Sitan Chen
25 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Academic Marathon (5) π Conference Polyglot (4) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (8)
π
Cross-Pollinator
(8)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(29)
π
Keyword Champion
(2)
π
Triple Crown
π₯
Unstoppable
(6)
β
The Questioner
π
Century Club
(25)
ποΈ
Keyword Collector
(73)
β‘
Prolific Year
(7)
Conferences
NIPS (9)
COLT (7)
ICML (5)
ICLR (4)
Top co-authors
Keywords
neural network
(4)
diffusion model
(3)
relu network
(3)
pac learning
(2)
relu activation
(2)
score estimation
(2)
distribution learning
(2)
denoising diffusion
(2)
generative model
(2)
probabilistic modeling
(1)
theoretical analysis
(1)
computational complexity
(1)
gaussian process
(1)
gradient descent
(1)
feature learning
(1)
dimensionality reduction
(1)
neural network learning
(1)
knowledge distillation
(1)
compressed sensing
(1)
hidden layer
(1)
Papers
Blink of an eye: a simple theory for feature localization in generative models
ICML 2025
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
ICML 2025
Predicting quantum channels over general product distributions
COLT 2025
S4S: Solving for a Fast Diffusion Model Solver
ICML 2025
Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
ICLR 2025
Low-rank fine-tuning lies between lazy training and feature learning
COLT 2025
Learning general Gaussian mixtures with efficient score matching
COLT 2025
A faster and simpler algorithm for learning shallow networks
COLT 2024
What does guidance do? A fine-grained analysis in a simple setting
NIPS 2024
Unrolled denoising networks provably learn to perform optimal Bayesian inference
NIPS 2024
Critical windows: non-asymptotic theory for feature emergence in diffusion models
ICML 2024
Learning Narrow One-Hidden-Layer ReLU Networks
COLT 2023
The probability flow ODE is provably fast
NIPS 2023
Learning Mixtures of Gaussians Using the DDPM Objective
NIPS 2023
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
ICLR 2023
Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-type Samplers
ICML 2023
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks
NIPS 2022
Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs
ICLR 2022
Learning (Very) Simple Generative Models Is Hard
NIPS 2022
Toward Instance-Optimal State Certification With Incoherent Measurements
COLT 2022
On InstaHide, Phase Retrieval, and Sparse Matrix Factorization
ICLR 2021
Efficiently Learning One Hidden Layer ReLU Networks From Queries
NIPS 2021
Learning Structured Distributions From Untrusted Batches: Faster and Simpler
NIPS 2020
Learning Polynomials in Few Relevant Dimensions
COLT 2020
Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability
NIPS 2020