A scalable approach to learning from probability measures using quantization.
problem Efficiently comparing and manipulating large sets of probability measures.
method Quantization of probability measures to a fixed support, followed by optimal transport computations.
result Consistency and convergence guarantees for quantized measures in various OT-based tasks.
A new method quantizes conditional probability measures using deep learning.
problem Quantizing conditional probability measures efficiently.
method DCMQ method using Huber-energy kernel and deep neural network.
result Promising results on various examples.
Optimal quantization of measures on Carnot groups
problem Quantization of probability measures on Carnot groups
method Zador-type asymptotic formula and weak convergence of empirical measures
result Convergence of quantization error and density of absolutely continuous part
Algorithm finds best Dirac mass approximation of target measure.
problem Finding optimal Dirac mass approximation of target measure.
method Minimizes statistical distance between original measure and quantized version using Huber-energy kernel.
result HEMQ algorithm robust and versatile, matches intuitive behavior.
Sharp estimates for Bergman metrics derived from Kähler quantization.
problem Estimating Bergman metrics in Kähler quantization.
method Upper and lower bounds on the Bergman metric expressed in terms of φ. result Optimal C1,1ˉ-convergence for quantization of Kähler currents. Higher-order tensors can represent scores in a rating system, frames in a video, and images of the same subject. In practice, the measurements are often highly quantized due to the sampling strategies or the quality of devices. Existing works on tensor recovery have focused on data losses and random noises. Only a few …
New approach to geometric quantization for symplectic manifolds.
problem Quantization of symplectic manifolds with non-singular Lagrangian fibrations.
method Using spectral convergence of metric measure spaces, the authors develop a new geometric quantization approach.
result Spectral and quantum Hilbert space convergence results for Kähler and almost Kähler quantizations.
Study shows simple vector quantization measures correlate with deep learning generalization.
problem Understanding and predicting generalization in deep learning models.
method Applying complexity measures from approximation and information theory to deep learning features.
result Simple vector quantization measures correlate well with generalization performance in deep learning.
The paper improves quantization error estimates on Riemannian manifolds.
problem Improving quantization error estimates on Riemannian manifolds.
method Using covering growth estimates of spheres instead of curvature bounds.
result Provides a more general integral condition for quantization error.
In recent years Deep Neural Networks (DNNs) have been rapidly developed in various applications, together with increasingly complex architectures. The performance gain of these DNNs generally comes with high computational costs and large memory consumption, which may not be affordable for mobile platforms. Deep model q…
Quantizes semipositive line bundles on complex manifolds.
problem Quantize semipositive line bundles without ample representatives.
method Use adjoint Bergman kernels and non-pluripolar Monge-Ampère measures.
result Quantized energy converges to Monge-Ampère energy in semipositive setting.
A practical algorithm improves approximate OT distances using quantization.
problem Substantial computational burden in computing OT distances for large samples.
method Introduces a quantization step to estimate OT distances between measures.
result The quantization step improves the performance of approximate solvers for entropy-regularized transport.
We address the problem of phase retrieval (PR) from quantized measurements. The goal is to reconstruct a signal from quadratic measurements encoded with a finite precision, which is indeed the case in many practical applications. We develop a rank-1 projection algorithm that recovers the signal subject to ensuring cons…
To measure the quality of a set of vector quantization points a means of measuring the distance between a random point and its quantization is required. Common metrics such as the {\em Hamming} and {\em Euclidean} metrics, while mathematically simple, are inappropriate for comparing natural signals such as speech or im…
The paper defines and analyzes coherent and squeezed states on manifolds and their quantization.
problem Defining and characterizing coherent and squeezed states on various manifolds.
method Definition and analysis of Rawnsley-type coherent and squeezed states, Berezin quantization.
result Properties and quantization of coherent and squeezed states on manifolds.
Estimates and quantizes expected persistence diagrams for efficient analysis.
problem Statistical summary of the topology of structured data.
method Expected Persistence Diagram (EPD) and its quantization.
result Optimal estimation of EPD with near-optimal quantization.
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…
This paper addresses a challenging problem - how to reduce energy consumption without incurring performance drop when deploying deep neural networks (DNNs) at the inference stage. In order to alleviate the computation and storage burdens, we propose a novel dataflow-based joint quantization approach with the hypothesis…
This paper deals with two related problems, namely distance-preserving binary embeddings and quantization for compressed sensing . First, we propose fast methods to replace points from a subset X⊂Rn, associated with the Euclidean metric, with points in the cube {±1}m and we associa…
This paper develops efficient bounds on the Wasserstein metric for discrete measures.
problem Computing the exact Wasserstein metric is computationally expensive.
method Formulates and solves a Kantorovich problem on a coarse grid using quantized measures and cost matrices, followed by upscaling and correction.
result Achieves a 10x-100x speedup while maintaining low approximation error.
Quantization on even-dimensional compact manifolds using cell decomposition.
problem Quantization of compact even-dimensional manifolds.
method Cell decomposition and embedding in CP^d, inducing local Poisson structure and star product.
result Achieved Berezin-type quantization on compact even-dimensional manifolds.
New algorithm recovers sparse binary vectors from generalized linear measurements efficiently.
problem Recovering sparse binary vectors from generalized linear measurements.
method Linear estimation algorithm and information theoretic lower bounds.
result Optimal sample complexity of O((k+σ2)logn) for noisy one bit quantized linear measurements. 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.
FP6 quantization outperforms INT4 in diverse generative tasks for LLMs.
problem Limited performance of 4-bit quantization methods in diverse generative tasks.
method Proposes a 4+2 design for FP6 quantization to achieve similar latency to INT4.
result FP6 quantization outperforms INT4 in various generative tasks, including code generation and summarization.
This paper improves support recovery in universal one-bit compressed sensing with fewer measurements.
problem Support recovery in universal one-bit compressed sensing.
method Developed algorithms to recover the support of sparse signals with a small number of false positives.
result Support recovery with ildeO(k3/2) measurements, improving to ildeO(k) with known dynamic range. Power spectral density (PSD) maps providing the distribution of RF power across space and frequency are constructed using power measurements collected by a network of low-cost sensors. By introducing linear compression and quantization to a small number of bits, sensor measurements can be communicated to the fusion cen…
Improved Heston model produces steeper smile for short maturities.
problem Implied volatility surface does not produce a steep enough smile for short maturities.
method Introduced Stationary Heston model with invariant measure and used Product Recursive Quantization for numerical solution.
result Stationary Heston model produces a steeper smile for short maturities.
The paper quantizes concatenated noisy vectors to a common cluster center, improving performance over naive methods.
problem Clustering concatenated noisy vectors from multiple sources.
method Asymptotic analysis of weighted sum of distances to a common cluster center.
result The clustering approach outperforms naive methods in terms of average distortion.
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.
New algorithm improves clustering and quantization using MMD.
problem Approximating probability distributions with weighted mixtures of Dirac measures.
method Gradient flow, mean shift, and MMD-optimal quantization.
result MSIP algorithm is more robust than state-of-the-art methods.
In this work, we propose to quantize all parts of standard classification networks and replace the activation-weight--multiply step with a simple table-based lookup. This approach results in networks that are free of floating-point operations and free of multiplications, suitable for direct FPGA and ASIC implementation…
This paper gives a rigorous interpretation of a Feynman path integral on a Riemannian manifold M with non-positive sectional curvature. A L2 Riemannian metric GP is given on the space of piecewise geodesic paths HP(M) adapted to the partition P of [0,1], whence a finite-dimensional approximation of Wiener …
Study quantizes ropelength and writhe of 12-crossing knots.
problem Quantifying geometric and topological properties of knots.
method Computation of ropelength and space writhe for 12-crossing knots.
result Non-alternating knots show evidence of writhe quantization, while alternating knots do.
We present DeepFPC, a novel deep neural network designed by unfolding the iterations of the fixed-point continuation algorithm with one-sided l1-norm (FPC-l1), which has been proposed for solving the 1-bit compressed sensing problem. The network architecture resembles that of deep residual learning and incorporates pri…
This paper provides a methodology for fast and accurate pricing of the long-dated contracts that arise as the building blocks of insurance and pension fund agreements. It applies the recursive marginal quantization (RMQ) and joint recursive marginal quantization (JRMQ) algorithms outside the framework of traditional ri…
Galen algorithm compresses neural networks for specific hardware with reduced latency.
problem Finding optimal compression policies for neural networks on specific hardware.
method Reinforcement learning using pruning and quantization to optimize inference latency.
result Compressed ResNet18 for ARM processor reduced inference latency by 80%.
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…
EQ-Net combines LLR estimation and quantization using deep learning.
problem Unified solution for LLR estimation and quantization.
method Two-stage algorithm using LLR compression as a pretext task.
result Achieves state-of-the-art results with gains in efficiency and latency.
New tools quantify deep generative models' performance.
problem Measuring the quality-diversity trade-off in deep generative models.
method Established non-asymptotic bounds on sample complexity and introduced frontier integrals.
result Smoothed estimators improve convergence rates of divergence frontiers.
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.
A method for vectorizing persistence diagrams simplifies topological data analysis.
problem Challenges in integrating persistence diagrams into machine learning pipelines.
method Quantized Persistence and Integral transforms of Diagrams (Qupid) using binning and discrete transforms.
result Qupid preserves highly competitive performances compared to state-of-the-art methods across various classification tasks.
Optimal quantization improves dataset distillation for faster training.
problem Efficiently train models with synthetic data.
method Reformulate disentangled methods as optimal quantization problems.
result Better performance and generalization on ImageNet-1K and subsets.
For Ginzburg-Landau vortices, energy quantization holds only when density is less than 2.
problem Energy quantization in Ginzburg-Landau vortices for higher dimensions.
method Analyzing normalized energy measures and vorticity sets.
result Energy quantization only holds when density is less than 2.
We propose and study a multi-scale approach to vector quantization. We develop an algorithm, dubbed reconstruction trees, inspired by decision trees. Here the objective is parsimonious reconstruction of unsupervised data, rather than classification. Contrasted to more standard vector quantization methods, such as K-mea…
In this paper, we introduce a novel and robust approach to Quantized Matrix Completion (QMC). First, we propose a rank minimization problem with constraints induced by quantization bounds. Next, we form an unconstrained optimization problem by regularizing the rank function with Huber loss. Huber loss is leveraged to c…
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.
Improves naturalness in TTS samples using quantized VAE and auto-regressive prosody.
problem Discontinuous and unnatural speech from standard VAE priors.
method Discretized latent features using vector quantization (VQ), and separately trained autoregressive (AR) prior model.
result Significantly improves naturalness in random sample generation.
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.