Quantization can be used to form new vectors/matrices with shared values close to the original. In recent years, the popularity of scalar quantization for value-sharing applications has been soaring as it has been found huge utilities in reducing the complexity of neural networks. Existing clustering-based quantization…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,932 papers · 148 categories
Trend · papers per month
48 results for “sparse quantization”
DeepFPC uses neural networks to recover sparse signals from quantized measurements.
problem Recovering sparse signals from quantized measurements.
method Unfolding the fixed-point continuation algorithm into a deep neural network.
result DeepFPC outperforms state-of-the-art algorithms in DOA estimation.
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.
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.
Sparse linear regression with compressed and low-precision data via concave quadratic programmingmath.OC
New method recovers sparse vectors from compressed, noisy data.
problem Recovering sparse vectors from compressed and noisy measurements.
method Non-convex quadratic programming exploiting prior magnitude information.
result More efficient support recovery with sufficient conditions for success.
MCQ uses Monte Carlo methods to efficiently quantize neural networks without re-training.
problem Efficiently quantizing neural networks for lower power consumption.
method Importance sampling for quantization of weights and activations.
result Minimal accuracy loss with quantized networks compared to full-precision networks.
Modern distributed training of machine learning models suffers from high communication overhead for synchronizing stochastic gradients and model parameters. In this paper, to reduce the communication complexity, we propose \emph{double quantization}, a general scheme for quantizing both model parameters and gradients. …
We propose in this contribution a method for l one regularization in prototype based relevance learning vector quantization (LVQ) for sparse relevance profiles. Sparse relevance profiles in hyperspectral data analysis fade down those spectral bands which are not necessary for classification. In particular, we consider …
Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a challenge in deploying them on constrained devices. Existing compression techniques, while excelling at reducing model sizes, struggle to be comp…
New method preserves spectral clustering performance under aggressive sparsification and quantization.
problem Maintaining spectral clustering performance with sparse and quantized data.
method Random matrix theory applied to eigenspectrum changes under sparsification and quantization.
result Spectral clustering performance is preserved even with aggressive sparsification and quantization.
This paper finds a new way to compress CNN weights, improving on pruning and quantization.
problem Improving performance and storage efficiency of CNNs.
method Identifying and exploiting repeated patterns in CNN weight tensors, using Huffman coding and block sparse matrix formats.
result Achieved compaction ratios of 1.4x to 3.1x in addition to pruning and quantization.
New algorithm recovers sparse binary vectors from generalized linear measurements efficiently.
problem Recovering sparse binary vectors from generalized linear measurements.
method Linear estimation algorithm and information theoretic lower bounds.
result Optimal sample complexity of for noisy one bit quantized linear measurements.
A new method for multiclass calibration using vector quantization.
problem Challenges in multiclass calibration, especially in high-stakes settings.
method Compositional approach via Vector Quantization (VQ) to learn region-specific calibration maps.
result Significant improvements in local calibration with competitive global calibration and predictive performance.
Paper proposes a hybrid model-based and data-driven method for one-bit compressive variational autoencoding.
problem Designing efficient one-bit compressive sensing systems.
method Hybrid model-based and data-driven approach for one-bit compressive variational autoencoding.
result Significant improvement in one-bit compressive sensing compared to state-of-the-art methods.
Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)cs.LG
EC2T creates sparse and ternary neural networks for resource-constrained devices.
problem Deploying deep neural networks on resource-constrained devices.
method Entropy-Constrained Trained Ternarization (EC2T) framework.
result EC2T creates sparse and ternary neural networks that are efficient in terms of storage and computation.
A fast binary embedding method preserves Euclidean distances in high-dimensional data.
problem Preserving Euclidean distances in high-dimensional datasets.
method Stable noise-shaping quantization of with a sparse Gaussian random matrix, followed by a linear transformation.
result Euclidean distances are approximated by the norm on binary sequences, leading to accurate binary codes.
The thesis explores how to integrate machine learning with hardware constraints.
problem Designing efficient neural networks for real-time processing with hardware limitations.
method Developed a library for training and converting sparse quantized neural networks to hardware.
result Demonstrated how to design and optimize neural networks for FPGA-based hardware.
SmartDeal reduces energy and storage costs for deep neural networks.
problem Heavy parameterization of deep neural networks leads to inefficient use of DRAM.
method SmartDeal decomposes weights into a small basis matrix and a structurally sparse coefficient matrix, quantized to power-of-2.
result Up to 2.44x energy efficiency improvement in inference and 10.56x reduction in training energy.
This paper improves support recovery in universal one-bit compressed sensing with fewer measurements.
problem Support recovery in universal one-bit compressed sensing.
method Developed algorithms to recover the support of sparse signals with a small number of false positives.
result Support recovery with measurements, improving to with known dynamic range.
Consider the recovery of an unknown signal from quantized linear measurements. In the one-bit compressive sensing setting, one typically assumes that is sparse, and that the measurements are of the form . Since such measurements give no informati…
EAST compresses deep ConvNets for tiny memory nodes.
problem Memory constraints in tiny devices for deep ConvNets.
method Encoding-Aware Sparse Training (EAST) with adaptive group pruning and LZ4 weight encoding.
result EAST achieves deep memory compression with lower sparsity and higher accuracy.
A Spike in Performance: Training Hybrid-Spiking Neural Networks with Quantized Activation Functionscs.LG
Improved SNNs with quantized activations outperform traditional networks.
problem Maintaining SotA accuracy in SNNs with limited bit precision.
method Interpolating between non-spiking and spiking regimes using signal processing tools.
result First hybrid SNN outperforms traditional RNNs in accuracy with reduced bit precision.
A new method reduces deep learning training costs by 92%.
problem High computational cost of backpropagation in deep neural networks.
method Dithered backprop with non-subtractive dither quantization.
result 92% sparsity with minimal accuracy loss.
New algorithm reduces communication in distributed learning by sharing compressed beliefs.
problem Efficiently learning from private data in a distributed setting with large hypothesis sets.
method Proposes a belief update rule for distributed cooperative learning with compressed (sparse or quantized) beliefs.
result Beliefs converge almost surely to optimal hypotheses with a linear concentration rate.
Paper proposes a learning-based sparse Bayesian method for accurate off-grid DOA estimation.
problem One-bit off-grid direction of arrival (DOA) estimation in a single snapshot scenario.
method Formulated off-grid DOA estimation model, used Sparse Bayesian framework, proposed Learning-based Sparse Bayesian approach.
result Improved computational efficiency and accuracy in off-grid DOA estimation.
Paper compresses neural network weight-updates for image artifacts removal.
problem Efficiently compressing neural network weight-updates for image artifacts removal.
method Fine-tuning a pre-trained artifact removal network on target data with a compression objective that encourages sparse and quantized weight-updates.
result Achieves reconstruction quality comparable to traditional codecs at comparable bitrates.
SmartExchange trades memory for computation in neural networks.
problem Energy-efficient inference of deep neural networks.
method Algorithm-hardware co-design framework integrating sparsification, decomposition, and quantization.
result SmartExchange reduces energy consumption and improves performance.
Embedding representation learning via neural networks is at the core foundation of modern similarity based search. While much effort has been put in developing algorithms for learning binary hamming code representations for search efficiency, this still requires a linear scan of the entire dataset per each query and tr…
One-bit quantization and sparsification improve multiclass classification with strong regularization.
problem Overfitting mislabeled data in multiclass classification.
method Linear regression with regularization and one-bit quantization/sparsification.
result Sparse and one-bit solutions perform almost as well as the optimal solution with .
Kolmogorov-Arnold Networks enable ultrafast online learning with fixed-point quantization.
problem Efficient online learning for high-frequency systems with strict memory constraints.
method Fixed-point online training on FPGAs exploiting B-spline locality in KANs.
result Kolmogorov-Arnold Networks are more efficient and expressive than MLPs for low-latency tasks.
Generates high-quality images using sparse DCT representations.
problem Challenges in generating images due to high dimensionality.
method Transformers trained on sparse DCT block sequences.
result Competitive image generation quality with state-of-the-art methods.
This work proposes a method to learn sparse representations that are more efficient for large-scale data retrieval.
problem Efficient retrieval of high-dimensional representations from large databases is computationally challenging.
method The approach minimizes the number of floating-point operations (FLOPs) by learning sparse embeddings with uniform non-zero entries.
result The proposed method achieves a similar or better speed-vs-accuracy tradeoff compared to existing baselines.
Survey on quantization methods on Kähler manifolds.
problem None explicitly stated; focuses on methods.
method Deformation quantization, geometric quantization, Berezin-Toeplitz quantization, BV quantization.
result New relationships among quantization methods on Kähler manifolds.
This paper examines a general class of noisy matrix completion tasks where the goal is to estimate a matrix from observations obtained at a subset of its entries, each of which is subject to random noise or corruption. Our specific focus is on settings where the matrix to be estimated is well-approximated by a product …
Improved LLM pre-training performance through better weight and variance control.
problem Improper weight and variance control in LLM pre-training affects downstream task performance.
method Introduced Layer Index Rescaling (LIR) and Target Variance Rescaling (TVR) techniques.
result Substantial improvements in downstream task performance (up to 4.6%) and reduced extreme activation values.
This paper examines fundamental error characteristics for a general class of matrix completion problems, where the matrix of interest is a product of two a priori unknown matrices, one of which is sparse, and the observations are noisy. Our main contributions come in the form of minimax lower bounds for the expected pe…
While the harmonic function solution performs well in many semi-supervised learning (SSL) tasks, it is known to scale poorly with the number of samples. Recent successful and scalable methods, such as the eigenfunction method focus on efficiently approximating the whole spectrum of the graph Laplacian constructed from …
The paper classifies quantizable functions and explores symmetry in quantization methods.
problem Classifying quantizable functions and understanding symmetry in quantization methods.
method Deformation quantization and geometric quantization methods are compared and classified.
result Formal quantizable functions are of a specific form and relate to Hamiltonian Killing vector fields.
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.
Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratchcs.CV
This paper introduces a differentiable, scalable quantization method for neural networks.
problem Previous quantization methods lacked differentiability and scalability.
method The approach is differentiable and scalable, using bit-shifting and logarithmic quantization.
result The method achieves comparable accuracy to state-of-the-art approaches with less training time and lower inference cost.
Binary Iterative Hard Thresholding converges with optimal number of 1-bit measurements.
problem Recovering sparse signals from 1-bit compressed measurements.
method Binary Iterative Hard Thresholding (BIHT) algorithm.
result BIHT converges with only O(k/ε) measurements, optimal for recovery.
StatQAT optimizes quantization for deep networks, reducing computational cost and memory usage.
problem Optimal quantization parameters selection for deep neural networks with diverse data distributions.
method Statistical error analysis framework for uniform and floating-point quantization, iterative and analytic quantizers designed for arbitrary and Gaussian-like distributions.
result Improved accuracy and stability in training low-precision neural networks.
Smart Quantization adapts binary and ternary quantization for neural networks.
problem Resource constraints in deploying neural networks on devices with limited resources.
method Adaptive combination of binary and ternary quantization with a regularization function.
result Adapts quantization depth during training to maintain high model accuracy.
This study optimizes quantized neural networks by considering model architecture and quantization types.
problem Optimizing quantized neural networks for low-power, high-throughput applications.
method Holistic approach including training methods and quantization-friendly architecture design.
result Deeper models are more sensitive to activation quantization, while wider models improve resilience to both weight and activation quantization.
RATQ is a new quantizer for optimizing noisy gradients in machine learning.
problem Optimizing noisy gradients in stochastic optimization.
method RATQ uses Hadamard transform and adaptive uniform quantization, and achieves near-optimal performance.
result RATQ nearly achieves information theoretic lower bounds for optimization accuracy.
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.
Extends ONNX for quantized neural networks with new formats and operators.
problem Handling arbitrary-precision quantization in neural networks.
method Introduces new formats and operators in ONNX to represent quantized neural networks.
result Enabled representation of uniform quantization in neural networks.
This paper improves support recovery in universal one-bit compressed sensing.
problem Support recovery in one-bit compressed sensing for sparse signals.
method Proposes approximate support recovery and superset recovery algorithms with polynomial-time complexity.
result Achieves improved support recovery with fewer measurements compared to existing methods.