40 citations · 242 across the 20 of their papers we have counts for
14 papers · 1 filter
Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM Inference
Chi-Wei Huang, Chia-Chi Tsai
Two-bit weight quantization is attractive for memory-efficient LLM inference, but the standard W2 level set {-2,-1,0,+1} often collapses under aggressive W2A4/KV4 settings. We stud…
Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics
Marloes Arts, Victor Garcia Satorras, Chin-Wei Huang +6
Coarse-grained (CG) molecular dynamics enables the study of biological processes at temporal and spatial scales that would be intractable at an atomistic resolution. However, accur…
Riemannian Diffusion Models
Chin-Wei Huang, Milad Aghajohari, Avishek Joey Bose +2
Diffusion models are recent state-of-the-art methods for image generation and likelihood estimation. In this work, we generalize continuous-time diffusion models to arbitrary Riema…
A Variational Perspective on Diffusion-Based Generative Models and Score Matching
Chin-Wei Huang, Jae Hyun Lim, Aaron Courville
Discrete-time diffusion-based generative models and score matching methods have shown promising results in modeling high-dimensional image data. Recently, Song et al. (2021) show t…
Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
Chin-Wei Huang, Ricky T. Q. Chen, Christos Tsirigotis +1
Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient para…
RealCause: Realistic Causal Inference Benchmarking
Brady Neal, Chin-Wei Huang, Sunand Raghupathi
There are many different causal effect estimators in causal inference. However, it is unclear how to choose between these estimators because there is no ground-truth for causal eff…
AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation
Jae Hyun Lim, Aaron Courville, Christopher Pal +1
Entropy is ubiquitous in machine learning, but it is in general intractable to compute the entropy of the distribution of an arbitrary continuous random variable. In this paper, we…
Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
Chin-Wei Huang, Laurent Dinh, Aaron Courville
In this work, we propose a new family of generative flows on an augmented data space, with an aim to improve expressivity without drastically increasing the computational cost of s…
Note on the bias and variance of variational inference
Chin-Wei Huang, Aaron Courville
In this note, we study the relationship between the variational gap and the variance of the (log) likelihood ratio. We show that the gap can be upper bounded by some form of disper…
Stochastic Neural Network with Kronecker Flow
Chin-Wei Huang, Ahmed Touati, Pascal Vincent +3
Recent advances in variational inference enable the modelling of highly structured joint distributions, but are limited in their capacity to scale to the high-dimensional setting o…
Hierarchical Importance Weighted Autoencoders
Chin-Wei Huang, Kris Sankaran, Eeshan Dhekane +2
Importance weighted variational inference (Burda et al., 2015) uses multiple i.i.d. samples to have a tighter variational lower bound. We believe a joint proposal has the potential…
Improving Explorability in Variational Inference with Annealed Variational Objectives
Chin-Wei Huang, Shawn Tan, Alexandre Lacoste +1
Despite the advances in the representational capacity of approximate distributions for variational inference, the optimization process can still limit the density that is ultimatel…
Neural Autoregressive Flows
Chin-Wei Huang, David Krueger, Alexandre Lacoste +1
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to…
Learnable Explicit Density for Continuous Latent Space and Variational Inference
Chin-Wei Huang, Ahmed Touati, Laurent Dinh +4
In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior. First, we decompose the…