Yin Tat Lee

Differentially Private Synthetic Data via Foundation Model APIs 2: Text ICML 2024 Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler COLT 2023 Condition-number-independent Convergence Rate of Riemannian Hamiltonian Monte Carlo with Numerical Integrators COLT 2023 Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping ICLR 2023 Learning threshold neurons via edge of stability NeurIPS 2023 A gradient sampling method with complexity guarantees for Lipschitz functions in high and low dimensions NeurIPS 2022 Decomposable Non-Smooth Convex Optimization with Nearly-Linear Gradient Oracle Complexity NeurIPS 2022 Differentially Private Fine-tuning of Language Models ICLR 2022 Private Convex Optimization via Exponential Mechanism COLT 2022 Sampling with Riemannian Hamiltonian Monte Carlo in a Constrained Space NeurIPS 2022 When Does Differentially Private Learning Not Suffer in High Dimensions? NeurIPS 2022 Fast and Memory Efficient Differentially Private-SGD via JL Projections NeurIPS 2021 Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions NeurIPS 2021 Numerical Composition of Differential Privacy NeurIPS 2021 Private Non-smooth ERM and SCO in Subquadratic Steps NeurIPS 2021 Structured Logconcave Sampling with a Restricted Gaussian Oracle COLT 2021 Acceleration with a Ball Optimization Oracle NeurIPS 2020 An Õ(m/ε^3.5)-Cost Algorithm for Semidefinite Programs with Diagonal Constraints COLT 2020 Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte Carlo COLT 2020 Network size and size of the weights in memorization with two-layers neural networks NeurIPS 2020 Adversarial examples from computational constraints ICML 2019 A near-optimal algorithm for approximating the John Ellipsoid COLT 2019 Complexity of Highly Parallel Non-Smooth Convex Optimization NeurIPS 2019 Near-optimal method for highly smooth convex optimization COLT 2019 Near Optimal Methods for Minimizing Convex Functions with Lipschitz p-th Derivatives COLT 2019 Optimal Convergence Rates for Convex Distributed Optimization in Networks JMLR 2019 Solving Empirical Risk Minimization in the Current Matrix Multiplication Time COLT 2019 The Randomized Midpoint Method for Log-Concave Sampling NeurIPS 2019 Efficient Convex Optimization with Membership Oracles COLT 2018 Optimal Algorithms for Non-Smooth Distributed Optimization in Networks NeurIPS 2018 Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks ICML 2017 Black-box Optimization with a Politician ICML 2016