arXiv research

New algorithms improve dueling bandit performance in multiplayer settings.

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 RL algorithms learn QSE from strategic feedbacks with sample efficiency.

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,…

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

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.

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

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

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.

New mechanism designs regulate herding in financial markets.

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

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.

Implementing large-scale information and communication technology (IT) projects carries large risks and easily might disrupt operations, waste taxpayers' money, and create negative publicity. Because of the high risks it is important that government leaders manage the attendant risks. We analysed a sample of 1,355 publ…

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…

Advances FTPL results for bandit problems with unbounded perturbations.

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.

The paper proves an obstruction to immersed curves with specific curvature.

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

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

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.

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.

Distributed learning systems have enabled training large-scale models over large amount of data in significantly shorter time. In this paper, we focus on decentralized distributed deep learning systems and aim to achieve differential privacy with good convergence rate and low communication cost. To achieve this goal, w…

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

Optimal bounds on regret and constraint violation in adversarial COCO.

Improved FTPL algorithm reduces regret in predictable minimax games.

Mutation improves FTRL convergence in zero-sum games.

Unified algorithm for linear bandits with improved regret bound.

New algorithm expands FTRL framework with improved worst-case regret bounds.

New algorithm reduces individual regret and communication costs in cooperative bandits.

Algorithm optimizes functions without parameters, converging to global minima.

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

Black-Scholes (BS) is the standard mathematical model for option pricing in financial markets. Option prices are calculated using an analytical formula whose main inputs are strike (at which price to exercise) and volatility. The BS framework assumes that volatility remains constant across all strikes, however, in prac…

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

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

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…

Follow-the-Leader (FTL) is an intuitive sequential prediction strategy that guarantees constant regret in the stochastic setting, but has terrible performance for worst-case data. Other hedging strategies have better worst-case guarantees but may perform much worse than FTL if the data are not maximally adversarial. We…

Develops a Best-of-Both-Worlds algorithm for linear contextual bandits with Tsallis entropy.