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.

168,695 papers · 148 categories

Trend · papers per month

21436485 · Jun 202019922001200920172026
48 results for mixed quantization

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.

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.

Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.

problem Memory limitations prevent accurate deployment of DNN models on tiny MCUs.
method Automated mixed-precision quantization using Reinforcement Learning for MCU constraints.
result Mixed-precision models achieve high accuracy with uniform quantization policies.

Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with homogeneous bitwidth for the same size constraint. Since choosing the optimal bitwi…

2019-05-27abs ↗pdf ↗

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.

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.

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.

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.

Neural network models are resource hungry. It is difficult to deploy such deep networks on devices with limited resources, like smart wearables, cellphones, drones, and autonomous vehicles. Low bit quantization such as binary and ternary quantization is a common approach to alleviate this resource requirements. Ternary…

2019-09-26abs ↗pdf ↗

Extends quantization theory to mixed polarizations using transverse differential operators.

problem Quantization in mixed polarization.
method Developed a theory of transverse differential operators associated to non-singular polarizations.
result Obtained a geometric interpretation of deformation quantization and sheaf of subalgebras acting on polarized sections.

Efficiently calibrates Bergomi models to VIX derivatives using vector quantization.

problem Calibrating Bergomi models to VIX derivatives for accurate pricing.
method Applied vector quantization in mixed Bergomi models for fast and efficient option pricing.
result Calibration of Bergomi models to VIX derivatives is feasible and accurate over daily data.

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.

In this paper, we study the analytic continuation to complex time of the Hamiltonian flow of certain G×TG\times T-invariant functions on the cotangent bundle of a compact connected Lie group GG with maximal torus TT. Namely, we will take the Hamiltonian flows of one G×GG\times G-invariant function, hh, and one $G\time…

2019-07-11abs ↗pdf ↗

Post-training quantization saves resources for neural networks.

problem Implementing neural networks in resource-constrained hardware.
method Generalized post-training quantization method (GPFQ) with modifications for sparsity and error analysis.
result Error decays linearly with over-parametrization, showing minor loss of accuracy.

This work takes place over a conformally flat spin manifold (M,g). We prove existence and uniqueness of the conformally equivariant quantization valued in spinor differential operators, and provide an explicit formula for it when restricted to first order operators. The Poisson algebra of symbols is realized as a space…

2012-08-20abs ↗pdf ↗

Study of Batalin-Vilkovisky algebra on Poisson manifolds with diagonalizable modular symmetry.

problem Exploring Batalin-Vilkovisky algebra structures on Poisson manifolds with specific symmetry conditions.
method Analysis of twisted Poincaré duality and mixed complex structure, combined with Kontsevich's deformation quantization and Koszul duality.
result Generalization of Batalin-Vilkovisky algebra structure to Poisson manifolds with diagonalizable modular symmetry.

Study of quantum spaces on Kähler manifolds with T-symmetry converging to a mixed polarization.

problem Quantum spaces on Kähler manifolds with T-symmetry and their convergence.
method Construction of a one-parameter family of Kähler structures and study of quantum spaces.
result Quantum spaces corresponding to different polarizations converge to a mixed polarization as the parameter goes to infinity.

A new method quantifies feature-map discriminativeness for efficient pruning of deep neural networks.

problem Efficiently pruning deep neural networks to reduce computation while maintaining accuracy.
method Presented a novel mathematical formulation (Discriminant Information, DI) to quantify feature-map discriminativeness, enabling efficient pruning and intra-layer mixed precision quantization.
result Our pruned ResNet50 achieves 44% FLOPs reduction without any Top-1 accuracy loss.

Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who can paraphrase without being bilingual. This work proposes to learn paraphrasin…

2019-05-29abs ↗pdf ↗

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.

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.

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.

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.

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…

2019-08-22abs ↗pdf ↗

The paper studies quantization on symplectic manifolds with real polarizations, comparing different quantization methods.

problem Quantization on compact symplectic manifolds with real polarizations.
method Geometric quantization, Toeplitz operators, Fourier transforms, asymptotic expansion of traces.
result Deformation quantization is realized through asymptotic traces of Toeplitz operators.

Unified finetuning of all quantization degrees of freedom achieves state-of-the-art 4-bit quantization.

problem Achieving high accuracy in quantized neural networks while maintaining speed and resource constraints.
method Quantization-aware finetuning (QFT) that jointly optimizes all quantization degrees of freedom.
result 4-bit weight quantization results on-par with state-of-the-art (SoTA) within PTQ constraints.

Geometric quantization of a Poisson manifold need not imply quantization of its symplectic leaves. We provide the leafwise geometric quantization of a Poisson manifold, seen as a foliated one, whose quantum algebra restricted to each leaf is quantized.

2001-10-18abs ↗pdf ↗

EMPIR combines low and full precision DNNs to enhance robustness against adversarial attacks.

problem Vulnerability of DNNs to adversarial attacks that misclassify inputs with small perturbations.
method Ensemble of quantized DNN models with different numerical precisions.
result EMPIR ensembles increase adversarial robustness by 42.6% on average across different tasks.