Jason M. Altschuler

Math. Program., September, 2025

Optimized methods for composite optimization: a reduction perspective.

[BibT_eX]

[DOI]

CoRR, June, 2025

Shifted Composition IV: Underdamped Langevin and Numerical Discretizations with Partial Acceleration.

[BibT_eX]

[DOI]

Matthew S. Zhang

CoRR, June, 2025

Negative Stepsizes Make Gradient-Descent-Ascent Converge.

[BibT_eX]

[DOI]

Henry Shugart

CoRR, May, 2025

Acceleration by Stepsize Hedging: Multi-Step Descent and the Silver Stepsize Schedule.

[BibT_eX]

[DOI]

J. ACM, April, 2025

Near-Linear Runtime for a Classical Matrix Preconditioning Algorithm.

[BibT_eX]

[DOI]

Xufeng Cai

Jelena Diakonikolas

CoRR, March, 2025

Shifted Composition I: Harnack and Reverse Transport Inequalities.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, January, 2025

Resolving the Mixing Time of the Langevin Algorithm to Its Stationary Distribution for Log-Concave Sampling.

[BibT_eX]

[DOI]

SIAM J. Math. Data Sci., 2025

Accelerating Proximal Gradient Descent via Silver Stepsizes.

[BibT_eX]

[DOI]

Proceedings of the Thirty Eighth Annual Conference on Learning Theory, 2025

2024

Faster High-accuracy Log-concave Sampling via Algorithmic Warm Starts.

[BibT_eX]

[DOI]

J. ACM, June, 2024

On the Privacy of Noisy Stochastic Gradient Descent for Convex Optimization.

[BibT_eX]

[DOI]

SIAM J. Comput., 2024

Shifted Composition III: Local Error Framework for KL Divergence.

[BibT_eX]

[DOI]

CoRR, 2024

Acceleration by Random Stepsizes: Hedging, Equalization, and the Arcsine Stepsize Schedule.

[BibT_eX]

[DOI]

CoRR, 2024

Shifted Composition II: Shift Harnack Inequalities and Curvature Upper Bounds.

[BibT_eX]

[DOI]

CoRR, 2024

Shifted Interpolation for Differential Privacy.

[BibT_eX]

[DOI]

Weijie J. Su

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

2023

Polynomial-time algorithms for multimarginal optimal transport problems with structure.

[BibT_eX]

[DOI]

Math. Program., May, 2023

Kernel Approximation on Algebraic Varieties.

[BibT_eX]

[DOI]

SIAM J. Appl. Algebra Geom., March, 2023

Near-linear convergence of the Random Osborne algorithm for Matrix Balancing.

[BibT_eX]

[DOI]

Math. Program., March, 2023

Acceleration by Stepsize Hedging I: Multi-Step Descent and the Silver Stepsize Schedule.

[BibT_eX]

[DOI]

CoRR, 2023

2022

Approximating Min-Mean-Cycle for Low-Diameter Graphs in Near-Optimal Time and Memory.

[BibT_eX]

[DOI]

SIAM J. Optim., September, 2022

Transport and Beyond: Efficient Optimization over Probability Distributions

[BibT_eX]

[DOI]

PhD thesis, 2022

Wasserstein Barycenters Are NP-Hard to Compute.

[BibT_eX]

[DOI]

SIAM J. Math. Data Sci., 2022

Asymptotics for Semidiscrete Entropic Optimal Transport.

[BibT_eX]

[DOI]

Jonathan Niles-Weed

Austin J. Stromme

SIAM J. Math. Anal., 2022

Concentration of the Langevin Algorithm's Stationary Distribution.

[BibT_eX]

[DOI]

CoRR, 2022

Flows, Scaling, and Entropy Revisited: a Unified Perspective via Optimizing Joint Distributions.

[BibT_eX]

[DOI]

CoRR, 2022

Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss.

[BibT_eX]

[DOI]

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

2021

Online Learning over a Finite Action Set with Limited Switching.

[BibT_eX]

[DOI]

Math. Oper. Res., 2021

Wasserstein barycenters can be computed in polynomial time in fixed dimension.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

Hardness results for Multimarginal Optimal Transport problems.

[BibT_eX]

[DOI]

Discret. Optim., 2021

Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Lyapunov Exponent of Rank-One Matrices: Ergodic Formula and Inapproximability of the Optimal Distribution.

[BibT_eX]

[DOI]

SIAM J. Control. Optim., 2020

High-precision Wasserstein barycenters in polynomial time.

[BibT_eX]

[DOI]

CoRR, 2020

Random Osborne: a simple, practical algorithm for Matrix Balancing in near-linear time.

[BibT_eX]

[DOI]

CoRR, 2020

2019

Best Arm Identification for Contaminated Bandits.

[BibT_eX]

[DOI]

Victor-Emmanuel Brunel

Alan Malek

J. Mach. Learn. Res., 2019

Massively scalable Sinkhorn distances via the Nyström method.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018

Approximating the Quadratic Transportation Metric in Near-Linear Time.

[BibT_eX]

[DOI]

CoRR, 2018

2017

Inclusion of forbidden minors in random representable matroids.

[BibT_eX]

[DOI]

Elizabeth Yang

Discret. Math., 2017

Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration.

[BibT_eX]

[DOI]