arXiv research

FTPL with Fréchet perturbation achieves near optimal regret bounds for m-set semi-bandit problems.

Advances FTPL results for bandit problems with unbounded perturbations.

Paper optimizes FTPL for adversarial and stochastic bandits with specific tail distributions.

We study the problem of online learning with non-convex losses, where the learner has access to an offline optimization oracle. We show that the classical Follow the Perturbed Leader (FTPL) algorithm achieves optimal regret rate of $O(T^{-1/2})$ in this setting. This improves upon the previous best-known regret rate of…

Adaptive learning rates improve FTPL's BOBW guarantees in bandit problems.

FTPL policy achieves best-of-both-worlds regret in decoupled bandits with reduced computational cost.

Paper analyzes FTPL's effectiveness in combinatorial semi-bandit problems.

New algorithm optimizes multi-armed bandits with low computational cost.

Proposes a new training algorithm for zero-sum games to avoid convergence issues.

Unified algorithm for linear bandits with improved regret bound.

Improved FTPL algorithm reduces regret in predictable minimax games.

We analyze linear McKean-Vlasov forward-backward SDEs arising in leader-follower games with mean-field type control and terminal state constraints on the state process. We establish an existence and uniqueness of solutions result for such systems in time-weighted spaces as well as a {convergence} result of the solution…

FTPL method shows near-optimal regret bounds for AMDPs with bandit feedback.

This paper improves FTPL algorithm for semi-bandit problems with best-of-both-worlds guarantees.

New algorithm reduces online learning iterations by a factor of T^2/3.

Characterizes preferences for decision-making under uncertainty using a leader-follower game model.

We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.

New algorithm reduces regret in online learning for piecewise continuous functions.

New algorithm reduces prediction errors across various loss functions.

We show a principled way of deriving online learning algorithms from a minimax analysis. Various upper bounds on the minimax value, previously thought to be non-constructive, are shown to yield algorithms. This allows us to seamlessly recover known methods and to derive new ones. Our framework also captures such "unort…

Optimal multiclass U-calibration error found to be Θ(√KT).

New RL algorithms learn QSE from strategic feedbacks with sample efficiency.

Mutation improves FTRL convergence in zero-sum games.

The online problem of computing the top eigenvector is fundamental to machine learning. In both adversarial and stochastic settings, previous results (such as matrix multiplicative weight update, follow the regularized leader, follow the compressed leader, block power method) either achieve optimal regret but run slow,…

New algorithms handle unpredictable actions in sequential learning.

Investors with asymmetric information play a game to optimize their portfolios.

New algorithms adapt to friendly environments in online learning.

In this note, we present a version of the Thompson sampling algorithm for the problem of online linear generalization with full information (i.e., the experts setting), studied by Kalai and Vempala, 2005. The algorithm uses a Gaussian prior and time-varying Gaussian likelihoods, and we show that it essentially reduces …

Neural operators approximate Stackelberg game solutions.

Study of $2 imes 2$ zero-sum games with noisy observations and commitments.

Game theory approach to predicting and responding to interventions based on causal relationships.

Coop-FTPL algorithm minimizes network regret in semi-bandit settings.

CB-RL solves complex decision-making problems with contextual information and exogenous events.

Recent work on follow the perturbed leader (FTPL) algorithms for the adversarial multi-armed bandit problem has highlighted the role of the hazard rate of the distribution generating the perturbations. Assuming that the hazard rate is bounded, it is possible to provide regret analyses for a variety of FTPL algorithms f…

New mechanism designs regulate herding in financial markets.

Using a two-point correlation technique, we study emergence of market efficiency in the emergent Russian futures market by focusing on lagged correlations. The correlation strength of leader-follower effects in the lagged inter-market correlations on the hourly time frame is seen to be significant initially (2009-2011)…

SLHF uses sequential game theory to optimize preferences from human feedback.

Paper studies zero-sum games with noisy observations and identifies equilibrium conditions.

We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a theoretical framework for the agent to optimize in the space of rewards consist…

We study a general online linear optimization problem(OLO). At each round, a subset of objects from a fixed universe of $n$ objects is chosen, and a linear cost associated with the chosen subset is incurred. To measure the performance of our algorithms, we use the notion of regret which is the difference between the to…

New methods improve online matrix optimization with reduced computational cost.

FPML algorithm reduces regret by limiting the number of arms chosen per round.

New aggregation strategy handles unbounded losses with regret bounds.

The paper explores how regularization can lead to convergence in imperfect information games.

New RL algorithms find SNE in Markov games with myopic followers.

New algorithms improve dueling bandit performance in multiplayer settings.

Communities in social networks or graphs are sets of well-connected, overlapping vertices. The effectiveness of a community detection algorithm is determined by accuracy in finding the ground-truth communities and ability to scale with the size of the data. In this work, we provide three contributions. First, we show t…

AMM finds optimal contract for LPs to maximize order flow.