iiinova — where your digital self keeps evolving

Eshwar Ram Arunachaleswaran

@epsilonrational.bsky.social

106 followers 360 following 12 posts

Studies Algorithmic game theory and online learning University of Pennsylvania/ Simons institute www.seas.upenn.edu/~eshwar

Posts Replies Media

Eshwar Ram Arunachaleswaran @epsilonrational.bsky.social · 23/10/2025

Some fun work connecting no regret algorithms, pricing and collusion, with @aaroth.bsky.social , @ncollina.bsky.social , @jubaz.bsky.social and my advisor Sampath Kannan

071

Reposted by Eshwar Ram Arunachaleswaran

Natalie Collina @ncollina.bsky.social · 22/10/2025

Our paper on algorithmic collusion was featured in a Quanta article! www.quantamagazine.org/the-game-the...

quantamagazine.org

The Game Theory of How Algorithms Can Drive Up Prices | Quanta Magazine

Recent findings reveal that even simple pricing algorithms can make things more expensive.

2309

Eshwar Ram Arunachaleswaran @epsilonrational.bsky.social · 04/07/2025

Ecstatic and deeply honored by this award. I've had great fun thinking about algorithms as strategies for repeated games over the past few years and hope that this highlight will push more researchers to come up with exciting directions in this field! Come to our talk on Monday to learn more!

2143

Eshwar Ram Arunachaleswaran @epsilonrational.bsky.social · 01/03/2025

What should swap-regret mean beyond normal-form games? We have a new paper (@ncollina.bsky.social, Mehryar Mohri, Yishay Mansour, Jon Schneider, Balu Sivan) tackling this question and providing a definitive answer! (thread) arxiv.org/abs/2502.20229

arxiv.org

Swap Regret and Correlated Equilibria Beyond Normal-Form Games

Swap regret is a notion that has proven itself to be central to the study of general-sum normal-form games, with swap-regret minimization leading to convergence to the set of correlated equilibria and...

1113

Eshwar Ram Arunachaleswaran @epsilonrational.bsky.social · 27/12/2024

Check out our new paper, on optimal algorithmic commitments against a distribution of opponents!

060