114 citations · 813 across the 92 of their papers we have counts for
19 papers · 1 filter
Efficiently avoiding saddle points with zero order methods: No gradients required
Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras
We consider the case of derivative-free algorithms for non-convex optimization, also known as zero order algorithms, that use only function evaluations rather than gradients. For a…
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games
Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras
We study a wide class of non-convex non-concave min-max games that generalizes over standard bilinear zero-sum games. In this class, players control the inputs of a smooth function…
From Darwin to Poincaré and von Neumann: Recurrence and Cycles in Evolutionary and Algorithmic Game Theory
Victor Boone, Georgios Piliouras
Replicator dynamics, the continuous-time analogue of Multiplicative Weights Updates, is the main dynamic in evolutionary game theory. In simple evolutionary zero-sum games, such as…
A Peek into the Unobservable: Hidden States and Bayesian Inference for the Bitcoin and Ether Price Series
Constandina Koki, Stefanos Leonardos, Georgios Piliouras
Conventional financial models fail to explain the economic and monetary properties of cryptocurrencies due to the latter's dual nature: their usage as financial assets on the one s…
Multiagent Evaluation under Incomplete Information
Mark Rowland, Shayegan Omidshafiei, Karl Tuyls +4
This paper investigates the evaluation of learned multiagent strategies in the incomplete information setting, which plays a critical role in ranking and training of agents. Tradit…
Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent
James P. Bailey, Gauthier Gidel, Georgios Piliouras
Gradient descent is arguably one of the most popular online optimization methods with a wide array of applications. However, the standard implementation where agents simultaneously…
Broken Detailed Balance and Non-Equilibrium Dynamics in Noisy Social Learning Models
Tushar Vaidya, Thiparat Chotibut, Georgios Piliouras
We propose new Degroot-type social learning models with feedback in a continuous time, to investigate the effect of a noisy information source on consensus formation in a social ne…
First-order methods almost always avoid saddle points: the case of vanishing step-sizes
Ioannis Panageas, Georgios Piliouras, Xiao Wang
In a series of papers \cite{LSJR16, PP17, LPP}, it was established that some of the most commonly used first order methods almost surely (under random initializations) and with ste…
PREStO: A Systematic Framework for Blockchain Consensus Protocols
Stefanos Leonardos, Daniel Reijsbergen, Georgios Piliouras
The rapid evolution of blockchain technology has brought together stakeholders from fundamentally different backgrounds. The result is a diverse ecosystem, as exemplified by the de…
The route to chaos in routing games: When is Price of Anarchy too optimistic?
Thiparat Chotibut, Fryderyk Falniowski, Michał Misiurewicz +1
Routing games are amongst the most studied classes of games. Their two most well-known properties are that learning dynamics converge to equilibria and that all equilibria are appr…
Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in Zero-Sum Games
Yun Kuen Cheung, Georgios Piliouras
We establish that algorithmic experiments in zero-sum games "fail miserably" to confirm the unique, sharp prediction of maxmin equilibration. Contradicting nearly a century of econ…
Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes
James P. Bailey, Georgios Piliouras
We show for the first time, to our knowledge, that it is possible to reconcile in online learning in zero-sum games two seemingly contradictory objectives: vanishing time-average r…
Oceanic Games: Centralization Risks and Incentives in Blockchain Mining
Nikos Leonardos, Stefanos Leonardos, Georgios Piliouras
To participate in the distributed consensus of permissionless blockchains, prospective nodes -- or miners -- provide proof of designated, costly resources. However, in contrast to…
Multi-Agent Learning in Network Zero-Sum Games is a Hamiltonian System
James P. Bailey, Georgios Piliouras
Zero-sum games are natural, if informal, analogues of closed physical systems where no energy/utility can enter or exit. This analogy can be extended even further if we consider ze…
Weighted Voting on the Blockchain: Improving Consensus in Proof of Stake Protocols
Stefanos Leonardos, Daniel Reijsbergen, Georgios Piliouras
Proof of Stake (PoS) protocols rely on voting mechanisms to reach consensus on the current state. If an enhanced majority of staking nodes, also called validators, agree on a propo…
Incentives in Ethereum's Hybrid Casper Protocol
Vitalik Buterin, Daniel Reijsbergen, Stefanos Leonardos +1
We present an overview of hybrid Casper the Friendly Finality Gadget (FFG): a Proof-of-Stake checkpointing protocol overlaid onto Ethereum's Proof-of-Work blockchain. We describe i…
-Rank: Multi-Agent Evaluation by Evolution
Shayegan Omidshafiei, Christos Papadimitriou, Georgios Piliouras +7
We introduce -Rank, a principled evolutionary dynamics methodology for the evaluation and ranking of agents in large-scale multi-agent interactions, grounded in a novel dynamica…
Short-distance commuters in the smart city
Francisco Benita, Garvit Bansal, Georgios Piliouras +1
This study models and examines commuter's preferences for short-distance transportation modes, namely: walking, taking a bus or riding a metro. It is used a unique dataset from a l…
Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
Yasin Yazıcı, Bruno Lecouat, Chuan-Sheng Foo +4
We propose a GAN design which models multiple distributions effectively and discovers their commonalities and particularities. Each data distribution is modeled with a mixture of $…