2025
Proceedings of the 16th Innovations in Theoretical Computer Science Conference, 2025
2024
Efficiently learning and sampling multimodal distributions with data-based initialization.
CoRR, 2024
Sampling from the Continuous Random Energy Model in Total Variation Distance.
CoRR, 2024
Convergence Bounds for Sequential Monte Carlo on Multimodal Distributions using Soft Decomposition.
CoRR, 2024
Learning Mixtures of Gaussians Using Diffusion Models.
CoRR, 2024
What does guidance do? A fine-grained analysis in a simple setting.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Principled Gradient-Based MCMC for Conditional Sampling of Text.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
How Flawed Is ECE? An Analysis via Logit Smoothing.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Parallelising Glauber Dynamics.
Proceedings of the Approximation, 2024
When is a Language Process a Language Model?
Proceedings of the Findings of the Association for Computational Linguistics, 2024
2023
Approximation Algorithms for the Random Field Ising Model.
SIAM J. Discret. Math., September, 2023
Principled Gradient-based Markov Chain Monte Carlo for Text Generation.
CoRR, 2023
Improved Bound for Mixing Time of Parallel Tempering.
CoRR, 2023
Provable benefits of score matching.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
The probability flow ODE is provably fast.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Connecting Pre-trained Language Model and Downstream Task via Properties of Representation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions.
Proceedings of the International Conference on Machine Learning, 2023
Pitfalls of Gaussians as a noise distribution in NCE.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
Convergence of score-based generative modeling for general data distributions.
Proceedings of the International Conference on Algorithmic Learning Theory, 2023
Fisher information lower bounds for sampling.
Proceedings of the International Conference on Algorithmic Learning Theory, 2023
2022
Convergence for score-based generative modeling with polynomial complexity.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Extracting Latent State Representations with Linear Dynamics from Rich Observations.
Proceedings of the International Conference on Machine Learning, 2022
Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022
Improved rates for prediction and identification of partially observed linear dynamical systems.
Proceedings of the International Conference on Algorithmic Learning Theory, 29 March, 2022
2021
Universal Approximation for Log-concave Distributions using Well-conditioned Normalizing Flows.
CoRR, 2021
Universal Approximation Using Well-Conditioned Normalizing Flows.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Efficient sampling from the Bingham distribution.
Proceedings of the Algorithmic Learning Theory, 2021
2020
Improved rates for identification of partially observed linear dynamical systems.
CoRR, 2020
Estimating normalizing constants for log-concave distributions: algorithms and lower bounds.
Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing, 2020
No-Regret Prediction in Marginally Stable Systems.
Proceedings of the Conference on Learning Theory, 2020
Robust guarantees for learning an autoregressive filter.
Proceedings of the Algorithmic Learning Theory, 2020
2019
MCMC algorithms for sampling from multimodal and changing distributions
PhD thesis, 2019
Online sampling from log-concave distributions.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
2018
Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition.
CoRR, 2018
Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
Spectral Filtering for General Linear Dynamical Systems.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
Towards Provable Control for Unknown Linear Dynamical Systems.
Proceedings of the 6th International Conference on Learning Representations, 2018
2017
On the Ability of Neural Nets to Express Distributions.
Proceedings of the 30th Conference on Learning Theory, 2017
2015
Quadratic polynomials of small modulus cannot represent OR.
CoRR, 2015
2014
Arch. Formal Proofs, 2014