Khashayar Gatmiry

Jon Schneider

CoRR, 2024

What does guidance do? A fine-grained analysis in a simple setting.

[BibT_eX]

[DOI]

CoRR, 2024

Learning Mixtures of Gaussians Using Diffusion Models.

[BibT_eX]

[DOI]

Holden Lee

CoRR, 2024

Bandit Algorithms for Prophet Inequality and Pandora's Box.

[BibT_eX]

[DOI]

Proceedings of the 2024 ACM-SIAM Symposium on Discrete Algorithms, 2024

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Simplicity Bias via Global Convergence of Sharpness Minimization.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Adversarial Online Learning with Temporal Feedback Graphs.

[BibT_eX]

[DOI]

Jon Schneider

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Sampling Polytopes with Riemannian HMC: Faster Mixing via the Lewis Weights Barrier.

[BibT_eX]

[DOI]

Santosh S. Vempala

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

EM for Mixture of Linear Regression with Clustered Data.

[BibT_eX]

[DOI]

Amirhossein Reisizadeh

Asuman E. Ozdaglar

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

A Unified Approach to Controlling Implicit Regularization via Mirror Descent.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2023

The Inductive Bias of Flatness Regularization for Deep Matrix Factorization.

[BibT_eX]

[DOI]

CoRR, 2023

When does Metropolized Hamiltonian Monte Carlo provably outperform Metropolis-adjusted Langevin algorithm?

[BibT_eX]

[DOI]

Yuansi Chen

CoRR, 2023

A Simple Proof of the Mixing of Metropolis-Adjusted Langevin Algorithm under Smoothness and Isoperimetry.

[BibT_eX]

[DOI]

Yuansi Chen

CoRR, 2023

Sampling with Barriers: Faster Mixing via Lewis Weights.

[BibT_eX]

[DOI]

Santosh S. Vempala

CoRR, 2023

Projection-Free Online Convex Optimization via Efficient Newton Iterations.

[BibT_eX]

[DOI]

Zakaria Mhammedi

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Quasi-Newton Steps for Efficient Online Exp-Concave Optimization.

[BibT_eX]

[DOI]

Zakaria Mhammedi

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

The Network Visibility Problem.

[BibT_eX]

[DOI]

Manuel Gomez-Rodriguez

ACM Trans. Inf. Syst., 2022

Optimal algorithms for group distributionally robust optimization and beyond.

[BibT_eX]

[DOI]

Tasuku Soma

CoRR, 2022

Convergence of the Riemannian Langevin Algorithm.

[BibT_eX]

[DOI]

Santosh S. Vempala

CoRR, 2022

On the generalization of learning algorithms that do not converge.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Optimization and Adaptive Generalization of Three layer Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2020

Testing Determinantal Point Processes.

[BibT_eX]

[DOI]

Maryam Aliakbarpour

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2018

Information Theoretic Bounds on Optimal Worst-case Error in Binary Mixture Identification.

[BibT_eX]

[DOI]