activity
20142024
most citedSparks of Artificial General Intelligence: Early experiments with GPT-4

1.6k citations · 1.7k across the 10 of their papers we have counts for

collaborators

6 papers

math.OC20221 cited

Decomposable Non-Smooth Convex Optimization with Nearly-Linear Gradient Oracle Complexity

Sally Dong, Haotian Jiang, Yin Tat Lee +2

Many fundamental problems in machine learning can be formulated by the convex program \[ \min_{θ\in R^d}\ \sum_{i=1}^{n}f_{i}(θ), \] where each is a convex, Lipschitz functio…

math.FA20224 cited

A Slightly Improved Bound for the KLS Constant

Arun Jambulapati, Yin Tat Lee, Santosh S. Vempala

We refine the recent breakthrough technique of Klartag and Lehec to obtain an improved polylogarithmic bound for the KLS constant.

cs.LG20222 cited

Private Convex Optimization in General Norms

Sivakanth Gopi, Yin Tat Lee, Daogao Liu +2

We propose a new framework for differentially private optimization of convex functions which are Lipschitz in an arbitrary norm . Our algorithms are based on a regulariz…

cs.LG20228 cited

When Does Differentially Private Learning Not Suffer in High Dimensions?

Xuechen Li, Daogao Liu, Tatsunori Hashimoto +4

Large pretrained models can be privately fine-tuned to achieve performance approaching that of non-private models. A common theme in these results is the surprising observation tha…

cs.DS2016

Subquadratic Submodular Function Minimization

Deeparnab Chakrabarty, Yin Tat Lee, Aaron Sidford +1

Submodular function minimization (SFM) is a fundamental discrete optimization problem which generalizes many well known problems, has applications in various fields, and can be sol…

cs.DS20145 cited

Single Pass Spectral Sparsification in Dynamic Streams

Michael Kapralov, Yin Tat Lee, Cameron Musco +2

We present the first single pass algorithm for computing spectral sparsifiers of graphs in the dynamic semi-streaming model. Given a single pass over a stream containing insertions…