261 citations · 359 across the 25 of their papers we have counts for
13 papers · 1 filter
Optimal Inference Schedules for Masked Diffusion Models
Sitan Chen, Kevin Cong, Jerry Li
A major bottleneck of standard auto-regressive large language models is that their inference process is inherently sequential, resulting in very long and costly inference times. To…
Robust Estimation Under Heterogeneous Corruption Rates
Syomantak Chaudhuri, Jerry Li, Thomas A. Courtade
We study the problem of robust estimation under heterogeneous corruption rates, where each sample may be independently corrupted with a known but non-identical probability. This se…
S4S: Solving for a Diffusion Model Solver
Eric Frankel, Sitan Chen, Jerry Li +3
Diffusion models (DMs) create samples from a data distribution by starting from random noise and iteratively solving a reverse-time ordinary differential equation (ODE). Because ea…
KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval
Marah I Abdin, Suriya Gunasekar, Varun Chandrasekaran +5
We study the ability of state-of-the art models to answer constraint satisfaction queries for information retrieval (e.g., 'a list of ice cream shops in San Diego'). In the past, s…
Matrix Completion in Almost-Verification Time
Jonathan A. Kelner, Jerry Li, Allen Liu +2
We give a new framework for solving the fundamental problem of low-rank matrix completion, i.e., approximating a rank- matrix (where $m…
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…
Learning (Very) Simple Generative Models Is Hard
Sitan Chen, Jerry Li, Yuanzhi Li
Motivated by the recent empirical successes of deep generative models, we study the computational complexity of the following unsupervised learning problem. For an unknown neural n…
Learning Polynomial Transformations
Sitan Chen, Jerry Li, Yuanzhi Li +1
We consider the problem of learning high dimensional polynomial transformations of Gaussians. Given samples of the form , where is hidden and $p:…
Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs
Sitan Chen, Jerry Li, Yuanzhi Li +1
Arguably the most fundamental question in the theory of generative adversarial networks (GANs) is to understand to what extent GANs can actually learn the underlying distribution.…
On Distinctive Properties of Universal Perturbations
Sung Min Park, Kuo-An Wei, Kai Xiao +2
We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations. Specifically, we show that targeted UAPs generat…
Learning Structured Distributions From Untrusted Batches: Faster and Simpler
Sitan Chen, Jerry Li, Ankur Moitra
We revisit the problem of learning from untrusted batches introduced by Qiao and Valiant [QV17]. Recently, Jain and Orlitsky [JO19] gave a simple semidefinite programming approach…
Randomized Smoothing of All Shapes and Sizes
Greg Yang, Tony Duan, J. Edward Hu +3
Randomized smoothing is the current state-of-the-art defense with provable robustness against adversarial attacks. Many works have devised new randomized smoothing schemes…
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Hadi Salman, Greg Yang, Jerry Li +4
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to -norm ad…