Zhiqi Bu
24 papers · 2019–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (43) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π¬
Deep Specialist
(11)
π
Triple Crown
π
Keyword Champion
(3)
π
Trend Setter
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(118)
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(23)
Application Areas
(13)
Deep Learning
(12)
Optimization & Theory Β· Machine Learning
(12)
Artificial Intelligence
(10)
Core AI
(8)
Security & Privacy
(6)
Differential Privacy
(6)
Optimization & Theory Β· Deep Learning
(6)
Core Methods
(5)
Techniques
(5)
Mathematics & Optimization
(4)
Bayesian & Probabilistic
(3)
Learning Types
(3)
Optimization
(3)
Keywords
differential privacy
(10)
gradient clipping
(5)
stochastic gradient descent
(5)
machine unlearning
(4)
deep learning
(3)
private training
(3)
large language model
(2)
high-dimensional regression
(2)
model editing
(2)
overparameterized neural network
(2)
privacy-preserving learning
(2)
sorted l1 penalty
(2)
model architecture
(1)
model pretraining
(1)
variable selection
(1)
feature selection
(1)
bayesian inference
(1)
false discovery rate
(1)
neural tangent kernel
(1)
computer vision
(1)
Papers
BLUR: A Bi-Level Optimization Approach for LLM Unlearning
EACL 2026
DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
ICLR 2025
Gradient descent with generalized Newtonβs method
ICLR 2025
LUME: LLM Unlearning with Multitask Evaluations
EMNLP 2025
MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
ICLR 2025
SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models
SemEval 2025
Towards hyperparameter-free optimization with differential privacy
ICLR 2025
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate
NAACL 2025
Differentially Private Bias-Term Fine-tuning of Foundation Models
ICML 2024
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
ICLR 2024
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
NeurIPS 2024
Pre-training Differentially Private Models with Limited Public Data
NeurIPS 2024
Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
ICLR 2024
Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
NeurIPS 2023
Differentially Private Optimization on Large Model at Small Cost
ICML 2023
Multiple Imputation with Neural Network Gaussian
Process for High-dimensional Incomplete Data
ACML 2022
Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy
NeurIPS 2022
Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
ICML 2021
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
AISTATS 2021
DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks
AISTATS 2021
Efficient Designs Of SLOPE Penalty Sequences In Finite Dimension
AISTATS 2021
Fast and Memory Efficient Differentially Private-SGD via JL Projections
NeurIPS 2021
The Complete Lasso Tradeoff Diagram
NeurIPS 2020
Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing
NeurIPS 2019