Kevin Tian

collaborators

5 papers

cs.DS2025

Radial Isotropic Position via an Implicit Newton's Method

Arun Jambulapati, Jonathan Li, Kevin Tian

Placing a dataset $A = {a_{i}}_{i \in [n]} \subset R^{d}$ in radial isotropic position, i.e., finding an invertible $R \in R^{d \times d}$ such th…

cs.DS2024

Eulerian Graph Sparsification by Effective Resistance Decomposition

Arun Jambulapati, Sushant Sachdeva, Aaron Sidford +2

We provide an algorithm that, given an $n$ -vertex $m$ -edge Eulerian graph with polynomially bounded weights, computes an $O ˘ (n lo g^{2} n \cdot ε^{- 2})$ -edge $\vare…

math.OC2024

Closing the Computational-Query Depth Gap in Parallel Stochastic Convex Optimization

Arun Jambulapati, Aaron Sidford, Kevin Tian

We develop a new parallel algorithm for minimizing Lipschitz, convex functions with a stochastic subgradient oracle. The total number of queries made and the query depth, i.e., the…

math.NA2024

Black-Box $k$ -to- $1$ -PCA Reductions: Theory and Applications

Arun Jambulapati, Syamantak Kumar, Jerry Li +3

The $k$ -principal component analysis ( $k$ -PCA) problem is a fundamental algorithmic primitive that is widely-used in data analysis and dimensionality reduction applications. In sta…

cs.LG2024

Testing Calibration in Nearly-Linear Time

Lunjia Hu, Arun Jambulapati, Kevin Tian +1

In the recent literature on machine learning and decision making, calibration has emerged as a desirable and widely-studied statistical property of the outputs of binary prediction…

Radial Isotropic Position via an Implicit Newton's Method

Eulerian Graph Sparsification by Effective Resistance Decomposition

Closing the Computational-Query Depth Gap in Parallel Stochastic Convex Optimization

Black-Box k-to-1-PCA Reductions: Theory and Applications

Testing Calibration in Nearly-Linear Time

Black-Box $k$ -to- $1$ -PCA Reductions: Theory and Applications