← Authors

Meisam Razaviyayn

27 papers · 2014–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (7) πŸ—ΊοΈ Taxonomy Completionist (33) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (11) πŸ‘‘ Triple Crown πŸ”₯ Unstoppable (9) πŸ’Ž Century Club (27) πŸ“ˆ Trend Setter ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (87)

Conferences

ICLR (7) NIPS (7) ICML (6) AISTATS (4) ALT (1) JMLR (1) NAACL (1)

Top co-authors

Andrew Lowy (5) Mingyi Hong (5) Tianjian Huang (4) Zeman Li (3) Sina Baharlouei (3) Jason Lee (3) Xinwei Zhang (3) Vahab Mirrokni (3) Maziar Sanjabi (3) Renyuan Xu (2)

Research topics

Differential Privacy (1)

Keywords

non-convex optimization (5) differential privacy (4) attribution method (3) nonconvex optimization (2) neural network (2) feature attribution (2) integrated gradient (2) explainable ai (2) stochastic gradient descent (1) game theory (1) model quantization (1) feature selection (1) optimal transport (1) robust classification (1) federated learning (1) binary classification (1) neural network interpretability (1) stochastic optimization (1) feature importance (1) privacy preservation (1)

Papers

Synthetic Text Generation for Training Large Language Models via Gradient Matching ICML 2025
Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models ICLR 2025
Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence ICML 2025
DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction ICLR 2025
Four Axiomatic Characterizations of the Integrated Gradients Attribution Method JMLR 2025
On the Inherent Privacy of Zeroth-Order Projected Gradient Descent AISTATS 2025
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction NIPS 2024
Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization ICLR 2024
Differentially Private Next-Token Prediction of Large Language Models NAACL 2024
f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization ICLR 2024
Optimal Differentially Private Model Training with Public Data ICML 2024
Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses ICLR 2023
Private Non-Convex Federated Learning Without a Trusted Server AISTATS 2023
Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes AISTATS 2023
Private Stochastic Optimization with Large Worst-Case Lipschitz Parameter: Optimal Rates for (Non-Smooth) Convex Losses and Extension to Non-Convex Losses ALT 2023
Stochastic Differentially Private and Fair Learning ICLR 2023
A Unifying Framework to the Analysis of Interaction Methods using Synergy Functions ICML 2023
A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions ICML 2022
Alternating Direction Method of Multipliers for Quantization AISTATS 2021
RΓ©nyi Fair Inference ICLR 2020
Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems NIPS 2020
Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods NIPS 2019
On the Convergence and Robustness of Training GANs with Regularized Optimal Transport NIPS 2018
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks ICML 2018
On Optimal Generalizability in Parametric Learning NIPS 2017
Discrete RΓ©nyi Classifiers NIPS 2015
Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization NIPS 2014