Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs. However, we observe that the conventional quantization approaches are vulnerable to adversarial attacks. This paper aims to raise people's awareness about the …
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “quantization efficiency”
BiQGEMM efficiently multiplies quantized DNN weights using lookup tables.
problem Efficiently multiplying quantized DNN weights on CPUs/GPUs with limited memory.
method BiQGEMM pre-computes and stores redundant intermediate results in lookup tables.
result BiQGEMM achieves lower overall computations and higher performance.
DJPQ optimizes neural network pruning and quantization for hardware efficiency.
problem Efficiently compress neural networks for hardware inference.
method Joint gradient-based optimization of pruning and quantization into a differentiable loss function.
result Significant reduction in Bit-Operations (BOPs) with minimal accuracy loss.
FrostNet improves INT8 quantization efficiency in mobile networks.
problem The importance of network architecture for optimal INT8 quantization.
method Quantization-aware training (QAT) with StatAssist and GradBoost, hardware-aware NAS.
result FrostNets achieve higher recognition accuracy with comparable latency when quantized.
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.
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.
Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscs.LG
We propose Additive Powers-of-Two~(APoT) quantization, an efficient non-uniform quantization scheme for the bell-shaped and long-tailed distribution of weights and activations in neural networks. By constraining all quantization levels as the sum of Powers-of-Two terms, APoT quantization enjoys high computational effic…
DQA efficiently quantizes deep neural network activations for resource-constrained devices.
problem Efficiently quantizing deep neural network activations for resource-constrained devices.
method DQA uses simple shifting-based operations and Huffman coding for sub-6-bit quantization.
result DQA achieves significantly better accuracy than direct quantization and state-of-the-art methods.
Q-GADMM reduces communication in decentralized ML by quantizing model updates.
problem Reducing communication in decentralized ML while maintaining accuracy.
method Quantized group ADMM (Q-GADMM) with adaptive quantization.
result Q-GADMM achieves similar accuracy and convergence to non-quantized methods with less communication.
Generative model for HW-aware DNN quantization.
problem Efficiently tuning DNNs for various hardware platforms.
method Generative model AQGAN for generating quantization configurations based on target accuracy.
result Generative model generates quantization configurations with competitive accuracy and lower search cost.
AdaQuantFL reduces communication in federated learning by adaptively quantizing model updates.
problem Efficient communication of model updates in federated learning with high-dimensional models and limited bandwidth.
method AdaQuantFL uses adaptive quantization to reduce the number of bits for model updates while maintaining low error floor.
result AdaQuantFL converges in fewer communicated bits compared to fixed quantization levels, with minimal impact on accuracy.
Due to its efficiency and ease to implement, stochastic gradient descent (SGD) has been widely used in machine learning. In particular, SGD is one of the most popular optimization methods for distributed learning. Recently, quantized SGD (QSGD), which adopts quantization to reduce the communication cost in SGD-based di…
Optimal gradient quantization reduces communication costs in distributed deep learning.
problem High communication costs in distributed training of deep neural networks.
method Deduced optimal gradient quantization conditions for binary and multi-level quantization, developed novel schemes for dynamic quantization levels.
result Demonstrated superior performance of proposed quantization schemes on CIFAR and ImageNet datasets.
FQ-Conv quantizes CNNs for efficient inference with low-precision weights and activations.
problem Reducing precision in DNNs leads to reduced accuracy.
method Fully quantized convolutional neural networks (FQ-Conv) using novel quantization and training techniques.
result Ternary-weight CNNs perform nearly as well as full-precision networks.
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.
Ternary MobileNets improve efficiency and accuracy on constrained devices.
problem Efficiently compressing MobileNets for real-time applications on constrained devices.
method Per-layer hybrid filter banks for ternary quantization of MobileNets.
result 27.98% energy savings and 51.07% reduction in model size with comparable accuracy.
APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.
problem Efficient deep learning inference on resource-constrained hardware.
method Joint optimization of neural architecture, pruning, and quantization policy using a quantization-aware accuracy predictor.
result Joint optimization leads to 2.3% higher ImageNet accuracy with reduced latency and energy consumption.
The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be carried out using integer-only arithmetic, which can be implemented more efficie…
A new gradient quantization scheme improves communication efficiency in distributed training.
problem Efficiently compressing gradients for parallel training of large models.
method Proposes a new gradient quantization scheme with theoretical guarantees and empirical performance.
result The new scheme matches and exceeds the performance of existing methods.
Unified framework LPCD optimizes quantization of complex submodules.
problem Quantization of complex submodules in neural networks.
method Layer-Projected Coordinate Descent (LPCD) for quantizing arbitrary submodules.
result LPCD enhances both layer-wise PTQ methods and existing submodule approaches.
Degree-Quant improves GNN efficiency by quantizing them without losing accuracy.
problem Efficiency of graph neural networks at inference time.
method Architecturally-agnostic method, Degree-Quant, for quantizing GNNs.
result Degree-Quant trained models perform as well as full-precision models and achieve up to 26% gains.
Efficient Bitwidth Search optimizes neural network quantization for better performance.
problem Finding optimal bitwidth for weights and activations of each layer efficiently.
method EBS algorithm reusing meta weights and binary decomposition for efficient mixed precision convolution.
result Mixed precision QNN outperforms uniform bitwidth and other techniques on CIFAR10 and ImageNet.
WaveQ uses sinusoidal regularization to optimize deep quantization for neural networks, improving both efficiency and accuracy.
problem Deep quantization reduces bitwidth but can lead to significant accuracy loss due to inter-layer dependencies.
method WaveQ employs sinusoidal regularization to learn multiple quantization parameters during gradient-based training, balancing compute efficiency and accuracy.
result WaveQ achieves accuracy preservation and efficiency gains across various deep networks, outperforming state-of-the-art techniques.
Quantized-TinyLLaVA reduces communication costs in split learning for multimodal models.
problem High communication costs in split learning for multimodal models.
method Integrates a compression module that quantizes intermediate features into discrete representations before transmission.
result Achieves an approximate 87.5% reduction in communication overhead with 2-bit quantization.
Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMMcs.LG
Efficient decentralized learning framework reduces communication costs.
problem Efficiently solve optimization problems in distributed learning networks.
method Censored and Quantized Generalized GADMM (CQ-GGADMM) framework.
result Achieves linear convergence rate under strong convexity assumptions.
Adaptive quantization improves SGD accuracy in data-parallel settings.
problem Fixed gradient quantization schemes lead to suboptimal performance in deep learning.
method Developed adaptive quantization schemes ALQ and AMQ that update compression schemes based on gradient statistics.
result Improved validation accuracy on CIFAR-10 and ImageNet datasets by 2% and 1% respectively.
DBQ quantizes lightweight networks efficiently for resource-constrained devices.
problem High computational and storage complexity of deep neural networks on resource-constrained devices.
method A differentiable non-uniform quantizer that can be mapped onto efficient ternary-based dot product engines.
result Achieves state-of-the-art results with minimal training overhead and best accuracy-complexity trade-off.
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. …
A simple and computationally efficient scheme for tree-structured vector quantization is presented. Unlike previous methods, its quantization error depends only on the intrinsic dimension of the data distribution, rather than the apparent dimension of the space in which the data happen to lie.
HMQ improves quantization for edge devices with mixed precision.
problem Efficient quantization for edge devices with uniform, power-of-two thresholds.
method Introduces HMQ, a mixed precision quantization block that repurposes Gumbel-Softmax for searching over quantization schemes.
result Achieves competitive and state-of-the-art results on ImageNet despite restrictions.
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.
Convolutional Neural Networks (CNN) has become more popular choice for various tasks such as computer vision, speech recognition and natural language processing. Thanks to their large computational capability and throughput, GPUs ,which are not power efficient and therefore does not suit low power systems such as mobil…
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.
This paper quantizes CapsNets for efficient edge deployment.
problem CapsNets require intense computations and are not suitable for resource-constrained edge devices.
method Developed a specialized quantization framework for CapsNets.
result Reduced memory footprint by 6.2x with only 0.15% accuracy loss.
We present Rotated Adaptive Tetra-iterated Quantizer (RATQ), a fixed-length quantizer for gradients in first order stochastic optimization. RATQ is easy to implement and involves only a Hadamard transform computation and adaptive uniform quantization with appropriately chosen dynamic ranges. For noisy gradients with al…
Paper proposes BQNs for efficient Bayesian quantized neural networks.
problem Learning with well-calibrated uncertainty in neural networks.
method Bayesian quantized networks (BQNs) with efficient algorithms for learning and prediction without sampling.
result BQNs achieve lower predictive errors and better-calibrated uncertainties than E-QNN with less than 20% negative log-likelihood.
Cyber-Physical Systems (CPSs) have been pervasive including smart grid, autonomous automobile systems, medical monitoring, process control systems, robotics systems, and automatic pilot avionics. As usually implemented on embedded devices, CPS is typically constrained by computation capacity and energy consumption. In …
LIQSS method improves accuracy and efficiency for power system simulations.
problem Accurately modeling and simulating long-duration mission profiles of Naval power systems.
method Linear Implicit Quantized State System (LIQSS) method for stiff, nonlinear, differential algebraic equations.
result LIQSS1 method yields results within 1% accuracy of continuous methods and increases efficiency logarithmically with quantization size.
In this paper, we introduce the problem of decision-oriented communications, that is, the goal of the source is to send the right amount of information in order for the intended destination to execute a task. More specifically, we restrict our attention to how the source should quantize information so that the destinat…
Deep neural network (DNN) quantization converting floating-point (FP) data in the network to integers (INT) is an effective way to shrink the model size for memory saving and simplify the operations for compute acceleration. Recently, researches on DNN quantization develop from inference to training, laying a foundatio…
Quantization techniques have been applied in many challenging finance applications, including pricing claims with path dependence and early exercise features, stochastic optimal control, filtering problems and efficient calibration of large derivative books. Recursive Marginal Quantization of the Euler scheme has recen…
New method trains quantized neural networks to global optimality.
problem Training optimal quantized neural networks is intractable due to combinatorial non-convex optimization.
method Convex optimization strategy using hidden convexity, semidefinite lifting, and Grothendieck's identity.
result Quantized NN problems can be solved to global optimality in polynomial-time.
Improved EXACT strategy reduces GNN memory consumption and runtime.
problem Efficiently training large-scale GNNs with reduced memory usage.
method Block-wise quantization of intermediate activation maps with improved variance minimization.
result Further reduction in memory consumption (>15%) and runtime speedup (5%) with similar performance trade-offs.
Paper shows how to integrate quantization into neural compression models.
problem Integrating quantization into neural compression models.
method Integrates uniform noise channel at test time using universal quantization.
result Eliminates mismatch between training and test phases while maintaining differentiability.
How can we efficiently mitigate the overhead of gradient communications in distributed optimization? This problem is at the heart of training scalable machine learning models and has been mainly studied in the unconstrained setting. In this paper, we propose Quantized-Frank-Wolfe (QFW), the first projection-free and co…
GOBO compresses 99.9% of BERT model parameters to 3 bits, improving inference efficiency.
problem Efficient execution of attention-based NLP models, especially in terms of latency and energy consumption.
method GOBO quantizes 32-bit floating-point parameters to 3 bits without fine-tuning, using hardware compression and co-designed architectures.
result GOBO maintains model accuracy while significantly reducing inference latency and energy consumption.
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.
Low bit-width integer weights and activations are very important for efficient inference, especially with respect to lower power consumption. We propose Monte Carlo methods to quantize the weights and activations of pre-trained neural networks without any re-training. By performing importance sampling we obtain quantiz…