arXiv research

Model predicts growth competition on curved surfaces.

Paper tackles online optimization with memory and competitive control.

Challenge encourages reproducible deep learning methods.

Proposes CoPO, a new policy optimization method for competitive games.

Develops a learning model predictive controller for competitive racing.

OMGD algorithm optimizes online convex optimization with switching costs and delayed gradients.

Data competitions rely on real-time leaderboards to rank competitor entries and stimulate algorithm improvement. While such competitions have become quite popular and prevalent, particularly in supervised learning formats, their implementations by the host are highly variable. Without careful planning, a supervised lea…

Model predicts competition between similar products in sales.

Motivated by applications in recommender systems, web search, social choice and crowdsourcing, we consider the problem of identifying the set of top $K$ items from noisy pairwise comparisons. In our setting, we are non-actively given $r$ pairwise comparisons between each pair of $n$ items, where each comparison has noi…

New particle-based method improves semi-supervised learning robustness to label noise.

New algorithms achieve optimal performance in online convex optimization with strong convexity and squared $\ell_2$ norms.

The paper analyzes optimal stock position-building strategies in competitive markets.

New Soft Actor-Critic for discrete actions.

Improved model accuracy can reduce overall user accuracy in competitive markets.

Paper analyzes strategic underreporting in competitive insurance markets.

We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018. This data driven competition asked participants to develop computer programs capable of solving supervised learning problems where the i.i.d. assumption did not hold. Large data sets w…

We consider Online Convex Optimization (OCO) in the setting where the costs are $m$-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive rat…

This work bridges competitive learning with gradient-based learning for faster feature extraction.

Algorithm for decentralized competition among adaptive agents.

Geometric theory explains substitutability in market outcomes based on production constraints.

This work tackles representation learning by introducing stochastic competition-based activations.

Paper studies competitive networks where teams aim to minimize their own objectives, adapting to each other's strategies.

Modeling gas fee competition in decentralized exchanges to optimize arbitrage profits.

Algorithm finds small confidence sets for arbitrary distributions.

Most sales applications are characterized by competition and limited demand information. For successful pricing strategies, frequent price adjustments as well as anticipation of market dynamics are crucial. Both effects are challenging as competitive markets are complex and computations of optimized pricing adjustments…

Adaptive learning rate improves FTRL's performance in online learning.

State-space models win a forecasting competition for unstable data.

The paper develops algorithms for competitive RL in partially observable MGs.

A game-theoretic analysis of DEX competition through dynamic trading fees.

We propose a simple dynamical model of the formation of production networks among monopolistically competitive firms. The model subsumes the standard general equilibrium approach à la Arrow-Debreu but displays a wide set of potential dynamic behaviors. It robustly reproduces key stylized facts of firms' demographics. O…

This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the learning rate. MI between the output layer and true outcomes is used to dynamically set the learning rate of the network through the trainin…

The study analyzes games and social hierarchies, incorporating luck and depth of competition.

A new method compares image classifiers using adaptive sampling of natural images.

New paper finds strategic trade centralization benefits firms, while naive centralization often harms them.

New algorithms prove self-play can be effective in competitive RL.

This paper uses NARX neural networks for macroeconomic forecasting and goal setting.

PAC-Bayes with Backprop trains neural nets with competitive error estimates and tighter risk bounds.

A fair reward system boosts participation in federated learning.

Study shows how competition affects learning in matching markets, proving it's possible to balance stability, fairness, and regret.

New algorithm for competing influence spread in unknown networks.

Study $N$-player and mean-field games in Itô-diffusion markets with competitive or homophilous interactions.

New model considers unfairness complaints to ensure multiple fairness criteria.

Study examines pricing strategies in competitive supply chains with discrete prices.

GNNRank uses neural networks to learn global rankings from competition match data.

The paper improves competitive and dynamic regret bounds for smoothed online learning.

The paper analyzes trading strategies in a competitive market with incomplete information.

Private cancer prediction model trained on federated genomic data.

Study many-player investment-consumption games with power FPPs, finding market-risk preference affects consumption.