AIConfPaper
← Search

Mohammadreza Nazari

5 accepted papers

2026

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling

Georgi Ganev, MohammadReza Nazari, Rees Davison, Amirhassan Fallah Dizche, XINMIN WU, Ralph Abbey +2
ICLR 2026poster

The Synthetic Minority Over-sampling Technique (SMOTE) is one of the most widely used methods for addressing class imbalance and generating synthetic data. Despite its popularity, little attention has been paid to its privacy implications; yet, it is used in the wild in many privacy-sensitive applic…

Cited by 0Source ↗code ↗Scholar ↗
2021

SONIA: A Symmetric Blockwise Truncated Optimization Algorithm

Majid Jahani, MohammadReza Nazari, Rachael Tappenden, Albert Berahas, Martin Takac
AISTATS 2021poster

This work presents a new optimization algorithm for empirical risk minimization. The algorithm bridges the gap between first- and second-order methods by computing a search direction that uses a second-order-type update in one subspace, coupled with a scaled steepest descent step in the orthogonal c…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2020

AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control

Afshin Oroojlooy, Mohammadreza Nazari, Davood Hajinezhad, Jorge Silva
NeurIPS 2020poster

We propose AttendLight, an end-to-end Reinforcement Learning (RL) algorithm for the problem of traffic signal control. Previous approaches for this problem have the shortcoming that they require training for each new intersection with a different structure or traffic flow distribution. AttendLight s…

Cited by 114Source ↗PDF ↗code ↗Scholar ↗
2019

Multi-Agent Image Classification via Reinforcement Learning

Hossein K. Mousavi, Mohammadreza Nazari, Martin Takáč, Nader Motee
IROS 2019poster

We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment. The objective is to classify an image over a finite time horizon. We propose a network architecture on how agents should form a local belief, ta…

Cited by 34Source ↗Scholar ↗
2018

Reinforcement Learning for Solving the Vehicle Routing Problem

MohammadReza Nazari, Afshin Oroojlooy, Lawrence Snyder, Martin Takac
NeurIPS 2018poster

We present an end-to-end framework for solving the Vehicle Routing Problem (VRP) using reinforcement learning. In this approach, we train a single policy model that finds near-optimal solutions for a broad range of problem instances of similar size, only by observing the reward signals and following…

Cited by 1551Source ↗PDF ↗Scholar ↗