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.

168,657 papers · 148 categories

Trend · papers per month

7142128 · May 201919922001200920172026
48 results for INT8 quantization

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.

This study improves Ernie's accuracy for INT8 inference by modifying its training process.

problem Improving the accuracy of pre-trained models like Ernie for low precision inference.
method Integrates a regularizer into the training process to make it more robust to quantization.
result Increased INT8 accuracy for Ernie models.

Efficient Winograd convolution for INT8 networks using RNS.

problem Difficulty in applying Winograd algorithm to low-precision quantized networks.
method Extends Winograd algorithm to Residue Number System (RNS) for efficient INT8 convolution.
result Arithmetic complexity reduction up to 7.03x with performance improvement up to 2.30x-4.69x.

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.

Study finds optimal learning rate schedules for sub-100M quantization-aware training across bit-widths.

problem Optimal learning rate schedules for quantization-aware training depend on bit-width.
method Factorial grid testing over bit-width, warmdown fraction, LR magnitude, model size, and seed.
result INT6 QAT requires a different schedule than higher-precision training, falsifying the primary hypothesis.

Paper develops a statistical framework for quantized training of deep neural networks.

problem Lack of theoretical understanding of gradient quantization in FQT.
method Presented a statistical framework for analyzing FQT algorithms, viewing quantized gradient as a stochastic estimator of QAT gradient.
result Developed two novel gradient quantizers with smaller variance than existing per-tensor quantizer.

We describe a method for training accurate Transformer machine-translation models to run inference using 8-bit integer (INT8) hardware matrix multipliers, as opposed to the more costly single-precision floating-point (FP32) hardware. Unlike previous work, which converted only 85 Transformer matrix multiplications to IN…

2020-01-03abs ↗pdf ↗

We extend quantization-aware training to extreme model compression.

problem Maximizing model accuracy with minimal model size.
method Quantize a random subset of weights during training, allowing unbiased gradients through other weights.
result Established new state-of-the-art compromises between accuracy and model size.

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.

Generative compression technique reduces neural network size and improves performance on microcontrollers.

problem Memory constraints on microcontrollers limit the size of neural networks, especially for 1x1 pointwise (PW) mixers.
method HYPER-TINYPW uses a shared micro-MLP to generate PW kernels from tiny per-layer codes, reducing memory usage.
result HYPER-TINYPW achieves comparable performance to larger models while being significantly smaller (225 kB vs 1.4 MB).

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.

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.

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.

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 ↗

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 ↗

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.

Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers an alternative approach with improved tolerance to different classes of data-type…

2020-02-18abs ↗pdf ↗

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 study analyzes quantization in deep learning models using statistical physics methods.

problem The computational resource requirements for large-scale data analysis models.
method Typical case analysis from statistical physics, specifically the replica method.
result Optimal quantization width minimizes error and delays overfitting.

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 …

2019-04-17abs ↗pdf ↗

In [3], the authors showed the existence and the uniqueness of a sl(m+1,\R)-equivariant quantization in the non-critical situations. The curved generalization of the sl(m+1,\R)-equivariant quantization is the natural and projectively equivariant quantization. In [1] and [7], the existence of such a quantization was pro…

2006-06-22abs ↗pdf ↗

A unified approach to geometric, symbol and deformation quantizations on a generalized flag manifold endowed with an invariant pseudo-Kaehler structure is proposed. The Hilbert space of states is realized via the Bott-Borel-Weil theorem in the sheaf cohomology of the geometric quantization line bundle. The correspondin…

1997-09-17abs ↗pdf ↗

A new method for robust product Markovian quantization overcomes numerical instabilities.

problem Numerical instabilities in the PMQ algorithm limit its adoption, especially for stochastic volatility models.
method Reformulated PMQ as standard vector quantization, applying accelerated Lloyd's algorithm for robustness.
result The method overcomes numerical instabilities and extends applicability to stochastic volatility models.

Memory-augmented neural networks (MANNs) refer to a class of neural network models equipped with external memory (such as neural Turing machines and memory networks). These neural networks outperform conventional recurrent neural networks (RNNs) in terms of learning long-term dependency, allowing them to solve intrigui…

2017-11-10abs ↗pdf ↗

Paper proposes a new binary quantization method for faster DNN inference.

problem Accelerating deep neural network inference on resource-limited devices.
method Quantized Compressed Sensing (QCS) for binary quantization.
result The proposed method preserves benefits of standard methods while reducing quantization error.

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.

Paper quantizes heavy-tailed data for near optimal estimation rates.

problem Estimating parameters from heavy-tailed data with quantization.
method Truncate and dither data, then uniformly quantize; achieves near minimax rates.
result Near optimal estimation rates achievable with quantized data.