A new method, REC, compresses images by encoding their latent representations efficiently.
problem Efficiently compressing single images with latent representations.
method Relative Entropy Coding (REC) that directly encodes latent representations with codelength close to relative entropy.
result REC is more efficient for single image compression compared to previous methods and is competitive for lossy compression.
Autoencoders learn compressed representations via mutual information maximization.
problem Learning efficient compressed representations of high-dimensional data.
method Proposes Uncertainty Autoencoders that treat latent representations as noisy projections and optimize mutual information.
result 32% improvement in statistical compressed sensing of high-dimensional datasets.
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.
Compressed LLM embeddings improve noisy regression tasks without overfitting.
problem Noisy regression tasks with high signal-to-noise ratios.
method Comparison of embedding compression techniques using autoencoder hidden representations.
result Compression improves performance on noisy tasks like financial return prediction.
Surface parameterizations and registrations are important in computer graphics and imaging, where 1-1 correspondences between meshes are computed. In practice, surface maps are usually represented and stored as 3D coordinates each vertex is mapped to, which often requires lots of storage memory. This causes inconvenien…
Modality-agnostic compression improves across diverse data types.
problem Efficiently compressing data across multiple modalities.
method Functional view of data, Implicit Neural Representation (INR), modality-agnostic latent representations, variational compression.
result Improved performance compared to existing methods, especially for diverse modalities.
LIT compresses deep networks by training intermediate representations, outperforming traditional methods.
problem Reducing the computational overhead of deep network inference.
method LIT trains a student model with the same width but shallower depth, using the intermediate representations from the teacher model.
result LIT achieves substantial network depth reductions without accuracy loss, outperforming traditional methods.
HOPE uses Hilbert space to deconstruct deep network representations.
problem Deconstructing learned representations in deep networks is challenging.
method Introduces Hilbert Operator for Progressive Encoding (HOPE) to deconstruct network weights.
result HOPE provides an unbiased approach to network compression and fine-tuning.
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.
End-to-end deep generative model for video compression.
problem Efficiently compressing video data with deep learning.
method Variational autoencoder (VAE) for sequential data, combined with neural image compression techniques.
result Our model achieves competitive rate-distortion results on diverse video content.
This paper improves the scalability of sparse neural network compression.
problem Sparse neural network compression for diverse data modalities.
method State-of-the-art sparsification techniques and meta-learning.
result Meta-learning sparse compression networks achieve new state-of-the-art results.
This work clarifies the compression phenomenon in deep neural networks.
problem Understanding the compression aspect of information bottleneck theory in deep neural networks.
method Introduced an auxiliary noisy DNN framework to measure meaningful mutual information, developed an estimator for mutual information, and monitored clustering of hidden representations.
result Compression is driven by the progressive clustering of hidden representations of inputs from the same class.
Scattering representations simplify SBI for images without extra compression.
problem Efficiently performing simulation-based inference on images with limited data.
method Use scattering representations for compression and learning, combined with spatial averaging and expressive density estimators.
result Scattering representations provide more information than traditional methods, without requiring additional simulations.
A simple method compresses neural network weights using entropy penalties.
problem Neural network weight compression for scalability and accuracy.
method Reparameterization with learned entropy penalty for compression.
result Maximized classification accuracy and model compressibility.
This paper proposes a new weight representation scheme for efficient model compression and performance enhancement.
problem Challenges in achieving performance enhancement on devices due to irregular sparse matrix representations.
method Fine-grained and unstructured pruning method combined with structured weight encryption.
result Achieved high compression ratios and performance on various deep learning models.
CRCCA framework improves non-linear CCA with compressed representations.
problem Non-linear CCA for multi-view data with limited samples.
method Information-theoretic compressed representation framework (CRCCA) based on lattice quantization.
result The CRCCA framework provides theoretical bounds and optimality conditions, offering a flexible and computationally efficient solution.
Develops algorithms for efficient visual data compression and search.
problem High-dimensional, large-scale visual data representation.
method Discrete synthesis and analysis models, RRQ and ML-STC frameworks.
result Fast query times and shorter database storage for similarity search.
Let M be a hyperbolizable, nontrivial compression body without toroidal boundary components. In this paper, we characterize which discrete and faithful representations of the fundamental group of M into PSL(2,C) are separable-stable. The set of separable-stable representations forms a domain of discontinuity for the ac…
New method compresses facial videos using GANs and latent space optimization.
problem Efficiently compressing facial videos at low bit rates.
method Leverages StyleGAN for latent space representation and compression, learns optimal compression through entropy model and perceptual loss.
result Significantly reduces perceptual distortion at low bit rates compared to state-of-the-art codecs.
Introduces REVE, a regularization scheme that compresses class conditioned entropy.
problem Improving generalization performance of deep learning models.
method Identifies a variable responsible for final prediction, compresses class conditioned entropy, introduces a variational upper bound, and integrates a tractable loss into training.
result Demonstrates the efficiency of REVE on various neural networks and datasets.
Improved chemical predictions through compressed atomic species representations.
problem Intractable chemical space of molecules and materials.
method Introducing elemental modes for compressed representation of atomic species.
result Elemental modes enable improvements in machine learning tasks for chemical predictions.
Paper establishes generalization bounds for representation learning using Minimum Description Length.
problem Designing efficient statistical supervised learning algorithms that generalize well to unseen data.
method Developed a compressibility framework using Minimum Description Length (MDL) to derive upper bounds on generalization error.
result Established the first theoretical generalization bounds for Information Bottleneck type encoders and representation learning.
New approach for sharing deep learning costs between devices and cloud.
problem Prohibitive deep learning computational requirements for embedded devices.
method Study of representation compressibility in MobileNetV2 for balancing computation, bandwidth, and accuracy.
result An optimal splitting layer for network can be found with a simple PCA-based compression scheme.
This work analyzes how different forms of compressibility affect adversarial robustness in neural networks.
problem Understanding the interaction between compressibility and adversarial robustness in neural networks.
method Developed a principled framework to analyze the effects of neuron-level sparsity and spectral compressibility on adversarial robustness.
result Identified that different forms of compression can induce highly sensitive directions in the representation space that adversaries can exploit.
Proposes Decodable Information Bottleneck for optimal representation learning.
problem Finding optimal representations for supervised learning.
method Integrates information retention and compression with the desired predictive family.
result Optimal representations lead to better expected test performance and can be estimated with guarantees.
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.
HSRL learns network embeddings capturing both local and global topology.
problem Capturing both local and global topological information in network analysis.
method HSRL recursively compresses networks into smaller ones, then learns embeddings using existing methods.
result HSRL outperforms state-of-the-art methods in link prediction.
A new method learns graph compression from data.
problem Graphs lack ordering, making conventional compression algorithms ineffective.
method Partition and Code framework: decompose, learn, encode.
result PnC achieves compression gains that grow with graph size.
Paper presents J-RFDL for robust DL in compressed space, improving data representation robustness and accuracy.
problem Improving data representation robustness and accuracy in the presence of noise and outliers.
method Joint Robust Factorization and Projective Dictionary Learning (J-RFDL) in a factorized compressed space.
result Delivers superior performance in data representation and classification over state-of-the-art methods.
A new algorithm for compressing latent representations in deep models.
problem Compressing continuous latent representations in deep models.
method Separates model design and training from quantization; uses adaptive quantization based on posterior uncertainty.
result Image compression with the proposed algorithm outperforms JPEG over a wide range of bit rates.
RandNet learns from compressed image data, improving efficiency and accuracy.
problem Efficiency and accuracy in training neural networks with large datasets.
method RandNet uses compressed random measurements of images to train neural networks efficiently.
result RandNet achieves comparable accuracy to full data training with minimal loss.
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.
This work explores the non-convex optimization in compressive learning and the performance of heuristics.
problem The challenge of learning from compressed representations in compressive learning.
method Numerical simulations of the non-convex optimization landscape and heuristic performance.
result Properties of the non-convex optimization landscape and heuristic performance are explored.
Paper compresses RNNs using HT decomposition for better performance.
problem Large model sizes of RNNs in sequence analysis.
method Hierarchical Tucker (HT) tensor decomposition for model compression.
result HT-LSTM achieves better compression and accuracy than state-of-the-art methods.
β-VAEs retain label info even at high compression.
problem Retaining label information in compressed representations.
method Investigation of β-VAE architectures on Binary Static MNIST and Omniglot. result β-VAEs can retain label information even at high compression.
Goal: This paper deals with the problems that some EEG signals have no good sparse representation and single channel processing is not computationally efficient in compressed sensing of multi-channel EEG signals. Methods: An optimization model with L0 norm and Schatten-0 norm is proposed to enforce cosparsity and low r…
New findings show compressed representations are exponentially easier to learn.
problem Understanding the generalization power of neural networks.
method Studied the entropy of input variables as a simplicity assumption and proved a bound on sample complexity.
result Compressed representations are exponentially easier to learn, providing new insights into neural network generalization.
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.
SANs use sparse activation functions to compress data representations.
problem Learning meaningful features without considering compression.
method Introduce φ metric, define activation functions, and present SANs.
result SANs achieve small description length and interpretable kernels.
Efficiently compress SPNs using tensor networks.
problem Efficiently compressing Sum-Product Networks (SPNs).
method Mapping SPNs onto tensor networks and employing novel optimization techniques.
result Remarkable parameter compression with negligible loss in accuracy.
In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in achieving binarization simulation, variable bit rates with multiple networks, entropy-friendly representations, inference-stage code optimiz…
Softmax temperature influences model representation rank and performance.
problem Understanding and optimizing softmax function's impact on model representations.
method Investigated softmax function's role in deep neural networks, introduced rank deficit bias.
result Softmax temperature affects model representation rank and can improve performance.
Improved neural image compression with refined latent representations.
problem Sub-optimal results from variational autoencoders due to imperfect optimization and capacity limitations.
method Stochastic Gumbel Annealing (SGA) and its extensions (SGA+), including three different methods.
result Significant improvement in compression performance, especially on the R-D trade-off.
Proposes a method to determine the most compact representation in deep neural networks.
problem Finding the most compact representation in deep neural networks.
method Layer-wise pruning method considering layer importance and total target sparsity.
result Achieved up to 75% better top-5 accuracy with 75% compression than baseline.
Autoencoders compress and reconstruct data for various applications.
problem Efficiently compress and reconstruct data.
method Neural network architecture that encodes and decodes data.
result Autoencoders can be applied to various data types and applications.
New method improves image compression using bits-back coding.
problem Lossy image compression with deep latent variable models.
method Iterative inference, stochastic annealing, bits-back coding.
result New state-of-the-art performance on lossy image compression.
Study connects compressed signal to AWGN model for risk estimation.
problem Estimating high-dimensional signals under compression constraints.
method Utilizes Gaussian approximation and Wasserstein distance to relate compressed and noisy signals.
result Establishes a connection between estimator risks under different conditions.
Proposes a new method for clustering compressed data.
problem Limited communication bandwidth and low-power consumption.
method Joint Variational Autoencoders with Bernoulli mixture models (VAB).
result The model can perform clustering in the compressed data domain.