Mehrdad Mahdavi
35 papers · 2012–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+13 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (17) 🌍 Conference Polyglot (6)
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
🏃
Academic Marathon
(13)
🌟
Keyword Trendsetter Combo
(3)
🤝
Dynamic Duo
(10)
🔬
Deep Specialist
(15)
🏆
Keyword Champion
(3)
❓
The Questioner
🗃️
Keyword Collector
(123)
📈
Trend Setter
💎
Century Club
(35)
🔥
Unstoppable
(7)
⚡
Prolific Year
(5)
Conferences
NIPS (17)
AISTATS (7)
COLT (4)
ICLR (3)
ICML (3)
JMLR (1)
Top co-authors
Keywords
stochastic gradient descent
(5)
communication efficiency
(4)
convex optimization
(4)
federated learning
(4)
convergence analysis
(3)
empirical risk minimization
(3)
distributed optimization
(3)
minimax optimization
(3)
optimization algorithm
(3)
distributed learning
(3)
low-rank matrix
(2)
online convex optimization
(2)
non-convex optimization
(2)
strong convexity
(2)
stochastic optimization
(2)
strongly convex
(2)
stochastic gradient
(2)
map inference
(2)
knowledge transfer
(2)
gradient descent
(2)
Papers
Stochastic Compositional Minimax Optimization with Provable Convergence Guarantees
AISTATS 2025
Learn more, but bother less: parameter efficient continual learning
NIPS 2024
Stochastic Quantum Sampling for Non-Logconcave Distributions and Estimating Partition Functions
ICML 2024
On the Generalization Ability of Unsupervised Pretraining
AISTATS 2024
Do We Really Need Complicated Model Architectures For Temporal Networks?
ICLR 2023
Understanding Deep Gradient Leakage via Inversion Influence Functions
NIPS 2023
Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation
NIPS 2023
Distributed Personalized Empirical Risk Minimization
NIPS 2023
Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection
AISTATS 2023
Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time
AISTATS 2022
Learning Distributionally Robust Models at Scale via Composite Optimization
ICLR 2022
Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks
ICLR 2022
Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems
NIPS 2022
Federated Learning with Compression: Unified Analysis and Sharp Guarantees
AISTATS 2021
Meta-learning with an Adaptive Task Scheduler
NIPS 2021
On Provable Benefits of Depth in Training Graph Convolutional Networks
NIPS 2021
Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency
AISTATS 2021
Distributionally Robust Federated Averaging
NIPS 2020
Online Structured Meta-learning
NIPS 2020
GCN meets GPU: Decoupling “When to Sample” from “How to Sample”
NIPS 2020
Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization
NIPS 2019
Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization
ICML 2019
Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data
AISTATS 2017
Train and Test Tightness of LP Relaxations in Structured Prediction
ICML 2016
Smooth and Strong: MAP Inference with Linear Convergence
NIPS 2015
Lower and Upper Bounds on the Generalization of Stochastic Exponentially Concave Optimization
COLT 2015
Mixed Optimization for Smooth Functions
NIPS 2013
Linear Convergence with Condition Number Independent Access of Full Gradients
NIPS 2013
Stochastic Convex Optimization with Multiple Objectives
NIPS 2013
Recovering the Optimal Solution by Dual Random Projection
COLT 2013
Passive Learning with Target Risk
COLT 2013
Trading Regret for Efficiency: Online Convex Optimization with Long Term Constraints
JMLR 2012
Stochastic Gradient Descent with Only One Projection
NIPS 2012
Online Optimization with Gradual Variations
COLT 2012
Nyström Method vs Random Fourier Features: A Theoretical and Empirical Comparison
NIPS 2012