Simplified neural network quantization speeds up process by 8 epochs.
problem Efficient quantization of neural networks for mobile devices.
method Trained scale factors for quantization thresholds.
result Significant reduction in training time and model size.
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.
Energy quantization for surfaces with area, volume, and mean curvature constraints.
problem Energy quantization for constrained Willmore surfaces.
method Established through strong compactness under energy thresholds.
result Strong compactness of constrained Willmore surfaces, including minimizers.
We prove a bubble-neck decomposition together with an energy quantization result for sequences of Willmore surfaces into an arbitrary euclidian space with uniformly bounded energy and non-degenerating conformal type. We deduce the strong compactness of Willmore closed surfaces of a given genus modulo the Möbius group a…
Paper proposes a hybrid model-based and data-driven method for one-bit compressive variational autoencoding.
problem Designing efficient one-bit compressive sensing systems.
method Hybrid model-based and data-driven approach for one-bit compressive variational autoencoding.
result Significant improvement in one-bit compressive sensing compared to state-of-the-art methods.
APoT quantization improves neural network efficiency and accuracy.
problem Efficiently quantizing weights and activations in neural networks.
method Constraining quantization levels as sums of Powers-of-Two terms, applying reparameterization, and weight normalization.
result 4-bit quantized ResNet-50 achieves 76.6% top-1 accuracy, 22% computational cost reduction.
The paper analyzes how quantization affects the Fisher Information Matrix's dominant eigenvalue.
problem The impact of quantization on the Fisher Information Matrix's dominant eigenvalue.
method The study examines spectral perturbation of the empirical Fisher Information Matrix under in-distribution input and quantized parameter perturbations.
result A bound on the eigenvalue under quantization noise, showing it strictly exceeds the unperturbed value at leading order.
New protocols show 1-bit mean estimation can be order-optimal without interaction.
problem Can 1-bit mean estimation be optimal without interaction?
method Adaptive and non-adaptive threshold and interval queries, with one adaptive transition.
result Arbitrary non-adaptive quantizers can match the adaptive rate, suggesting interaction is not necessary.
Deep learning models have been successfully used in computer vision and many other fields. We propose an unorthodox algorithm for performing quantization of the model parameters. In contrast with popular quantization schemes based on thresholds, we use a novel technique based on periodic functions, such as continuous t…
A new method for unsupervised disentanglement using axis-aligned cliffs.
problem Unsupervised disentanglement of latent factors under nonlinear maps.
method Encouraging axis-aligned discontinuities (cliffs) in the estimated density of factors.
result Cliff method outperforms baselines on disentanglement benchmarks.
The paper proposes a nonparametric test for incomplete samples quantized to B bits.
problem Statistical inference with lossy or incomplete samples.
method Nonparametric testing procedure based on B-bit quantized samples.
result The proposed test achieves the classical minimax rate of testing for spline models when B exceeds a threshold.
Differentially quantized gradient methods improve convergence in noisy communication channels.
problem Optimizing distributed learning with limited communication bandwidth and noise.
method Introduces Differential Quantization (DQ) to compensate for quantization errors in gradient descent.
result DQ-GD achieves the same contraction factor as unquantized GD at high bitrates, proving asymptotic optimality.
Binary Iterative Hard Thresholding converges with optimal number of 1-bit measurements.
problem Recovering sparse signals from 1-bit compressed measurements.
method Binary Iterative Hard Thresholding (BIHT) algorithm.
result BIHT converges with only O(k/ε) measurements, optimal for recovery.
This work optimizes quantization of linear models to reduce memory usage.
problem Optimizing memory usage for high-dimensional linear models.
method Information-theoretic framework with randomized embedding-based algorithms.
result Matching upper and lower bounds for minimax risk under quantization constraints.
Modern scientific instruments produce vast amounts of data, which can overwhelm the processing ability of computer systems. Lossy compression of data is an intriguing solution, but comes with its own drawbacks, such as potential signal loss, and the need for careful optimization of the compression ratio. In this work, …
Proposes a simple neural network model similar to gradient boosted decision trees.
problem Building a neural network equivalent to gradient boosted decision trees.
method Converts an ensemble of decision trees to a neural network, relaxes properties, and trains a simple neural network model.
result The proposed Hammock model achieves similar performance to gradient boosted decision trees.
In the past years, Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such powerful algorithm in the low power and resource-limited mobile systems. As the c…
New approach finds analytic interpretation of algebraic invariants for balanced metrics.
problem Finding analytic interpretation of algebraic invariants for balanced metrics.
method Using log canonical thresholds and basis divisors, the approach involves quantized Ding functionals on Bergman spaces.
result Each δ_m is the coercivity threshold of a quantized Ding functional on the m-th Bergman space, characterizing the existence of balanced metrics.
Study on hyperbolic elastic flow, proving convergence and quantifying singularities.
problem Understanding singularities and convergence of elastic flow in hyperbolic plane.
method Analyzes closed and open curves with clamped boundary conditions, proving convergence without small energy assumption.
result Each singularity carries an energy cost of at least 8, and blow-ups are explicitly classified.
This paper improves federated learning efficiency by auto-tuning secure aggregation parameters.
problem Efficient communication in federated learning with quantized updates.
method Auto-tuning secure aggregation parameters based on random rotation properties.
result Improved communication efficiency in federated learning with secure aggregation.
One-bit clustering method for two-component sub-Gaussian mixture models
problem Clustering in sub-Gaussian mixture models
method One-bit clustering using dithered quantization
result Decaying misclassification rate with exponential signal-to-noise ratio
This letter presents the sparse vector signal detection from one bit compressed sensing measurements, in contrast to the previous works which deal with scalar signal detection. In this letter, available results are extended to the vector case and the GLRT detector and the optimal quantizer design are obtained. Also, a …
Study on hemisphere threshold for Escobar functional on Riemannian manifolds, revealing mass and boundary invariant behaviors.
problem Analyzing the hemisphere threshold for the Escobar functional on compact Riemannian manifolds.
method Near-threshold landscape organization by boundary invariants, exact evaluation of weighted profile moments, Lyapunov-Schmidt correction, and blow-up analysis.
result At threshold, blow-ups concentrate at umbilic points with vanishing mass and gradient, leading to compactness and hemispherical rigidity.
RFX accelerates and compresses Random Forests for large datasets.
problem Memory bottleneck in proximity matrices limits Random Forest analysis.
method QLORA compression, CPU TriBlock storage, GPU batch sizing, 3D MDS visualization.
result Proximity-based Random Forest analysis on larger datasets is feasible.
Survey on quantization methods on Kähler manifolds.
problem None explicitly stated; focuses on methods.
method Deformation quantization, geometric quantization, Berezin-Toeplitz quantization, BV quantization.
result New relationships among quantization methods on Kähler manifolds.
Paper analyzes BIHT for noisy 1-bit CS, improving results with up to τ-fraction of incorrect measurements.
problem Estimating sparse vectors from noisy sign measurements in 1-bit compressed sensing.
method Binary Iterative Hard Thresholding (BIHT) algorithm, using Gaussian matrices and high-dimensional geometry analysis.
result BIHT provides estimates within ε+τ error with τ-fraction of incorrect measurements, maintaining universality of measurements.
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.
Consider the recovery of an unknown signal x from quantized linear measurements. In the one-bit compressive sensing setting, one typically assumes that x is sparse, and that the measurements are of the form sign(⟨ai,x⟩)∈{±1}. Since such measurements give no informati…
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.
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.
RATQ is a new quantizer for optimizing noisy gradients in machine learning.
problem Optimizing noisy gradients in stochastic optimization.
method RATQ uses Hadamard transform and adaptive uniform quantization, and achieves near-optimal performance.
result RATQ nearly achieves information theoretic lower bounds for optimization accuracy.
Extends ONNX for quantized neural networks with new formats and operators.
problem Handling arbitrary-precision quantization in neural networks.
method Introduces new formats and operators in ONNX to represent quantized neural networks.
result Enabled representation of uniform quantization in neural networks.
New method for quantizing symplectic manifolds with Lagrangian bundles.
problem Quantization of symplectic manifolds with Lagrangian bundles.
method A new construction of strict deformation quantization.
result Established a correspondence between differential operators and principal symbols.
Introduces sheaf quantization, a topological approach to geometric quantization.
problem Topological realization of WKB-states in geometric quantization.
method Enhancement of constructible sheaves, Betti counterpart of Fukaya--Floer theory.
result Introduction to sheaf quantization as a topological realization of WKB-states.
Network quantization is an effective solution to compress deep neural networks for practical usage. Existing network quantization methods cannot sufficiently exploit the depth information to generate low-bit compressed network. In this paper, we propose two novel network quantization approaches, single-level network qu…
The article defines and compares two types of quantizations on compact manifolds.
problem Quantization on arbitrary compact smooth manifolds.
method Embedding into CP^n and inducing quantizations from there.
result Generalizations of earlier quantization methods.
Quantized Adam reduces communication cost in deep learning training.
problem Reducing communication cost in distributed deep learning training.
method Gradient and weight quantization with error feedback in Adam.
result Proposed methods converge to first-order stationary points.
Proposes a robust neural network quantization method.
problem Training model's dependency on specific quantization methods.
method Intrinsic robustness to various quantization processes.
result Single model capable of operating at various bit-widths and policies.
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.
Quantizes neural networks using frame theory for improved accuracy.
problem Improving neural network efficiency and accuracy through quantization.
method Sigma-Delta (ΣΔ) quantization with finite unit-norm tight frames. result Error bound between original and quantized neural networks derived.
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.
Abstract proposes a new categorical approach to quantization of Poisson algebras.
problem Quantization of Poisson algebras.
method Defining quantization categories as subcategories of R-module categories with classical limits.
result Categories of strict deformation quantization, prequantization, and matrix regularization are equivalent, while Poisson enveloping algebra is not.
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.
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.
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.
We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision post-training produces classification accuracies within 2% of floating point networks…