Holden Lee

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 53

Top Topics

Dynamical Systems

Partially Observed

Top Venues

Publications

Li Du, Holden Lee, Jason Eisner, Ryan Cotterell
When is a Language Process a Language Model? ACL (Findings) (2024)
Evan Camrud, Ewan Davies, Alex Karduna, Holden Lee
Sampling List Packings. CoRR (2024)
Holden Lee, Matheau Santana-Gijzen
Convergence Bounds for Sequential Monte Carlo on Multimodal Distributions using Soft Decomposition. CoRR (2024)
Holden Lee, Qiang Wu
Sampling from the Continuous Random Energy Model in Total Variation Distance. CoRR (2024)
Muthu Chidambaram, Holden Lee, Colin McSwiggen, Semon Rezchikov
How Flawed is ECE? An Analysis via Logit Smoothing. CoRR (2024)
Khashayar Gatmiry, Jonathan A. Kelner, Holden Lee
Learning Mixtures of Gaussians Using Diffusion Models. CoRR (2024)
Chenwei Wu, Holden Lee, Rong Ge
Connecting Pre-trained Language Model and Downstream Task via Properties of Representation. NeurIPS (2023)
Holden Lee, Zeyu Shen
Improved Bound for Mixing Time of Parallel Tempering. CoRR (2023)
Sinho Chewi, Patrik Gerber, Holden Lee, Chen Lu
Fisher information lower bounds for sampling. ALT (2023)
Chirag Pabbaraju, Dhruv Rohatgi, Anish Prasad Sevekari, Holden Lee, Ankur Moitra, Andrej Risteski
Provable benefits of score matching. NeurIPS (2023)
Holden Lee
Parallelising Glauber dynamics. CoRR (2023)
Chirag Pabbaraju, Dhruv Rohatgi, Anish Prasad Sevekari, Holden Lee, Ankur Moitra, Andrej Risteski
Provable benefits of score matching. CoRR (2023)
Sitan Chen, Sinho Chewi, Holden Lee, Yuanzhi Li, Jianfeng Lu, Adil Salim
The probability flow ODE is provably fast. CoRR (2023)
Tyler Helmuth, Holden Lee, Will Perkins, Mohan Ravichandran, Qiang Wu
Approximation Algorithms for the Random Field Ising Model. SIAM J. Discret. Math. 37 (3) (2023)
Sitan Chen, Sinho Chewi, Holden Lee, Yuanzhi Li, Jianfeng Lu, Adil Salim
The probability flow ODE is provably fast. NeurIPS (2023)
Holden Lee, Jianfeng Lu, Yixin Tan
Convergence of score-based generative modeling for general data distributions. ALT (2023)
Li Du, Afra Amini, Lucas Torroba Hennigen, Xinyan Velocity Yu, Jason Eisner, Holden Lee, Ryan Cotterell
Principled Gradient-based Markov Chain Monte Carlo for Text Generation. CoRR (2023)
Holden Lee, Chirag Pabbaraju, Anish Prasad Sevekari, Andrej Risteski
Pitfalls of Gaussians as a noise distribution in NCE. ICLR (2023)
Hongrui Chen, Holden Lee, Jianfeng Lu
Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions. ICML (2023)
Frederic Koehler, Holden Lee, Andrej Risteski
Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods. CoRR (2022)
Holden Lee, Jianfeng Lu, Yixin Tan
Convergence of score-based generative modeling for general data distributions. CoRR (2022)
Frederic Koehler, Holden Lee, Andrej Risteski
Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods. COLT (2022)
Sinho Chewi, Patrik Gerber, Holden Lee, Chen Lu
Fisher information lower bounds for sampling. CoRR (2022)
Abraham Frandsen, Rong Ge, Holden Lee
Extracting Latent State Representations with Linear Dynamics from Rich Observations. ICML (2022)
Holden Lee, Chirag Pabbaraju, Anish Prasad Sevekari, Andrej Risteski
Pitfalls of Gaussians as a noise distribution in NCE. CoRR (2022)
Holden Lee
Improved rates for prediction and identification of partially observed linear dynamical systems. ALT (2022)
Holden Lee, Jianfeng Lu, Yixin Tan
Convergence for score-based generative modeling with polynomial complexity. CoRR (2022)
Hongrui Chen, Holden Lee, Jianfeng Lu
Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions. CoRR (2022)
Holden Lee, Jianfeng Lu, Yixin Tan
Convergence for score-based generative modeling with polynomial complexity. NeurIPS (2022)
Rong Ge, Holden Lee, Jianfeng Lu, Andrej Risteski
Efficient sampling from the Bingham distribution. ALT (2021)
Holden Lee, Chirag Pabbaraju, Anish Prasad Sevekari, Andrej Risteski
Universal Approximation Using Well-Conditioned Normalizing Flows. NeurIPS (2021)
Tyler Helmuth, Holden Lee, Will Perkins, Mohan Ravichandran, Qiang Wu
Approximation algorithms for the random-field Ising model. CoRR (2021)
Holden Lee, Chirag Pabbaraju, Anish Sevekari, Andrej Risteski
Universal Approximation for Log-concave Distributions using Well-conditioned Normalizing Flows. CoRR (2021)
Udaya Ghai, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang
No-Regret Prediction in Marginally Stable Systems. CoRR (2020)
Udaya Ghai, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang
No-Regret Prediction in Marginally Stable Systems. COLT (2020)
Rong Ge, Holden Lee, Jianfeng Lu
Estimating normalizing constants for log-concave distributions: algorithms and lower bounds. STOC (2020)
Holden Lee, Cyril Zhang
Robust guarantees for learning an autoregressive filter. ALT (2020)
Rong Ge, Holden Lee, Jianfeng Lu, Andrej Risteski
Efficient sampling from the Bingham distribution. CoRR (2020)
Holden Lee
Improved rates for identification of partially observed linear dynamical systems. CoRR (2020)
Holden Lee, Cyril Zhang
Robust guarantees for learning an autoregressive filter. CoRR (2019)
Holden Lee, Oren Mangoubi, Nisheeth K. Vishnoi
Online sampling from log-concave distributions. NeurIPS (2019)
Rohith Kuditipudi, Xiang Wang, Holden Lee, Yi Zhang, Zhiyuan Li, Wei Hu, Sanjeev Arora, Rong Ge
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets. CoRR (2019)
Rohith Kuditipudi, Xiang Wang, Holden Lee, Yi Zhang, Zhiyuan Li, Wei Hu, Rong Ge, Sanjeev Arora
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets. NeurIPS (2019)
Rong Ge, Holden Lee, Jianfeng Lu
Estimating Normalizing Constants for Log-Concave Distributions: Algorithms and Lower Bounds. CoRR (2019)
Holden Lee, Oren Mangoubi, Nisheeth K. Vishnoi
Online Sampling from Log-Concave Distributions. CoRR (2019)
Holden Lee, Andrej Risteski, Rong Ge
Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo. NeurIPS (2018)
Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang
Spectral Filtering for General Linear Dynamical Systems. CoRR (2018)
Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang
Spectral Filtering for General Linear Dynamical Systems. NeurIPS (2018)
Sanjeev Arora, Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang
Towards Provable Control for Unknown Linear Dynamical Systems. ICLR (Workshop) (2018)
Rong Ge, Holden Lee, Andrej Risteski
Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition. CoRR (2018)
Rong Ge, Holden Lee, Andrej Risteski
Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo. CoRR (2017)
Holden Lee, Rong Ge, Andrej Risteski, Tengyu Ma, Sanjeev Arora
On the ability of neural nets to express distributions. CoRR (2017)
Holden Lee, Rong Ge, Tengyu Ma, Andrej Risteski, Sanjeev Arora
On the Ability of Neural Nets to Express Distributions. COLT (2017)
Holden Lee
Quadratic polynomials of small modulus cannot represent OR. CoRR (2015)
Holden Lee
Vector Spaces. Arch. Formal Proofs 2014 (2014)