Data pruning algorithms struggle in high compression regimes, as shown by theoretical and empirical studies.
problem Limitations of score-based data pruning algorithms in high compression regimes.
method Theoretical and empirical analysis of score-based data pruning algorithms.
result Score-based data pruning algorithms fail in high compression regimes due to 'No Free Lunch' theorems.
Paper proposes a 1-bit quantization scheme for high-dimensional statistical estimation.
problem High-dimensional statistical estimation with limited data.
method Uniformly dithered 1-bit quantization for sparse covariance matrix estimation, sparse linear regression, and matrix completion.
result Near minimax rates in sub-Gaussian regime and improved rates in heavy-tailed regime.
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.
Proposes GPLFR for predicting high-dimensional outputs with few data.
problem Predicting high-dimensional outputs from limited data.
method GPLFR combines Gaussian process and linear-Gaussian decoding for high-dimensional prediction.
result GPLFR outperforms existing methods in predicting high-dimensional outputs.
Clapping reduces memory usage in distributed optimization by reusing data samples.
problem Significant communication overhead and impractical memory overhead in pipeline-parallel distributed optimization.
method Lazy sampling strategy to reuse data samples across steps, supporting convergence without unbiased gradient assumptions.
result Clapping achieves convergence in few-epoch or online training regimes without sample-size memory overhead.
New uncertainty principle limits compression in distributed learning, suggesting optimal methods.
problem Minimizing communication cost while maintaining message quality in distributed learning.
method Formalized uncertainty principle for compression operators, introduced Kashin compression.
result Explicit formula for Kashin compression's variance bound, dimension independent.
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 compresses non-Gaussian distributions exponentially.
problem Efficiently representing and computing non-Gaussian probability distributions.
method Tensor-Network Fourier Methods using QTT representation.
result Exponential compression of non-Gaussian distributions.
GOTabPFN improves tabular model performance with compact tokenization for HDLSS data.
problem Making tabular models effective for high-dimensional, low-sample size data without retraining.
method Introducing Graph-guided Ordering with Local Refinement (GO-LR) and Neuro-Inspired Subunit Compression (NSC) to create compact meta-features.
result GOTabPFN improves stability and accuracy in tabular benchmarks with compact tokenization.
High signal to noise ratio (SNR) consistency of model selection criteria in linear regression models has attracted a lot of attention recently. However, most of the existing literature on high SNR consistency deals with model order selection. Further, the limited literature available on the high SNR consistency of subs…
Paper finds sample complexity for learning high-dimensional simplices from noisy data.
problem Learning high-dimensional simplices from noisy samples.
method Combines sample compression, high-dimensional geometry, and Fourier analysis.
result Proves sample complexity bound for achieving a simplex within a certain distance from the true simplex.
This paper studies the classification of high-dimensional Gaussian signals from low-dimensional noisy, linear measurements. In particular, it provides upper bounds (sufficient conditions) on the number of measurements required to drive the probability of misclassification to zero in the low-noise regime, both for rando…
EControl improves fast distributed optimization with compression and error control.
problem Stable convergence issues in distributed training with compression.
method Proposes EControl to regulate error compensation and prove fast convergence.
result Proves fast convergence for EControl in various convex settings without additional assumptions.
Unified analysis of SGD variants for nonconvex federated optimization.
problem Performance of stochastic gradient methods in nonconvex optimization.
method Proposed a unified assumption for modeling stochastic gradient second moment, leading to a single convergence analysis for various methods.
result Unified convergence analysis for a wide range of SGD variants and distributed methods.
CoDeQ simplifies joint model compression by integrating pruning and quantization.
problem Joint pruning and quantization methods are complex and require additional procedures.
method CoDeQ uses a dead-zone quantizer to directly induce sparsity and learn quantization parameters.
result CoDeQ achieves high sparsity and low-precision accuracy with minimal bit operations.
Study of deep neural networks with dependent weights leading to new model limits and properties.
problem Characterizing deep neural networks with dependent weights in the infinite-width limit.
method Modeling weights as a mixture of Gaussian distributions and analyzing the infinite-width limit.
result Characterization of neural network layers by scalar parameters and Lévy measures, leading to new model limits.
We study the limits and methods of training two-layer autoencoders.
problem Understanding the limits and methods of training two-layer autoencoders.
method Focus on non-linear two-layer autoencoders trained in the proportional regime, using gradient methods.
result Gradient methods achieve the minimizers of the population risk and reveal the structure of the features.
Neural networks compress uninformative input directions, improving test error.
problem Data lie in a high-dimensional space but labels vary along a lower-dimensional manifold.
method One-hidden layer network trained with gradient descent, analyzing weight evolution and compression.
result Compression factor λ ∼ √p improves test error, with β Feature > β Lazy.
The relevance of data quantifies learning efficiency.
problem Understanding the statistical nature of high-dimensional, sparse data.
method Defining relevance as information content, and using it to define ideal limits of samples and learning machines.
result Maximally informative samples and optimal learning machines exhibit critical features like power-law frequency distributions and anomalously large susceptibility.
Study uncovers scaling laws and spectral properties of shallow neural networks.
problem Understanding scaling laws and spectral properties of shallow neural networks.
method Leveraging connections with matrix compressed sensing and LASSO, derived a phase diagram for excess risk.
result Uncovered crossovers between scaling regimes and plateau behaviors, validated empirical observations.
Overparameterization aids in model pruning, leading to improved test accuracy.
problem Improving lightweight model performance through pruning.
method Theoretical analysis and high-dimensional asymptotics of model pruning in overparameterized neural networks.
result Even with known informative features, training a large model and then pruning leads to better test accuracy.
Optimal privacy and accuracy in distributed mean estimation with compression.
problem Achieving optimal accuracy under privacy and communication constraints.
method Compression to reduce communication while maintaining privacy and accuracy.
result Achieves optimal error with significantly reduced communication.
The restricted isometry property (RIP) for design matrices gives guarantees for optimal recovery in sparse linear models. It is of high interest in compressed sensing and statistical learning. This property is particularly important for computationally efficient recovery methods. As a consequence, even though it is in …
Paper optimizes privacy-preserving distribution estimation for sparse data.
problem Sparse distribution estimation under local differential privacy constraints.
method Compressive sensing approaches for privacy-preserving estimation.
result Significant reduction in sample complexity for approximately sparse distributions.
CoreFlow models matrix-valued distributions efficiently, preserving shared low-rank structure.
problem Learning matrix-valued distributions from high-dimensional and incomplete data.
method Low-rank flow model that learns shared row/column subspaces and trains a normalizing flow on the core.
result CoreFlow improves generation quality in few-sample regimes and remains competitive in data-rich settings.
Auto-Compressing Subset Pruning reduces model size for faster inference.
problem High parameter counts and slow inference times in semantic segmentation models.
method Learning a channel selection mechanism based on temperature annealing schedule.
result Significant compression of segmentation models with acceptable inference performance.
L21 SNF compresses mixed-sign data robustly.
problem Compression of mixed-sign data with high fidelity.
method Regularized L21 Semi-NonNegative Matrix Factorization (L21 SNF).
result Rigorous proof of convergence and use-case advantages demonstrated.
ResNet learns to compress information during training.
problem Applying information bottleneck principle to deep learning models.
method Trained PixelCNN++ models to measure mutual information between ResNet hidden layers and input data.
result Compression occurs in both classification and autoencoding training regimes.
Linear regression studies the problem of estimating a model parameter β∗∈Rp, from n observations {(yi,xi)}i=1n from linear model yi=⟨xi,β∗⟩+εi. We consider a significant generalization in which the relationship between $\langle \mathbf{x}_i,β^* \ran…
We discuss algorithms for estimating the Shannon entropy h of finite symbol sequences with long range correlations. In particular, we consider algorithms which estimate h from the code lengths produced by some compression algorithm. Our interest is in describing their convergence with sequence length, assuming no limit…
Paper introduces MoTEF for faster decentralized optimization with compressed communication.
problem Efficiency bottleneck in decentralized machine learning applications.
method Integrates communication compression with Momentum Tracking and Error Feedback.
result Significantly outperforms existing methods under arbitrary data heterogeneity.
BCAE-2D compresses 3D data from a time projection chamber at high speed.
problem Compressing high-speed, sparse 3D data from a time projection chamber.
method 2D Bicephalous Convolutional Autoencoder (BCAE-2D) approach.
result 3x speedup in compression throughput with improved reconstruction accuracy.
New video compression method outperforms traditional approaches.
problem Efficient video compression in low latency mode.
method Feedback Recurrent Autoencoder network architecture.
result State of the art MS-SSIM/rate performance on UVG dataset.
C3 compresses images and videos with low complexity and high performance.
problem High complexity and low performance in neural compression models.
method Overfits a small model to each image or video separately, improving RD performance with low complexity.
result Matches the RD performance of state-of-the-art neural and video codecs with significantly lower decoding complexity.
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.
Efficiently compress pretrained models using RSI for improved predictive accuracy.
problem Efficiently compressing large pretrained models for practical deployment.
method Randomized subspace iteration (RSI) for low-rank approximation of pretrained models.
result RSI achieves near-optimal approximation quality and outperforms RSVD in predictive accuracy.
A new framework uses an Incremental Transformer to design geopolymer mixtures efficiently.
problem Designing geopolymer mixtures with limited data and physical constraints.
method Topology-aware surrogate framework guided by Incremental Transformer.
result The design space is redundant, with fewer effective mixture regimes.
This paper investigates the average-case time complexity of certifying RIP matrices.
problem Certifying the restricted isometry property (RIP) for large sparsity levels in random Gaussian matrices.
method Analysis of the low-degree likelihood ratio to determine the average-case time complexity.
result Subexponential runtime of NildeΩ(s2/M) is required for certifying RIP matrices. 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 produce embeddings of knots in thin position that admit compressible thin levels. We also find the bridge number of tangle sums where each tangle is high distance.
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.
This paper speeds up SVC clustering by compressing data while preserving key properties.
problem Efficiently clustering large-scale real-world data sets.
method Spectrum-preserving data compression for fast support vector clustering.
result Achieved 100X and 115X speedups on real-world data sets while maintaining clustering quality.
Uniform approximations for RHTs improve kernel approximation and distance estimation.
problem Theoretical guarantees for RHTs in low-dimensional applications.
method Proved uniform convergence of average of function over RHTs entries.
result Improved guarantees for kernel approximation and distance estimation.
Gradient sparsification enhances privacy-preserving machine learning models.
problem Improving performance of differentially-private machine learning models under privacy constraints.
method Gradient sparsification combined with compressed sensing and additive Laplace noise.
result Gradient sparsification can improve performance of differentially-private machine learning models for small privacy budgets.
In real-world, many problems can be formulated as the alignment between two geometric patterns. Previously, a great amount of research focus on the alignment of 2D or 3D patterns, especially in the field of computer vision. Recently, the alignment of geometric patterns in high dimension finds several novel applications…
New method for cross-validation in high-dimensional data with dependent or heavy-tailed covariates.
problem Inconsistent cross-validation in high-dimensional settings with dependent or heavy-tailed covariates.
method ROTI-GCV framework for cross-validation under proportional asymptotics regime.
result Demonstrated accuracy of ROTI-GCV in synthetic and semi-synthetic settings.
Efficiently price high-dimensional Bermudan options using tensor compression.
problem High-dimensional option pricing with computational complexity.
method Hierarchical tensor compression for Monte Carlo and dual martingale methods.
result Tensor compression alleviates the curse of dimensionality for Bermudan option pricing.
Measures strategy durability through minimum regime performance, revealing trade-offs between efficiency and resilience.
problem Systematic investing strategies are vulnerable to regime changes, affecting their effectiveness and performance.
method Introduces minimum regime performance (MRP) to quantify the durability of systematic strategies, capturing how performance deteriorates under changing market conditions.
result Higher long-term Sharpe ratios do not always correlate with higher MRP, highlighting a new dimension of portfolio fragility.