← Authors

Yin Tat Lee

32 papers · 2016–2024 · 5 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (13) 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (8) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (7) 🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (34) πŸŒ‰ Interdisciplinary Bridge πŸ”¬ Deep Specialist (13) 🀝 Dynamic Duo (10) 🧬 Topic Evolution πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (127) ❓ The Questioner ⚑ Prolific Year (5) πŸ’Ž Century Club (32) πŸ”₯ Unstoppable (9) πŸ“ˆ Trend Setter

Conferences

NIPS (14) COLT (11) ICML (4) ICLR (2) JMLR (1)

Top co-authors

SΓ©bastien Bubeck (10) Ruoqi Shen (7) Sivakanth Gopi (6) Kevin Tian (5) Janardhan Kulkarni (5) Aaron Sidford (5) Daogao Liu (4) Qijia Jiang (4) Swati Padmanabhan (3) Yin-Tat Lee (3)

Research topics

Differential Privacy (1)

Keywords

convex optimization (11) mixing time (5) differential privacy (5) markov chain monte carlo (5) convergence rate (3) distributed optimization (3) stochastic method (3) gradient descent (3) network optimization (3) riemannian hamiltonian monte carlo (2) interior point method (2) stochastic gradient descent (2) neural network (2) empirical risk minimization (2) oracle complexity (2) gradient oracle (2) hamiltonian monte carlo (2) primal-dual algorithm (2) semidefinite programming (1) privacy-preserving learning (1)

Papers

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