Artin Tajdini

activity

20202026

collaborators

8 papers

math.CO2026

Decay-Ramsey Sequences

Francesco Di Braccio, Simon Griffiths, Pedram Noohi +1

Given a sequence $a = (a_{i})_{i \geq 1}$ of positive real numbers, we say that a colouring $c : E (K_{n}) \to N$ is $a$ -bounded if the proportion of edges coloured…

cs.AI2026

Defense via Consensus: Mitigating Subliminal Learning through Multi-Teacher Distillation

Adhyyan Narang, Artin Tajdini, Claire Zhang +1

Fine-tuning can introduce unwanted behaviors through deliberate poisoning or unexpected generalization from seemingly benign data. Because these effects may be difficult to anticip…

cs.LG2025

Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards

Artin Tajdini, Jonathan Scarlett, Kevin Jamieson

We study stochastic linear bandits with heavy-tailed rewards, where the rewards have a finite $(1 + ε)$ -absolute central moment bounded by $υ$ for some $ε \in (0, 1]$ . We improv…

cs.GT2025

Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals

Junyan Liu, Arnab Maiti, Artin Tajdini +2

We initiate the study of a repeated principal-agent problem over a finite horizon $T$ , where a principal sequentially interacts with $K \geq 2$ types of agents arriving in an advers…

cs.LG2024

Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification

Haolin Liu, Artin Tajdini, Andrew Wagenmaker +1

In linear bandits, how can a learner effectively learn when facing corrupted rewards? While significant work has explored this question, a holistic understanding across different a…

cs.LG2023

Nearly Minimax Optimal Submodular Maximization with Bandit Feedback

Artin Tajdini, Lalit Jain, Kevin Jamieson

We consider maximizing an unknown monotonic, submodular set function $f : 2^{[n]} \to [0, 1]$ with cardinality constraint under stochastic bandit feedback. At each time $t=1,…

quant-ph2021

Time and Query Optimal Quantum Algorithms Based on Decision Trees

Salman Beigi, Leila Taghavi, Artin Tajdini

It has recently been shown that starting with a classical query algorithm (decision tree) and a guessing algorithm that tries to predict the query answers, we can design a quantum…

math.CO2020

On a question of Haemers regarding vectors in the nullspace of Seidel matrices

Saieed Akbari, Sebastian M. Cioabă, Samira Goudarzi +2

In 2011, Haemers asked the following question: If $S$ is the Seidel matrix of a graph of order $n$ and $S$ is singular, does there exist an eigenvector of $S$ corresponding to $0$ …