arXiv research

Two new feature selection methods improve breast cancer diagnosis accuracy.

Study proposes hybrid machine learning models for crop yield prediction.

Gradient Descent (GD) approximators often fail in the solution space with multiple scales of convexities, i.e., in subspace learning and neural network scenarios. To handle that, one solution is to run GD multiple times from different randomized initial states and select the best solution over all experiments. However,…

Prediction models in mobility and transportation maintenance systems have been dramatically improved through using machine learning methods. This paper proposes novel machine learning models for intelligent road inspection. The traditional road inspection systems based on the pavement condition index (PCI) are often as…

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…

We study online convex optimization in a setting where the learner seeks to minimize the sum of a per-round hitting cost and a movement cost which is incurred when changing decisions between rounds. We prove a new lower bound on the competitive ratio of any online algorithm in the setting where the costs are $m$-strong…

New framework promotes reproducible, domain-agnostic reinforcement learning algorithms.

We consider online algorithms under both the competitive ratio criteria and the regret minimization one. Our main goal is to build a unified methodology that would be able to guarantee both criteria simultaneously. For a general class of online algorithms, namely any Metrical Task System (MTS), we show that one can sim…

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

Market competition depends on computational complexity, P != NP makes it impossible.

New algorithm uses imperfect advice to improve online bipartite matching performance.

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…

New algorithm for competing influence spread in unknown networks.

AlgoPerf competition evaluates neural network training speed-ups.

New algorithm handles bandit problems under translations and scales.

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

In this study, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of reinforcement learning (RL) in competition tasks. Within the actor-critic RL, we introduce multiple cooperative critics from two levels of the hierarchy and propose a reinforcement learnin…

We consider a novel multi-armed bandit framework where the rewards obtained by pulling the arms are functions of a common latent random variable. The correlation between arms due to the common random source can be used to design a generalized upper-confidence-bound (UCB) algorithm that identifies certain arms as $non-c…

Paper tackles online optimization with memory and competitive control.

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

MineRL Competition reduced reinforcement learning sample needs.

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

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

Paper tackles AI driving competition challenges with mixed simulation and real-world data.

In this paper, we study a certain class of online optimization problems, where the goal is to maximize a function that is not necessarily concave and satisfies the Diminishing Returns (DR) property under budget constraints. We analyze a primal-dual algorithm, called the Generalized Sequential algorithm, and we obtain t…

Improved resource allocation method reduces procurement costs.

Competition aims to develop sample-efficient reinforcement learning methods.

HMCNAS generates competitive neural architectures without human-defined parameters.

This is a report for reproducibility challenge of NeurlIPS 2019 on the paper Competitive Gradient Descent (Schafer et al., 2019). The paper introduces a novel algorithm for the numerical computation of Nash equilibria of competitive two-player games. It avoids oscillatory and divergent behaviours seen in alternating gr…

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…

Algorithm for decentralized competition among adaptive agents.

Adaptive volatility method improves probabilistic financial forecasting.

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

Model analyzes competitive pricing strategies in large markets of perishable products.

Algorithm provides online learning guarantees against general comparators in full and bandit feedback.

We study online optimization in a setting where an online learner seeks to optimize a per-round hitting cost, which may be non-convex, while incurring a movement cost when changing actions between rounds. We ask: \textit{under what general conditions is it possible for an online learner to leverage predictions of futur…

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

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

New algorithms predict causal links better than traditional methods in time series data.

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

This research proposes the econophysics kinetic market model as an evolutionary algorithm's instance. The immediate results from this proposal is a new replacement rule for family competition genetic algorithms. It also represents a starting point to adding evolvable entities to kinetic market models.

Paper refutes EM convergence theory and introduces a new EM algorithm.

Combines gradient-based and competitive learning for unsupervised feature extraction.

New algorithm improves self-play reinforcement learning for competitive games.

Study examines how traders with asymmetric information and adaptive learning strategies affect market efficiency.

Algorithm converges to Nash equilibria in competitive games.

Efficiently recovers piecewise linear functions from noisy samples.

A new method for analyzing product competition using low-dimensional embeddings.