Wu Lin
10 papers · 2017–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏃 Academic Marathon (7)
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(4)
💎
Century Club
(10)
🚀
Conference Pioneer
❓
The Questioner
🔥
Unstoppable
(5)
Conferences
ICML (7)
AISTATS (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
variational inference
(5)
natural gradient
(3)
second-order optimization
(2)
deep learning
(2)
uncertainty quantification
(1)
model behavior
(1)
data valuation
(1)
gradient-based method
(1)
exponential family
(1)
matrix optimization
(1)
weight perturbation
(1)
natural gradient descent
(1)
mean-field approximation
(1)
stochastic process
(1)
mirror descent
(1)
fisher information matrix
(1)
stochastic mirror descent
(1)
training data attribution
(1)
influence function
(1)
approximate unrolling
(1)
Papers
Training Data Attribution via Approximate Unrolling
NIPS 2024
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
ICML 2024
Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC
ICML 2024
Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning
ICML 2023
Tractable structured natural-gradient descent using local parameterizations
ICML 2021
Handling the Positive-Definite Constraint in the Bayesian Learning Rule
ICML 2020
Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations
ICML 2019
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
ICML 2018
Variational Message Passing with Structured Inference Networks
ICLR 2018
Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models
AISTATS 2017