65 citations · 169 across the 14 of their papers we have counts for
17 papers
Conic-Lifting for Learning-rate-free Convex Optimization
Julien Grand-Clément, Joon Kwon, Francesco Orabona
A central topic in online and stochastic optimization is to design algorithms that do not require tuning of hyperparameters. Successful strategies in online learning include AdaGra…
Sharper bounds on the thresholds for sensitive and Blackwell optimality
Xavier Allamigeon, Stéphane Gaubert, Julien Grand-Clément +1
In perfect-information two-player stochastic games, the notions of Blackwell and sensitive optimality provide generalizations of the classical mean-payoff optimality and discount o…
Regret Matching+: (In)Stability and Fast Convergence in Games
Gabriele Farina, Julien Grand-Clément, Christian Kroer +2
Regret Matching+ (RM+) and its variants are important algorithms for solving large-scale games. However, a theoretical understanding of their success in practice is still a mystery…
Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor
Julien Grand-Clément, Marek Petrik
We introduce the Blackwell discount factor for Markov Decision Processes (MDPs). Classical objectives for MDPs include discounted, average, and Blackwell optimality. Many existing…
On the convex formulations of robust Markov decision processes
Julien Grand-Clément, Marek Petrik
Robust Markov decision processes (MDPs) are used for applications of dynamic optimization in uncertain environments and have been studied extensively. Many of the main properties a…
The Best Decisions Are Not the Best Advice: Making Adherence-Aware Recommendations
Julien Grand-Clément, Jean Pauphilet
Many high-stake decisions follow an expert-in-loop structure in that a human operator receives recommendations from an algorithm but is the ultimate decision maker. Hence, the algo…
Solving optimization problems with Blackwell approachability
Julien Grand-Clément, Christian Kroer
We introduce the Conic Blackwell Algorithm (CBA) regret minimizer, a new parameter- and scale-free regret minimizer for general convex sets. CBA is based on Blackwell a…
Interpretable Machine Learning for Resource Allocation with Application to Ventilator Triage
Julien Grand-Clément, You Hui Goh, Carri Chan +2
Rationing of healthcare resources is a challenging decision that policy makers and providers may be forced to make during a pandemic, natural disaster, or mass casualty event. Well…
Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving
Julien Grand-Clément, Christian Kroer
We develop new parameter-free and scale-free algorithms for solving convex-concave saddle-point problems. Our results are based on a new simple regret minimizer, the Conic Blackwel…
From Convex Optimization to MDPs: A Review of First-Order, Second-Order and Quasi-Newton Methods for MDPs
Julien Grand-Clément
In this paper we present a review of the connections between classical algorithms for solving Markov Decision Processes (MDPs) and classical gradient-based algorithms in convex opt…
First-Order Methods for Wasserstein Distributionally Robust MDP
Julien Grand-Clément, Christian Kroer
Markov decision processes (MDPs) are known to be sensitive to parameter specification. Distributionally robust MDPs alleviate this issue by allowing for \emph{ambiguity sets} which…
Scalable First-Order Methods for Robust MDPs
Julien Grand-Clément, Christian Kroer
Robust Markov Decision Processes (MDPs) are a powerful framework for modeling sequential decision-making problems with model uncertainty. This paper proposes the first first-order…
Robust Policies For Proactive ICU Transfers
Julien Grand-Clement, Carri W. Chan, Vineet Goyal +1
Patients whose transfer to the Intensive Care Unit (ICU) is unplanned are prone to higher mortality rates than those who were admitted directly to the ICU. Recent advances in machi…
A First-Order Approach To Accelerated Value Iteration
Vineet Goyal, Julien Grand-Clement
Markov decision processes (MDPs) are used to model stochastic systems in many applications. Several efficient algorithms to compute optimal policies have been studied in the litera…
The operator approach to entropy games
Marianne Akian, Stéphane Gaubert, Julien Grand-Clément +1
Entropy games and matrix multiplication games have been recently introduced by Asarin et al. They model the situation in which one player (Despot) wishes to minimize the growth rat…
Robust Markov Decision Process: Beyond Rectangularity
Vineet Goyal, Julien Grand-Clément
We consider a robust approach to address uncertainty in model parameters in Markov Decision Processes (MDPs), which are widely used to model dynamic optimization in many applicatio…
Log-sum-exp neural networks and posynomial models for convex and log-log-convex data
Giuseppe C. Calafiore, Stephane Gaubert, Corrado Possieri
We show in this paper that a one-layer feedforward neural network with exponential activation functions in the inner layer and logarithmic activation in the output neuron is an uni…