Weiwei "William" Kong
Hi! I'm William Kong, a Research Software Engineer at Google Research (NYC) in Athena. Here you'll find my publications, open-source software, mathematical blog posts, and course notes.
Previously, I was a postdoc in the CSMD at Oak Ridge National Labs under Miroslav Stoyanov, a Research Intern at Google Research (MTV), and a Senior Risk Analyst at TD Bank.
I received my Ph.D. in Operations Research from Georgia Tech under Renato D. C. Monteiro, along with an M.Sc. in Computational Science & Engineering (Georgia Tech) and a B.Math. from the University of Waterloo.
Recent News
Blog →- Nov 2026 Released Proxax — a library of certified composite optimization solvers in JAX and Optax.
- Aug 2026 New preprint: A Mini-Batch Counterexample to Last-Iterate Convergence in Definable Optimization.
- Jul 2026 ContinuousBench accepted to the ICML 2026 Workshop on Memorization in Trustworthy Foundation Models.
- Feb 2026 Released preprints on JAX-Privacy and Coarse-to-Fine Wavelet Modeling for Private Image Generation.
- Jan 2026 Escaping Collapse: The Strength of Weak Data for Large Language Model Training published at NeurIPS 38.
- Apr 2025 Differentially Private Optimization for Non-Decomposable Objective Functions accepted to ICLR 2025.
Research Pillars
27 papers →Differential Privacy & Scalable DP-ML
Fast per-example gradient clipping, privacy auditing (DP-Auditorium), non-decomposable DP optimization, and production DP libraries in JAX (JAX-Privacy).
Synthetic Data & LLM Training
Escaping model collapse with weak data, limitations of ERM on synthetic corpora, private prediction for synthetic text, and ContinuousBench.
Nonconvex Composite Optimization
Accelerated proximal, penalty, spectral, and augmented Lagrangian solvers with certified stationarity bounds—implemented in Proxax (JAX) and NC-OPT.
Interactive Demo
Explore Proxax & software →Nonconvex Banana Valley: Why Adaptive Acceleration Matters
Proxax APD)
Solve this nonconvex problem in Python / JAX with Proxax (px.solvers.APD) — or read the Acceleration blog series
import jax.numpy as jnp
from proxax import px
b = 100.0 # Rosenbrock valley steepness (nonconvex, kappa ≈ 2500 at x*)
def rosenbrock(x):
return (1.0 - x[0]) ** 2 + b * (x[1] - x[0] ** 2) ** 2
problem = px.CompositeProblem(smooth=rosenbrock)
sol = px.solve(
problem=problem,
x0=jnp.array([-1.2, 1.0]),
solver=px.solvers.APD(opt_tol=1e-6),
)
print(sol.status_enum.name, sol.x, sol.stats.opt_residual)
The live plot above runs directly in your browser in JavaScript (no backend server). Because the Rosenbrock
valley is nonconvex and severely ill-conditioned (local condition number at when ), fixed-step GD crawls along the curved trough.
Adaptive curvature estimation combined with accelerated extrapolation and restart—as implemented in Proxax
(px.solvers.APD)—reaches machine precision orders of magnitude faster without
tuning or .