261 citations · 359 across the 25 of their papers we have counts for
28 papers
Frequency-Aware Self-Supervised Music Representation Learning
Yicheng Gu, Junan Zhang, Jerry Li +2
Self-supervised learning (SSL) has emerged as an essential paradigm for music information retrieval (MIR). While current SSL models achieve state-of-the-art performance across vari…
Aliasing-Free Neural Audio Synthesis
Yicheng Gu, Junan Zhang, Chaoren Wang +3
In neural audio synthesis, neural vocoders and codecs are models that reconstruct waveforms from acoustic and latent representations, which are essential to the resulting audio qua…
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…
Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
Tiancheng Xing, Jerry Li, Yixuan Du +1
Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose th…
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…
Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection
Jerry Li, Evangelos Papalexakis
Large Language Models (LLMs) have demonstrated effectiveness across a wide variety of tasks involving natural language, however, a fundamental problem of hallucinations still plagu…
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
Scott Geng, Hamish Ivison, Chun-Liang Li +4
Improvements in language models are often driven by improving the quality of the data we train them on, which can be limiting when strong supervision is scarce. In this work, we sh…
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…
Predicting quantum channels over general product distributions
Sitan Chen, Jaume de Dios Pont, Jun-Ting Hsieh +3
We investigate the problem of predicting the output behavior of unknown quantum channels. Given query access to an -qubit channel and an observable , we aim to learn the…
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…
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…
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…
The Full Landscape of Robust Mean Testing: Sharp Separations between Oblivious and Adaptive Contamination
Clément L. Canonne, Samuel B. Hopkins, Jerry Li +2
We consider the question of Gaussian mean testing, a fundamental task in high-dimensional distribution testing and signal processing, subject to adversarial corruptions of the samp…
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…
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…
When Does Adaptivity Help for Quantum State Learning?
Sitan Chen, Brice Huang, Jerry Li +2
We consider the classic question of state tomography: given copies of an unknown quantum state , output which is close to in some sense,…
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:…
Tight Bounds for Quantum State Certification with Incoherent Measurements
Sitan Chen, Brice Huang, Jerry Li +1
We consider the problem of quantum state certification, where we are given the description of a mixed state , copies of a mixed state $ρ\in \mathb…
Semi-Random Sparse Recovery in Nearly-Linear Time
Jonathan A. Kelner, Jerry Li, Allen Liu +2
Sparse recovery is one of the most fundamental and well-studied inverse problems. Standard statistical formulations of the problem are provably solved by general convex programming…
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…
Robust Model Selection and Nearly-Proper Learning for GMMs
Jerry Li, Allen Liu, Ankur Moitra
In learning theory, a standard assumption is that the data is generated from a finite mixture model. But what happens when the number of components is not known in advance? The pro…