Low-bit training framework reduces energy consumption in CNNs.
problem Reducing energy consumption in convolutional neural networks.
method Low-bit training framework using MLS tensor format with dynamic quantization.
result Achieves superior trade-off between accuracy and bit-width.
SMGD trains low-bit neural networks with memory constraints.
problem Training large neural networks with limited memory.
method Stochastic Markov Gradient Descent (SMGD).
result Encouraging numerical results and theoretical guarantees.
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.
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.
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.
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.
Neural network VQ-VAE with WaveNet decodes speech at 1.6 kbps with high quality.
problem Efficiently transmitting and storing speech signals at low bit-rates.
method VQ-VAE and WaveNet architecture for speech coding.
result Speech coding at 1.6 kbps with perceptual quality between MELP and AMR-WB.
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.
New method quantizes neural networks for mobile devices.
problem High computational and memory costs of deep neural networks.
method Formulates quantization as a differentiable function.
result Quantization networks outperform state-of-the-art methods.
BCGD algorithm improves training of quantized neural networks.
problem Training quantized deep neural networks at low bit-widths.
method Introduces coarse gradient descent and blended correction for training.
result BCGD achieves high accuracy in quantized neural networks.
New method reduces deep learning complexity on IoT devices.
problem High computational complexity limits deep learning on IoT devices.
method Local quantization region for low-bit data representation.
result Models retain accuracy with reduced computational complexity.
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.
Meta learning optimizes neural network quantization for efficient inference.
problem Uniform bitwidth quantization is sub-optimal for neural network compression.
method Meta learning to automatically generate hybrid quantization policies.
result Meta learning outperforms uniform quantization and RL approaches.
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.
Moniqua improves SGD convergence with quantized communication.
problem Efficiently communicating in decentralized SGD with limited bandwidth.
method Modulo quantized communication in decentralized SGD.
result Moniqua converges at the same rate as full-precision communication with less bits.
Deep learning improves decoding of constrained sequence codes, reducing errors and increasing throughput.
problem Errors during transmission of constrained sequence codes.
method Deep learning, specifically MLP and CNN networks.
result Achieved low bit error rates close to MAP decoding and improved system throughput.
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-l 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.
A novel method quantizes Batch Normalization for QNNs, maintaining accuracy and efficiency.
problem Quantization challenges in Batch Normalization for QNNs.
method Converts BN to fixed-point operation with shared scale, suitable for hardware.
result Maintains same outputs through rigorous analysis and experiments.
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.
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.
TensorQuant simulates quantization of DNNs for efficient computation.
problem Optimal quantization method and bit number for DNNs are topology-dependent.
method TensorQuant simulates quantization of existing DNN topologies.
result TensorQuant supports experimental evaluation of quantization impact.
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.
QABBA improves time series storage efficiency while preserving shape information.
problem Efficient storage and shape preservation of time series data.
method Quantized symbolic time series approximation (QABBA) using ABBA technique.
result QABBA achieves a new state-of-the-art on Monash regression dataset.
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.