544 citations · 653 across the 48 of their papers we have counts for
54 papers
Hierarchical Gaussian Processes for Survey Weighting: Local Equivalent Weights in Structured Populations
Seonghun Lee
Regression-based survey weighting connects model-based population estimation with design-based inference through equivalent weights. For nonlinear models, equivalent weights can be…
Finding Gaussian Structure in Bosonic States
Alvan Arulandu, Sitan Chen, Ziyun Chen +2
We study agnostic tomography of pure bosonic Gaussian states: given copies of an arbitrary -mode bosonic state , the goal is to output a pure Gaussian state whose infidelity…
Out-of-control Hamiltonian Learning
Weiyuan Gong, Muzhou Ma, Sitan Chen +2
Learning the Hamiltonian of a many-body system from its dynamics is a central task in quantum science, yet the algorithms with the strongest provable guarantees assume some level o…
Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems
Woosang Jeon, Jaeyeon Kim, Sham Kakade +6
Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on problems governed by complex global…
Online Shadow Tomography Matching the Classical Bounds
Sitan Chen, Ryan O'Donnell, Angelos Pelecanos +1
In Online Shadow Tomography, we are given copies of an unknown -dimensional quantum state , an adversary (adaptively) proposes a sequence of bounded observables $A^{(1)},\ldo…
Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
Jaeyeon Kim, Jonathan Geuter, David Alvarez-Melis +2
Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces. By generating sequences in any order and allowing for parallel decod…
A Provably Efficient Method for Tensor Ring Decomposition and Its Applications
Han Chen, Sitan Chen, Anru R. Zhang
We present the first deterministic, finite-step algorithm for exact tensor ring (TR) decomposition. Our method leverages blockwise simultaneous diagonalization to recover TR cores…
Fine-Tuning Masked Diffusion for Provable Self-Correction
Jaeyeon Kim, Seunggeun Kim, Taekyun Lee +4
A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Models (MDMs) have emerged as a promi…
Stabilizer bootstrapping: A recipe for efficient agnostic tomography and magic estimation
Sitan Chen, Weiyuan Gong, Qi Ye +1
We study the task of agnostic tomography: given copies of an unknown -qubit state which has fidelity with some state in a given class , find a state which has fidelit…
Optimal high-precision shadow estimation
Sitan Chen, Jerry Li, Allen Liu
We give the first tight sample complexity bounds for shadow tomography and classical shadows in the regime where the target error is below some sufficiently small inverse polynomia…
Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
Shivam Gupta, Linda Cai, Sitan Chen
Sampling algorithms play an important role in controlling the quality and runtime of diffusion model inference. In recent years, a number of works~\cite{chen2023sampling,chen2023od…
Optimal tradeoffs for estimating Pauli observables
Sitan Chen, Weiyuan Gong, Qi Ye
We revisit the problem of Pauli shadow tomography: given copies of an unknown -qubit quantum state , estimate for some set of Pauli operators to within ad…
Learning general Gaussian mixtures with efficient score matching
Sitan Chen, Vasilis Kontonis, Kulin Shah
We study the problem of learning mixtures of Gaussians in dimensions. We make no separation assumptions on the underlying mixture components: we only require that the covar…
Critical windows: non-asymptotic theory for feature emergence in diffusion models
Marvin Li, Sitan Chen
We develop theory to understand an intriguing property of diffusion models for image generation that we term critical windows. Empirically, it has been observed that there are narr…
An optimal tradeoff between entanglement and copy complexity for state tomography
Sitan Chen, Jerry Li, Allen Liu
There has been significant interest in understanding how practical constraints on contemporary quantum devices impact the complexity of quantum learning. For the classic question o…
Efficient Pauli channel estimation with logarithmic quantum memory
Sitan Chen, Weiyuan Gong
Here we revisit one of the prototypical tasks for characterizing the structure of noise in quantum devices: estimating every eigenvalue of an -qubit Pauli noise channel to error…
A faster and simpler algorithm for learning shallow networks
Sitan Chen, Shyam Narayanan
We revisit the well-studied problem of learning a linear combination of ReLU activations given labeled examples drawn from the standard -dimensional Gaussian measure. Chen e…
Learning Mixtures of Gaussians Using the DDPM Objective
Kulin Shah, Sitan Chen, Adam Klivans
Recent works have shown that diffusion models can learn essentially any distribution provided one can perform score estimation. Yet it remains poorly understood under what settings…
The probability flow ODE is provably fast
Sitan Chen, Sinho Chewi, Holden Lee +3
We provide the first polynomial-time convergence guarantees for the probability flow ODE implementation (together with a corrector step) of score-based generative modeling. Our ana…
Learning Narrow One-Hidden-Layer ReLU Networks
Sitan Chen, Zehao Dou, Surbhi Goel +2
We consider the well-studied problem of learning a linear combination of ReLU activations with respect to a Gaussian distribution on inputs in dimensions. We give the first…
Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers
Sitan Chen, Giannis Daras, Alexandros G. Dimakis
We develop a framework for non-asymptotic analysis of deterministic samplers used for diffusion generative modeling. Several recent works have analyzed stochastic samplers using to…
The Complexity of NISQ
Sitan Chen, Jordan Cotler, Hsin-Yuan Huang +1
The recent proliferation of NISQ devices has made it imperative to understand their computational power. In this work, we define and study the complexity class , wh…
Learning to predict arbitrary quantum processes
Hsin-Yuan Huang, Sitan Chen, John Preskill
We present an efficient machine learning (ML) algorithm for predicting any unknown quantum process over qubits. For a wide range of distributions on…
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
Sitan Chen, Sinho Chewi, Jerry Li +3
We provide theoretical convergence guarantees for score-based generative models (SGMs) such as denoising diffusion probabilistic models (DDPMs), which constitute the backbone of la…