2 citations · 2 across the 9 of their papers we have counts for
9 papers
Gap-Free Streaming PCA Beyond Rank-One Updates: Near-Optimal Rates and Applications to Differential Privacy
Anming Gu, Syamantak Kumar, Kevin Tian +1
Streaming principal component analysis (PCA) seeks to recover a leading spectral subspace in a single pass over a data stream. We give a new analysis of the ubiquitous Oja's algori…
The Tractability Landscape of Sampling with Inexact Scores
Anming Gu, Kevin Tian, Hubert Yang +1
We provide a simple and tight characterization of the types of inexact score oracle access that permit sampling with vanishing total variation bias, for a standard, well-behaved ta…
Functional Stochastic Localization
Anming Gu, Bobby Shi, Kevin Tian
Eldan's stochastic localization is a probabilistic construction that has proved instrumental to modern breakthroughs in high-dimensional geometry and the design of sampling algorit…
Differentially Private Wasserstein Barycenters
Anming Gu, Sasidhar Kunapuli, Mark Bun +2
The Wasserstein barycenter is defined as the mean of a set of probability measures under the optimal transport metric, and has numerous applications spanning machine learning, stat…
Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics
Anming Gu, Edward Chien, Kristjan Greenewald
We provide an algorithm to privately generate continuous-time data (e.g. marginals from stochastic differential equations), which has applications in highly sensitive domains invol…
Mirror Mean-Field Langevin Dynamics
Anming Gu, Juno Kim
The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over , and has gained attention recently…
Compute-Optimal LLMs Provably Generalize Better With Scale
Marc Finzi, Sanyam Kapoor, Diego Granziol +4
Why do larger language models generalize better? To investigate this question, we develop generalization bounds on the pretraining objective of large language models (LLMs) in the…
Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior
Anming Gu, Edward Chien, Kristjan Greenewald
Trajectory inference seeks to recover the temporal dynamics of a population from snapshots of its (uncoupled) temporal marginals, i.e. where observed particles are not tracked over…
k-Mixup Regularization for Deep Learning via Optimal Transport
Kristjan Greenewald, Anming Gu, Mikhail Yurochkin +2
Mixup is a popular regularization technique for training deep neural networks that improves generalization and increases robustness to certain distribution shifts. It perturbs inpu…