Holden Lee
26 papers · 2017–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (37) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Keyword Champion
(4)
π
Triple Crown
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(120)
Top co-authors
Research topics
Machine Learning
(25)
Optimization & Theory Β· Machine Learning
(22)
Deep Learning
(11)
Mathematics & Optimization
(11)
Core Methods
(10)
Models
(9)
Optimization
(8)
Artificial Intelligence
(6)
Bayesian & Probabilistic Β· Machine Learning
(4)
Optimization & Theory Β· Deep Learning
(4)
Core AI
(3)
Mathematics
(3)
Bayesian & Probabilistic Β· Artificial Intelligence
(2)
Natural Language Processing
(1)
Architectures
(1)
Keywords
linear dynamical system
(4)
score-based generative modeling
(4)
markov chain monte carlo
(3)
convergence guarantee
(3)
diffusion model
(3)
markov chain
(3)
score function
(3)
langevin diffusion
(2)
language model
(2)
langevin monte carlo
(2)
generative model
(2)
statistical efficiency
(2)
variational inference
(2)
bayesian inference
(2)
probability distribution
(2)
wasserstein distance
(2)
system identification
(2)
score estimation
(2)
multimodal distribution
(2)
autoregressive filter
(2)
Papers
Efficiently learning and sampling multimodal distributions with data-based initialization
COLT 2025
Learning Mixtures of Gaussians Using Diffusion Models
COLT 2025
How Flawed Is ECE? An Analysis via Logit Smoothing
ICML 2024
Principled Gradient-Based MCMC for Conditional Sampling of Text
ICML 2024
What does guidance do? A fine-grained analysis in a simple setting
NeurIPS 2024
When is a Language Process a Language Model?
ACL 2024
Connecting Pre-trained Language Model and Downstream Task via Properties of Representation
NeurIPS 2023
Convergence of score-based generative modeling for general data distributions
ALT 2023
Fisher information lower bounds for sampling
ALT 2023
Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions
ICML 2023
Pitfalls of Gaussians as a noise distribution in NCE
ICLR 2023
Provable benefits of score matching
NeurIPS 2023
The probability flow ODE is provably fast
NeurIPS 2023
Convergence for score-based generative modeling with polynomial complexity
NeurIPS 2022
Extracting Latent State Representations with Linear Dynamics from Rich Observations
ICML 2022
Improved rates for prediction and identification of partially observed linear dynamical systems
ALT 2022
Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods
COLT 2022
Efficient sampling from the Bingham distribution
ALT 2021
Universal Approximation Using Well-Conditioned Normalizing Flows
NeurIPS 2021
No-Regret Prediction in Marginally Stable Systems
COLT 2020
Robust guarantees for learning an autoregressive filter
ALT 2020
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
NeurIPS 2019
Online sampling from log-concave distributions
NeurIPS 2019
Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo
NeurIPS 2018
Spectral Filtering for General Linear Dynamical Systems
NeurIPS 2018
On the Ability of Neural Nets to Express Distributions
COLT 2017