Skip to content
conftrace_

Sitan Chen

27 papers · 2020–2026 · 4 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 ↓
+11 more ↓ πŸ—ΊοΈ Taxonomy Completionist (42) πŸƒ Academic Marathon Β· Sprint 🌍 Conference Polyglot Β· Bronze πŸŒ‰ Interdisciplinary Bridge Β· Gold 🐣 Hot Topic Early Bird
πŸ”¬ Deep Specialist (12) πŸ‘‘ Triple Crown 🧬 Topic Evolution πŸ† Keyword Champion (3) ⚑ Prolific Year Β· Productive πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (143) ❓ The Questioner πŸ”₯ Unstoppable Β· Bronze 🌈 Renaissance Researcher (6) πŸ’Ž Century Club Β· Bronze

Venues

COLT (9) NeurIPS (9) ICML (5) ICLR (4)

Top co-authors

Jerry Li (8) Raghu Meka (5) Kulin Shah (4) Adam Klivans (4) Yuanzhi Li (4) Vasilis Kontonis (2) Ankur Moitra (2) Adil SALIM (2) Marvin Li (2) Sinho Chewi (2)

Research topics

Machine Learning (25) Optimization & Theory (25) Deep Learning (18) Models (13) Core Methods (8) Mathematics & Optimization (7) Optimization (6) Artificial Intelligence (4) Architectures (3) Computer Science (2) Computer Vision (2) Interdisciplinary (2) Core AI (2) Foundations (2) Generation (2)

Keywords

diffusion model (8) neural network (4) relu activation (3) generative model (3) score estimation (3) relu network (3) distribution learning (3) critical windows (2) denoising diffusion (2) learning theory (2) autoregressive model (2) gaussian distribution (2) score matching (2) masked diffusion model (2) pac learning (2) unsupervised learning (2) neural network learning (2) phase retrieval (2) knowledge distillation (1) bayesian inference (1)

Papers

Information-computation gaps in quantum learning via low-degree likelihood COLT 2026 Optimal Inference Schedules for Masked Diffusion Models COLT 2026 Blink of an eye: a simple theory for feature localization in generative models ICML 2025 Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel ICLR 2025 Learning general Gaussian mixtures with efficient score matching COLT 2025 Low-rank fine-tuning lies between lazy training and feature learning COLT 2025 Predicting quantum channels over general product distributions COLT 2025 S4S: Solving for a Fast Diffusion Model Solver ICML 2025 Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions ICML 2025 A faster and simpler algorithm for learning shallow networks COLT 2024 Critical windows: non-asymptotic theory for feature emergence in diffusion models ICML 2024 Unrolled denoising networks provably learn to perform optimal Bayesian inference NeurIPS 2024 What does guidance do? A fine-grained analysis in a simple setting NeurIPS 2024 Learning Mixtures of Gaussians Using the DDPM Objective NeurIPS 2023 Learning Narrow One-Hidden-Layer ReLU Networks COLT 2023 Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-type Samplers ICML 2023 Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions ICLR 2023 The probability flow ODE is provably fast NeurIPS 2023 Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks NeurIPS 2022 Learning (Very) Simple Generative Models Is Hard NeurIPS 2022 Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs ICLR 2022 Toward Instance-Optimal State Certification With Incoherent Measurements COLT 2022 Efficiently Learning One Hidden Layer ReLU Networks From Queries NeurIPS 2021 On InstaHide, Phase Retrieval, and Sparse Matrix Factorization ICLR 2021 Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability NeurIPS 2020 Learning Polynomials in Few Relevant Dimensions COLT 2020 Learning Structured Distributions From Untrusted Batches: Faster and Simpler NeurIPS 2020