Hongzhou Lin
11 papers · 2015–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (17) π Interdisciplinary Bridge π Academic Marathon (10) π£ Hot Topic Early Bird π Cross-Pollinator (7)
π§
Keyword Pioneer
π
Conference Polyglot
(6)
π
Keyword Champion
(2)
β
The Questioner
π
Century Club
(11)
Conferences
NIPS (4)
ICML (3)
AISTATS (1)
ICLR (1)
JMLR (1)
NAACL (1)
Top co-authors
Keywords
first-order method
(3)
gradient descent
(3)
accelerated gradient
(2)
convex optimization
(2)
nonconvex optimization
(2)
nesterov acceleration
(2)
function approximation
(1)
compositional learning
(1)
stochastic optimization
(1)
decentralized optimization
(1)
nonsmooth optimization
(1)
worst-case analysis
(1)
task generalization
(1)
variance reduction
(1)
oracle complexity
(1)
machine unlearning
(1)
strongly convex
(1)
stochastic approximation
(1)
knowledge distillation
(1)
meta-learning
(1)
Papers
UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models
NAACL 2025
From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
ICLR 2025
Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?
ICML 2025
Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity
ICML 2022
Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning
NIPS 2021
Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions
ICML 2020
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method
NIPS 2020
Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice
JMLR 2018
Catalyst for Gradient-based Nonconvex Optimization
AISTATS 2018
ResNet with one-neuron hidden layers is a Universal Approximator
NIPS 2018
A Universal Catalyst for First-Order Optimization
NIPS 2015