Real-world data typically contain repeated and periodic patterns. This suggests that they can be effectively represented and compressed using only a few coefficients of an appropriate basis (e.g., Fourier, Wavelets, etc.). However, distance estimation when the data are represented using different sets of coefficients i…
Paper tackles noisy labels by compressing feature representations.
problem Learning with noisy labels leads to overfitting and poor generalization.
method Introduces compression inductive bias using Dropout and Nested Dropout.
result Compression helps in combating label noise and improving performance.