
Solving MinMax Optimization with Hidden Structure via Gradient Descent Ascent
Many recent AI architectures are inspired by zerosum games, however, th...
read it

Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving ZeroSum Games
The predominant paradigm in evolutionary game theory and more generally ...
read it

ExplorationExploitation in MultiAgent Learning: Catastrophe Theory Meets Game Theory
Explorationexploitation is a powerful and practical tool in multiagent...
read it

Exploring the Predictability of Cryptocurrencies via Bayesian Hidden Markov Models
In this paper, we consider a variety of multistate Hidden Markov models...
read it

Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent
We consider a natural model of online preference aggregation, where sets...
read it

Noregret learning and mixed Nash equilibria: They do not mix
Understanding the behavior of noregret dynamics in general Nplayer gam...
read it

DataDriven Models of Selfish Routing: Why Price of Anarchy Does Depend on Network Topology
We investigate traffic routing both from the perspective of real world d...
read it

Catastrophe by Design in Population Games: Destabilizing Wasteful Lockedin Technologies
In multiagent environments in which coordination is desirable, the hist...
read it

Chaos, Extremism and Optimism: Volume Analysis of Learning in Games
We present volume analyses of Multiplicative Weights Updates (MWU) and O...
read it

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
In this paper we investigate the Follow the Regularized Leader dynamics ...
read it

Smooth markets: A basic mechanism for organizing gradientbased learners
With the success of modern machine learning, it is becoming increasingly...
read it

Efficiently avoiding saddle points with zero order methods: No gradients required
We consider the case of derivativefree algorithms for nonconvex optimi...
read it

Poincaré Recurrence, Cycles and Spurious Equilibria in GradientDescentAscent for NonConvex NonConcave ZeroSum Games
We study a wide class of nonconvex nonconcave minmax games that gener...
read it

From Darwin to Poincaré and von Neumann: Recurrence and Cycles in Evolutionary and Algorithmic Game Theory
Replicator dynamics, the continuoustime analogue of Multiplicative Weig...
read it

Multiagent Evaluation under Incomplete Information
This paper investigates the evaluation of learned multiagent strategies ...
read it

Finite Regret and Cycles with Fixed StepSize via Alternating Gradient DescentAscent
Gradient descent is arguably one of the most popular online optimization...
read it

PREStO: A Systematic Framework for Blockchain Consensus Protocols
The rapid evolution of the blockchain community has brought together sta...
read it

The route to chaos in routing games: Population increase drives perioddoubling instability, chaos & inefficiency with Price of Anarchy equal to one
We study a learning dynamic model of routing (congestion) games to explo...
read it

Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in ZeroSum Games
We establish that algorithmic experiments in zerosum games "fail misera...
read it

Fast and Furious Learning in ZeroSum Games: Vanishing Regret with NonVanishing Step Sizes
We show for the first time, to our knowledge, that it is possible to rec...
read it

Oceanic Games: Centralization Risks and Incentives in Blockchain Mining
To participate in the distributed consensus of permissionless blockchain...
read it

Weighted Voting on the Blockchain: Improving Consensus in Proof of Stake Protocols
Proof of Stake (PoS) protocols rely on voting mechanisms to reach consen...
read it

Incentives in Ethereum's Hybrid Casper Protocol
We present an overview of hybrid Casper the Friendly Finality Gadget (FF...
read it

MultiAgent Learning in Network ZeroSum Games is a Hamiltonian System
Zerosum games are natural, if informal, analogues of closed physical sy...
read it

αRank: MultiAgent Evaluation by Evolution
We introduce αRank, a principled evolutionary dynamics methodology, for...
read it

Shortdistance commuters in the smart city
This study models and examines commuter's preferences for shortdistance...
read it

Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
We propose a GAN design which models multiple distributions effectively ...
read it

Optimistic mirror descent in saddlepoint problems: Going the extra (gradient) mile
Owing to their connection with generative adversarial networks (GANs), s...
read it

Mirror descent in saddlepoint problems: Going the extra (gradient) mile
Owing to their connection with generative adversarial networks (GANs), s...
read it

The Unusual Effectiveness of Averaging in GAN Training
We show empirically that the optimal strategy of parameter averaging in ...
read it

Rethinking Blockchain Security: Position Paper
Blockchain technology has become almost as famous for incidents involvin...
read it

Wealth Inequality and the Price of Anarchy
Price of anarchy quantifies the degradation of social welfare in games d...
read it

Learning Dynamics and the CoEvolution of Competing Sexual Species
We analyze a stylized model of coevolution between any two purely compe...
read it

Firstorder Methods Almost Always Avoid Saddle Points
We establish that firstorder methods avoid saddle points for almost all...
read it

Cycles in adversarial regularized learning
Regularized learning is a fundamental technique in online optimization, ...
read it

Routing Games in the Wild: Efficiency, Equilibration and Regret (LargeScale Field Experiments in Singapore)
Routing games are amongst the most well studied domains of game theory. ...
read it

Truly Multimodal YouTube8M Video Classification with Video, Audio, and Text
The YouTube8M video classification challenge requires teams to classify...
read it

Learning Agents in BlackScholes Financial Markets: Consensus Dynamics and Volatility Smiles
BlackScholes (BS) is the standard mathematical model for option pricing...
read it
Georgios Piliouras
is this you? claim profile
Assistant Professor at Engineering Systems and Design Singapore University of Technology and Design (SUTD)