research
∙
09/04/2023
Memory Efficient Optimizers with 4-bit States
Optimizer states are a major source of memory consumption for training n...
share
research
∙
06/21/2023
Training Transformers with 4-bit Integers
Quantizing the activation, weight, and gradient to 4-bit is promising to...
research
∙
06/18/2023
Stabilizing GANs' Training with Brownian Motion Controller
The training process of generative adversarial networks (GANs) is unstab...
research
∙
05/30/2023
Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
Large pre-trained language models (PLMs) have demonstrated strong perfor...
research
∙
05/06/2023
Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
Diffusion models have exhibited excellent performance in various domains...
research
∙
04/25/2023
Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning
Guided sampling is a vital approach for applying diffusion models in rea...
research
∙
11/02/2022
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
Diffusion probabilistic models (DPMs) have achieved impressive success i...
research
∙
06/22/2022
GACT: Activation Compressed Training for General Architectures
Training large neural network (NN) models requires extensive memory reso...
research
∙
06/17/2022
Fast Lossless Neural Compression with Integer-Only Discrete Flows
By applying entropy codecs with learned data distributions, neural compr...
research
∙
06/16/2022
Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matching
Score-based generative models have excellent performance in terms of gen...
research
∙
06/02/2022
DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
Diffusion probabilistic models (DPMs) are emerging powerful generative m...
research
∙
04/30/2022
Deep Ensemble as a Gaussian Process Approximate Posterior
Deep Ensemble (DE) is an effective alternative to Bayesian neural networ...
research
∙
04/29/2021
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
The increasing size of neural network models has been critical for impro...
research
∙
03/17/2021
Implicit Normalizing Flows
Normalizing flows define a probability distribution by an explicit inver...
research
∙
11/21/2020
BARS: Joint Search of Cell Topology and Layout for Accurate and Efficient Binary ARchitectures
Binary Neural Networks (BNNs) have received significant attention due to...
research
∙
10/27/2020
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
Fully quantized training (FQT), which uses low-bitwidth hardware by quan...
research
∙
06/19/2020
BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud
Bird's-eye-view (BEV) is a powerful and widely adopted representation fo...
research
∙
02/22/2020
VFlow: More Expressive Generative Flows with Variational Data Augmentation
Generative flows are promising tractable models for density modeling tha...
research
∙
04/10/2018
Towards Training Probabilistic Topic Models on Neuromorphic Multi-chip Systems
Probabilistic topic models are popular unsupervised learning methods, in...
research
∙
10/29/2017
Stochastic Training of Graph Convolutional Networks
Graph convolutional networks (GCNs) are powerful deep neural networks fo...
research
∙
09/18/2017
ZhuSuan: A Library for Bayesian Deep Learning
In this paper we introduce ZhuSuan, a python probabilistic programming l...
research
∙
02/23/2017
Scalable Inference for Nested Chinese Restaurant Process Topic Models
Nested Chinese Restaurant Process (nCRP) topic models are powerful nonpa...
research
∙
10/08/2016
SaberLDA: Sparsity-Aware Learning of Topic Models on GPUs
Latent Dirichlet Allocation (LDA) is a popular tool for analyzing discre...
research
∙
02/19/2016
Scaling up Dynamic Topic Models
Dynamic topic models (DTMs) are very effective in discovering topics and...
research
∙
01/06/2016
Streaming Gibbs Sampling for LDA Model
Streaming variational Bayes (SVB) is successful in learning LDA models i...
research
∙
10/29/2015
WarpLDA: a Cache Efficient O(1) Algorithm for Latent Dirichlet Allocation
Developing efficient and scalable algorithms for Latent Dirichlet Alloca...
research
∙
11/24/2014