Mirko Giacchini

Postdoc at Columbia University

GitHub
mg5011 [AT] columbia [DOT] edu

I am a postdoctoral researcher at Columbia University, where I am an Italian Academy Fellow and I am advised by Eric Balkanski.

I obtained my Ph.D. in Computer Science from Sapienza University of Rome, where I was advised by Flavio Chierichetti and Alessandro Panconesi. My research focuses on online algorithms and theoretical foundations of machine learning. Specifically, I have worked on stochastic online bipartite matching and learning algorithms for discrete choice models, including random utility models and multinomial-logit/Plackett-Luce models.

I have served (or am serving) as PC member for KDD (2024), TheWebConf (2024, 2026), and AAAI (2026), and as reviewer for SODA (2025, 2026, 2027), ITCS (2025), ESA (2025), NeurIPS (2026), ICML (2026 Gold Reviewer), KDD (2023), TheWebConf (2025), SDM (2024), and TIST.

Teaching

Advanced Algorithms, Sapienza University of Rome, Spring 2026
Co-Lecturer with Flavio Chierichetti

Publications

On the LSH Distortion of Ulam and Cayley Similarities
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar, Erasmo Tani

RANDOM 2026 · Paper

Learning Multinomial Logits in O(n log n) time
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar, Silvio Lattanzi, Alessandro Panconesi, Erasmo Tani, Andrew Tomkins

ICALP 2026 · Paper

User Choice, Hidden Gems, and the Quadratic Horizon
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar, Alessandro Panconesi, Andrew Tomkins

PNAS Nexus (2026) · Paper · Code

Man, these New York Times games are hard! A computational perspective
Alessandro Giovanni Alberti, Flavio Chierichetti, Mirko Giacchini, Daniele Muscillo, Alessandro Panconesi, Erasmo Tani

FUN 2026 · Paper

On the Metricity of the Chatterjee Correlation Coefficient
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar

The American Statistician (2026) · Paper · Code

A New Impossibility Result for Online Bipartite Matching Problems
Flavio Chierichetti, Mirko Giacchini, Alessandro Panconesi, Andrea Vattani

ICALP 2025 · Paper

Tight Bounds for Learning RUMs from Small Slates
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar, Alessandro Panconesi, Andrew Tomkins

NeurIPS 2024 · Paper

Coordinating “7 Billion Humans” is hard
Alessandro Panconesi, Pietro Maria Posta, Mirko Giacchini

FUN 2024 · Paper

Approximating a RUM from Distributions on k-slates
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar, Alessandro Panconesi, Andrew Tomkins

AISTATS 2023 · Paper · Code