Research
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.

169,181 papers · 148 categories

Trend · papers per month

1223 · Apr 202019922001200920182026
37 results for Low-bit

Kernel Quantization improves CNN compression without sacrificing performance.

problem Efficiently compressing CNN models without significant performance loss.
method Quantizes convolution kernels as the unit, learning a codebook for low-bit indexes.
result Significant compression ratio achieved with minimal accuracy loss.

Paper proposes efficient INT4 quantization for neural networks.

problem Efficient inference on limited hardware resources for large neural networks.
method Formalizes quantization as MMSE problem, optimizes constrained MSE at each layer, partitions parameters, uses multiple quantized tensors.
result 4-bit integer (INT4) quantization yields state-of-the-art results with minimal accuracy loss.

LSQ+ improves quantization of neural nets with Swish activations, achieving state-of-the-art results.

problem Quantization of neural nets with Swish activations, especially negative activations, leads to significant performance loss.
method Introduces learnable scale and offset parameters for asymmetric quantization, and uses MSE-based initialization for quantization parameters.
result Significantly outperforms LSQ for low-bit quantization of neural nets with Swish activations, achieving up to 5.6% gain with W2A2 quantization of EfficientNet-B0.

Proposes QEP to mitigate quantization error propagation in layer-wise post-training quantization.

problem Growth of quantization errors across layers degrades performance, especially in low-bit regimes.
method Quantization Error Propagation (QEP) framework that explicitly propagates and compensates for quantization errors.
result QEP-enhanced layer-wise PTQ achieves substantially higher accuracy, especially in low-bit regimes.

Two novel network quantization approaches improve deep neural network compression.

problem Efficiently compress deep neural networks for practical usage.
method Single-level network quantization (SLQ) and Multi-level network quantization (MLQ).
result Both SLQ and MLQ achieve impressive results in compressing state-of-the-art neural networks.

A new quantization strategy reduces Transformer model size and inference time.

problem Heavy computation load and memory overhead in Transformer models for mobile devices.
method Mixed precision quantization with varying bits per word in embedding blocks.
result 11.8x smaller model size and 3.5x speed up for on-device NMT.

MSD removes dequantization bottleneck in LLM inference by approximating high-precision activations.

problem Dequantization bottleneck in LLM inference on modern AI accelerators.
method MSD decomposes high-precision activations into multiple low-precision components for direct multiplication with quantized weights.
result MSD avoids INT8-to-BF16 weight conversion, reducing dequantization cycles and HBM traffic.

New framework reduces LLM complexity by directly finetuning in Boolean domain.

problem Reducing the complexity of large language models (LLMs) while maintaining performance.
method Proposes a novel framework using multi-kernel Boolean parameters for direct finetuning in the Boolean domain.
result Significantly reduces complexity during both finetuning and inference, outperforming recent techniques.

Probabilistic BLRNet uses binary weights and activations for efficient neural networks.

problem Efficiently training and deploying deep neural networks with limited memory and compute.
method Probabilistic training method for binary weights and activations, introducing stochastic operations.
result BLRNet achieves performance comparable to full-precision networks while using fewer bits.

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.

New quantization methods improve accuracy of Random Fourier Features.

problem Improving accuracy of Random Fourier Features for machine learning.
method Sigma-Delta and distributed noise-shaping quantization methods for 1-bit and low bit-depth quantization.
result Quantized RFFs allow high accuracy approximation of underlying kernels with polynomial error decay.

Enhances LLM quantization with MDBF, improving perplexity and accuracy.

problem Limited performance of Double Binary Factorization in extreme quantization.
method Introduces Multi-envelope DBF, retaining sign matrices and replacing single envelope with rank-ll envelope.
result Improves perplexity and zero-shot accuracy over previous binary formats.

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.

This work improves DNN weight quantization with ADMM, achieving lossless binarization and reduced search space.

problem Improving DNN model compression and accuracy with low bit quantization.
method Extending ADMM framework for DNN weight quantization with progressive multi-step approach.
result Achieved lossless and fully binarized DNNs with reduced accuracy loss.

Flexpoint improves deep learning training efficiency by using adaptive 16-bit format.

problem Training deep neural networks in low bit-width formats is challenging.
method Flexpoint uses a shared exponent dynamically adjusted to minimize overflows and maximize dynamic range.
result 16-bit Flexpoint tensors closely match 32-bit floating point in training deep networks without tuning.

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.

Bayesian Bits unifies quantization and pruning through gradient optimization.

problem Joint mixed precision quantization and pruning for efficient neural networks.
method Gradient-based optimization with a novel bit width decomposition and learnable stochastic gates.
result Bayesian Bits achieves better accuracy vs. efficiency trade-off compared to static bit width networks.

Post-training quantization method using multiple low-precision points achieves higher precision for critical weights.

problem Discretizing pre-trained deep neural networks without re-training.
method Multipoint quantization with efficient greedy selection and adaptive point number.
result Outperforms state-of-the-art methods on ImageNet classification and PASCAL VOC object detection.

Flexible deep learning models for dynamic accuracy and speed trade-offs.

problem Dynamic accuracy and speed trade-offs in real-world applications.
method Training deep neural networks with a new method allowing flexible numerical precision during inference.
result Achieved comparable accuracy to dedicated models trained at the same precision with dynamic precision settings.

Study quantization effects on high-dimensional linear regression learning.

problem Understanding quantization's impact on learning high-dimensional linear regression models.
method Analyzes stochastic gradient descent for high-dimensional linear regression under various quantization targets.
result Establishes precise bounds on excess risk for different quantization schemes.

Quantization-aware training can recover accuracy lost by post-training quantization.

problem Post-training quantization (PTQ) can fail sharply at aggressive bitwidths.
method A unified geometric framework that explains PTQ failure and QAT recovery.
result QAT has a useful bias that steers iterates back into the basin.

This work proposes a complete 8-bit quantization framework for large-scale deep neural networks.

problem Training large-scale deep neural networks with high performance and low memory footprint.
method WAGEUBN framework that quantizes all data paths including weights, activations, gradients, errors, updates, and batch normalization.
result Achieves competitive accuracy on the ImageNet dataset using only 8-bit integers.