tags

ADDA AEC AIMET Activation-aware Weight Quantization (AWQ) AdaRound Adaboost Adaptation Adaptive Filters Angular softmax loss Art Asymmetric Quantization Batch Normalization Bayes Filter Bayesian Learning Bayesian Network Bayesian Optimization Brownian Motion CGMM CNN CTC CUDA CV Candidate sampling Characteristic Exponent Computational Graph Concrete distribution Conditional Entropy Conditional Random Field Conjugate Prior Continuity Equation Continuous Normalizing Flow (CNF) Correlation matrix Counting Process Coursera Covariance matrix Cross Entropy DARTS DKM Data Free Quantization (DFQ) Deep Learning Denoising Diffusion Probabilistic Models Denoising Score Matching Diffusion Model Distributed Data Parallel (DDP) Divergence ELBO EWGS Embedding Entropy Ergodic Markov Chains Ergodicity Euler Method Expectation Maximization Extended Kalman Filter Factor Analysis Fake Quantization Fisher Divergence Fisher Information Matrix Flow Matching Fokker-Planck Equation Frost GAN GPTQ GRU Gauss Divergence Theorem Gaussian Process Gaussian Vector Generative Model Gibbs Sampling Gradient Boost Gradient Descent Gradient Norm Penalty Gumbel distribution Gumbel max sampling Gumbel max trick HMC Hamiltonian Dynamic Hamiltonian Monte Carlo Hard Concrete distribution Hessian Hessian Vector Product (HVP) Hung-yi Lee Itô formula Jacobian Jacobian Vector Product (JVP) KKT Kaldi Kalman Filter L0 regularization LCMV LMS LSQ LSQ+ Langevin Dynamics Langevin Monte Carlo Linear Quantization LoRA LoRAPrune Localization Lévy Processes MAP MCMC MCRA ML MLE MMSE-LSA MMSE-STSA MSNR MVDR MWF Markov Chain Markov Chains Markov Localization Markov Network Maximum Mutual Information Metropolis Hastings Model Predictive Control Modified Euler Method Modified softmax loss Motion Model Movement pruning Multi-trail NAS Mutual Information N2UQ NCE NLMS NVIDIA Neural Architecture Search (NAS) Noise Contrastive Estimation Nonlinear Constraint Optimization Nonlinear Quantization OCTAV ODE OLA OLS OMLSA Observer One-shot NAS Optimal Brain Quantization (OBQ) Ordinary Differential Equations PACT PEFT POS tagging Poisson Process Post Training Quantization (PTQ) Probabilistic Graphical Models Probability Space Probably Approximately Correct (PAC) Pruning PyTorch Quantization Aware Training (QAT) Quantization Error ROS Re-parameterization trick Renewal Process Runge Kutta Methods SAM SGD SWA Sampled softmax loss Scale Invariant Function Score Function Score Matching Sharpness-Aware Minimization Sliced Score Matching SmoothQuant Spatial Spectral Density Speculative Decoding Speculative Sampling Speech Recognition SphereFace Spherical Linear Interpolation (Slerp) Stationary Stochastic Continuity Stochastic Convergences Stochastic Gradient Descent Stochastic Integration Stochastic Processes Stochastic Weight Averaging Straight Through Estimator (STE) Structure Perceptron Structure SVM Symmetric Quantization TensorFlow Transformer Udacity Unscented Kalman Filter VAE-GAN Variational Auto Encoder (VAE) Variational Inference Vector Jacobian Product (VJP) WGAN Weight Normalization Weight Only Quantization (WOQ) Wide-Sense Stationary adaboost aggregation anechoic model array manifold vector