LLMs compress financial texts, but distort decision-making.
problem LLMs compress financial texts, altering decision-making.
method Analyzed two diagnostic patterns: decontextualization and model dependency. Proposed Agentic Context Compression.
result LLM-compressed financial texts alter decision-making.
This paper develops a method to estimate the rate-distortion function for general data sources.
problem Estimating the rate-distortion function for general data sources.
method Develops an algorithm for sandwiching the R-D function of a general (not necessarily discrete) source using i.i.d. data samples.
result Estimates R-D sandwich bounds for various data sources, including natural images, indicating potential for improving compression methods.
Distiller simplifies DNN compression research with a Python package.
problem Efficiently compressing deep neural networks.
method Open-source Python package with DNN compression algorithms.
result Facilitates new research and learning tasks in DNN compression.
New insights into image compression trade-offs with private randomness.
problem Trade-off between compression rate and perceptual quality in image compression.
method Characterization of rate-distortion trade-off with private randomness under different realism constraints.
result Encoder private randomness is not useful if compression rate is below source entropy, even with limited common and decoder private randomness.
New method quantifies redundant information using information bottleneck.
problem Quantifying redundant information among multiple sources.
method Formulated as an information bottleneck problem, termed redundancy bottleneck.
result Extracts information that best predicts the target without revealing source identity.
New method estimates rate-distortion function using optimal transport.
problem Estimating the fundamental performance limit of data compression.
method Wasserstein gradient descent to learn optimal reproduction distribution.
result Local convergence and sample complexity analysis of R-D estimator.
HiLLoC compresses large images losslessly using VAEs.
problem Lossless compression of large color photographs.
method Fully convolutional VAE models trained on ImageNet are applied to lossless compression.
result Achieves state-of-the-art compression for full-size ImageNet images.
We study a new class of codes for lossy compression with the squared-error distortion criterion, designed using the statistical framework of high-dimensional linear regression. Codewords are linear combinations of subsets of columns of a design matrix. Called a Sparse Superposition or Sparse Regression codebook, this s…
Paper proposes IABF to improve NECST robustness.
problem Limited robustness of NECST learned coding networks.
method Infomax Adversarial-Bit-Flip (IABF) to improve stability and robustness.
result IABF achieves state-of-the-art performances on compression and error correction benchmarks.
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.
FibQuant improves KV-cache compression for long-context inference.
problem Memory traffic bottleneck in long-context inference due to KV cache growth.
method Introduces FibQuant, a universal vector quantizer that combines Beta-quantile radii, Fibonacci/Roberts-Kronecker directions, and Lloyd-Max refinement.
result FibQuant achieves high compression rates with minimal loss in attention cosine similarity.
A new compressed sensing system speeds up PSTE detection.
problem Accurately detecting fast, small optical events (PSTEs) is challenging.
method Developed a novel compressed sensing algorithm for rolling shutter systems.
result Accurately recovered PSTEs with spatial undersampling, showing speed and quality advantages.
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.
Compressed sensing in MRI enables high subsampling factors while maintaining diagnostic image quality. This technique enables shortened scan durations and/or improved image resolution. Further, compressed sensing can increase the diagnostic information and value from each scan performed. Overall, compressed sensing has…
Deep latent variable models have seen recent success in many data domains. Lossless compression is an application of these models which, despite having the potential to be highly useful, has yet to be implemented in a practical manner. We present `Bits Back with ANS' (BB-ANS), a scheme to perform lossless compression w…
Source coding is the canonical problem of data compression in information theory. In a locally encodable source coding, each compressed bit depends on only few bits of the input. In this paper, we show that a recently popular model of semi-supervised clustering is equivalent to locally encodable source coding. In this …
Data compression is a popular technique for improving the efficiency of data processing workloads such as SQL queries and more recently, machine learning (ML) with classical batch gradient methods. But the efficacy of such ideas for mini-batch stochastic gradient descent (MGD), arguably the workhorse algorithm of moder…
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.
Plug-and-play L-GM-AMP improves CS recovery for any i.i.d. source prior.
problem Efficiently recovering signals from compressed measurements with unknown priors.
method Deep learning with Gaussian-mixture model to approximate source prior, combined with learned denoising.
result L-GM-AMP achieves state-of-the-art performance without prior knowledge of source distribution.
Unified strategy for efficient data compression and model estimation.
problem Limited interactive exploration and data interaction in linear model development and deployment.
method Conditionally sufficient statistics for optimal data compression and estimation of linear models.
result Linear models can be estimated from compressed data without loss of parameters or covariances.
We propose computationally efficient encoders and decoders for lossy compression using a Sparse Regression Code. The codebook is defined by a design matrix and codewords are structured linear combinations of columns of this matrix. The proposed encoding algorithm sequentially chooses columns of the design matrix to suc…
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.
Model compression improves dynamic forecasting ensembles while reducing computational costs.
problem High computational costs and lack of transparency in dynamic forecasting ensembles.
method Model compression applied to dynamic forecasting ensembles of various types of models.
result Compressed models achieve comparable predictive performance and significant computational savings.
Diffusion models improve image compression at low bit-rates.
problem Efficiently compressing images at very low bit-rates.
method Encoding into an embedding, using diffusion models to refine the embedding iteratively.
result Realistic reconstructions can be generated at extremely low bit-rates.
New method finds compact strong lottery tickets in partially frozen networks.
problem Finding compact strong lottery tickets in randomly pruned networks.
method Freezing a random subset of initial weights in a partially frozen network.
result Better accuracy and compression achieved with frozen networks.
This paper simplifies ANS for statisticians, making it easier to use.
problem Statisticians struggle to understand ANS and its versatility.
method Present ANS from a latent variable model perspective and guide step-by-step implementation.
result Made ANS more accessible for statisticians through a Python implementation and library.
CCVFM uses coreset to improve generative models by refining residual flows.
problem Generating multimodal distributions from scratch is challenging.
method Augments hierarchical rectified flow with a data-informed source distribution using a coreset.
result CCVFM achieves competitive few-step generation without a learned noise-to-data map.
Study neural communication systems with bandwidth-limited channels.
problem Reliable message transmission despite noisy channels.
method Jointly model compression and error correction with neural networks; introduce prior for missing information; use auxiliary latent variables.
result Joint neural communication systems outperform separate models under expected information loss.
Unified bounds linking compressibility, fractal dimensions, and mutual information.
problem Understanding generalization in stochastic learning algorithms.
method Rate-distortion theory applied to machine learning generalization.
result Unified bounds linking compressibility, fractal dimensions, and mutual information.
Differentiable model compression adds noise to parameters during training.
problem Model compression for efficient deployment.
method Adding pseudo quantization noise to model parameters during training.
result Compresses model by more than 8x on ImageNet with 0.3% accuracy loss.
In this paper, the `Approximate Message Passing' (AMP) algorithm, initially developed for compressed sensing of signals under i.i.d. Gaussian measurement matrices, has been extended to a multi-terminal setting (MAMP algorithm). It has been shown that similar to its single terminal counterpart, the behavior of MAMP algo…
In this work, we formulate the fixed-length distribution matching as a Bayesian inference problem. Our proposed solution is inspired from the compressed sensing paradigm and the sparse superposition (SS) codes. First, we introduce sparsity in the binary source via position modulation (PM). We then present a simple and …
In this paper, we consider the joint design of data compression and 802.15.4-based medium access control (MAC) protocol for smartgrids with renewable energy. We study the setting where a number of nodes, each of which comprises electricity load and/or renewable sources, report periodically their injected powers to a da…
Autoencoders fail to capture sparse structure in 1-bit data compression.
problem Proving the performance of shallow autoencoders on sparse data compression.
method Gradient descent analysis and approximate message passing.
result Gradient descent minimizer for sparse data is the identity (up to permutation) above critical sparsity.
BottleNet++ compresses deep learning features for efficient mobile inference.
problem Balancing computation and communication in mobile devices with deep learning models.
method End-to-end architecture with encoder, non-trainable channel layer, and decoder.
result Achieves high compression ratio and bandwidth reduction with minimal accuracy loss.
Paper models and compresses wideband CSI feedback in FDD MIMO systems.
problem Fundamental limits of channel state information (CSI) feedback in FDD massive MIMO systems.
method Modeling CSI as a Gaussian-mixture source with latent geometry states, proposing Gaussian-mixture transform coding (GMTC).
result Near-optimal CSI compression achieved through state-adaptive transform coding without large neural encoders.
This paper proposes a method to compress and adapt CNNs for real-world applications.
problem Differences in data distributions and high computational costs limit CNN adoption.
method Joint optimization of CNNs for unsupervised domain adaptation and knowledge distillation.
result The proposed method achieves the highest accuracy with comparable or lower time complexity.
The paper analyzes geometric densities and compression radii for knot types.
problem Optimizing geometric quantities associated with knot types.
method Develops a factorization framework for scale-covariant size functionals.
result Different minimizing sequences for density, compression, packing, and ropelength problems.
Hybrid model improves music source separation by 1.4 dB.
problem Improving music source separation accuracy.
method End-to-end hybrid spectrogram and waveform model, using model decision for domain choice.
result 1.4 dB improvement in Signal-to-Distortion (SDR) on MusDB HQ dataset.
Estimates rate-distortion function for large datasets using neural networks.
problem Designing lossy data compression schemes and comparing them with theoretical limits.
method Re-formulate rate-distortion objective and solve using neural networks.
result NERD accurately estimates the rate-distortion function for real-world datasets.
JPEG2000 (j2k) is a highly popular format for image and video compression.With the rapidly growing applications of cloud based image classification, most existing j2k-compatible schemes would stream compressed color images from the source before reconstruction at the processing center as inputs to deep CNNs. We propose…
PAQ8 is an open source lossless data compression algorithm that currently achieves the best compression rates on many benchmarks. This report presents a detailed description of PAQ8 from a statistical machine learning perspective. It shows that it is possible to understand some of the modules of PAQ8 and use this under…
Distilled teacher model transfers knowledge to student model on new datasets.
problem Improving model quality using unlabeled data.
method Knowledge distillation with an unlabeled teacher model.
result Teacher model knowledge transfers to student model on out-of-distribution datasets.
The muti-layer information bottleneck (IB) problem, where information is propagated (or successively refined) from layer to layer, is considered. Based on information forwarded by the preceding layer, each stage of the network is required to preserve a certain level of relevance with regards to a specific hidden variab…
We propose a joint source and channel coding (JSCC) technique for wireless image transmission that does not rely on explicit codes for either compression or error correction; instead, it directly maps the image pixel values to the complex-valued channel input symbols. We parameterize the encoder and decoder functions b…
We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands of experiments, we demonstrate that complex techniques (Molchanov et al., 2017;…
RFX accelerates and compresses Random Forests for large datasets.
problem Memory bottleneck in proximity matrices limits Random Forest analysis.
method QLORA compression, CPU TriBlock storage, GPU batch sizing, 3D MDS visualization.
result Proximity-based Random Forest analysis on larger datasets is feasible.
In compressed sensing, a small number of linear measurements can be used to reconstruct an unknown signal. Existing approaches leverage assumptions on the structure of these signals, such as sparsity or the availability of a generative model. A domain-specific generative model can provide a stronger prior and thus allo…